CA2029540C - Solder joint locator - Google Patents
Solder joint locatorInfo
- Publication number
- CA2029540C CA2029540C CA002029540A CA2029540A CA2029540C CA 2029540 C CA2029540 C CA 2029540C CA 002029540 A CA002029540 A CA 002029540A CA 2029540 A CA2029540 A CA 2029540A CA 2029540 C CA2029540 C CA 2029540C
- Authority
- CA
- Canada
- Prior art keywords
- pixels
- determining
- image
- window
- center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/06—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and measuring the absorption
- G01N23/083—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and measuring the absorption the radiation being X-rays
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/06—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and measuring the absorption
- G01N23/18—Investigating the presence of flaws defects or foreign matter
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Abstract
ABSTRACT OF THE DISCLOSURE
A system (82) and method for locating features in an image. In the preferred embodiments, the present invention accepts as input a tilted view X-ray image of a PC board (10), as well as expected locations of solder joints (18) in the PC board (10). The present invention then determines the actual center locations (32) of these solder joints (18) by defining windows within the image and checking individual areas within the window, to see if they fall below a predetermined threshold. In addition, the system (82) determines if these pixels are connected to other pixels that have been previously determined to be part of the solder joint (18). Finally, the system (82) determines the center of the group of pixels determined to be part of the solder joint and displays the coordinate location of this center.
A system (82) and method for locating features in an image. In the preferred embodiments, the present invention accepts as input a tilted view X-ray image of a PC board (10), as well as expected locations of solder joints (18) in the PC board (10). The present invention then determines the actual center locations (32) of these solder joints (18) by defining windows within the image and checking individual areas within the window, to see if they fall below a predetermined threshold. In addition, the system (82) determines if these pixels are connected to other pixels that have been previously determined to be part of the solder joint (18). Finally, the system (82) determines the center of the group of pixels determined to be part of the solder joint and displays the coordinate location of this center.
Description
2~9~0 SOLDER JOINT LOC~TOR
1. Technical Field This invention relates to systems and methods for analyzing images, and more particularly, to system for locating features in an image.
2. Discussion One of the primary goals of image processing is to automatically recognize certain features or textures within an image. in typical image processing systems, fields of picture elements (pixels) are automatically scanned, and some algorithm is chosen to analyze the image to recognize particular features.
One approach is to arbitrarily select a given region, or window, in the image and to analyze the pixels within the window to detect the particular features.
For example, one previous approach is to calculate a centroid, or weighted centroid, on all of the pixels within a window that are below a certain fixed threshold, where the desired feature is known to have an intensity below the threshold. This kind of approach, however, often causes adjacent objects, that are not sought to be detected, to add errors to the calculation when they fall below the threshold. In addition, often such thresholds must be set somewhat ~k :
:- ' ~2~5~
1 higher than desirable to account for variability in the desired features. This higher intensity threshold often can allow for even more errors from adjacent objects. Thus, it would be desirable to provide an image processor which is less prone to detect unwanted features adjacent to the desired features to more accurately analyze the desired features. In addition, it would be desirable to provide an image processor in which the threshold used to detect the features is adaptable to particular portions of the image, and not fixed. In this way the threshold may be set more closely approximate the intensity of the feature.
One image processing application of particular concern, is the task of automatically inspecting printed circuit boards. This task is made more complicated because the mechanical systems employed in the manufacture of printed circuit boards do not always position solder joints in exactly the same place every time. In addition, a the number of features of the board vary from board to board.
An early step in such automatic inspection systems is to analyze an image of the printed circuit board. For example, this may be an X-ray image. As a result of inaccuracies in manufacturing, when an automatic inspection system attempts to inspect a particular feature on the ~oard, such as a solder joint, the physical appearance of the joint in the image does not match from one board to the next, or from one production run to the next. Thus, to accomplish automatic inspection of printed circuit boards, there is needed a way to find the physical position of the joint in an image accurately enough to perform all of the subsequent tests. If the feature, such as the solder joint is not accurately located, the subsequent testing will give faulty results.
"'` ` -2~29~0 1 For example, if the system is looking for an area that should have substantial amounts of solder but the test system is slightly offset so that it does not look at the center of the solder joint, the system may assume that there should be solder where it should not be and classify a good joint as a bad joint.
Conversely, this problem may also cause the system to label a bad joint, a good joint.
Thus, it would be desirable to provide an image processing system which can accurately find the center of features on a printed circuit board, such as solder joints, to improve the accuracy of automatic testing systems.
:
:
, .' ' . - ~ '', -.
~029~0 l SUMMARY OF THE INV~NTION
Pursuant to the present invention, a method and system is provided for automatically detecting features in an image. The system comprises a means for measuring and storing the intensity of pixels in the image, and a means for defining a window within the image. This window is selected so that the center of the window is coincident with the expected center of the feature to be located. The system also includes a means for determining which pixels in the window are below a predetermined upper threshold of intensity. The system also determines if pixels found below the threshold are connected to the center pixel and labels those pixels as feature pixels. Also, the system determines if pixels found to below the threshold are connected to any pixels previously labeled feature pixels, and labels those pixels also feature pixels. Finally, the system determines the ~0 center of the group of feature pixels and displays the coordinate location of this cen~er.
To further improve the ability to recognize desired features, in accordance with a second embodiment of the present invention, there is provided a means for adaptively setting the threshold for each window that is analyzed. This is done by providing a means for measuring the intensity of a solder strip of known thickness in the image. The system then can set a threshold that is equal to this measured intensity of the solder strip. The system further measures the intensity of several pixels in the vicinity of the center pixel and determine the darkest of these pixels. The system then will determine if this darkest pixel is lighter than the previously set threshold. If it is, the system stops because this `` 2~9~9LQ
would mean that the feature ~alls outside the acceptable range. For example, this could mean a defective solder joint. On the other hand, if the darkest pixel is not lighter than the threshold, then a new threshold is set that is equal to the value of this darkest pixel plus a predefined margin. As a result, the threshold used by the system is adapted for each window to be closely calibrated to the particular intensity of the feature to be analyzed.
In this way, there is less likelihood of the system mistakenly identi~ying a nonfeature as a feature.
Other aspects of this invention are as follows:
A system ~or automatically detecting Peatures in an image, said system comprising:
means for measuring the intensity of pixels in said image, each pixel having a coordinate location;
means for storing said measured intensity values;
means for defining a window within said image, the window having one of said predetermined expected feature locations at its center pixel;
means for labeling the center pixel;
means for determining if the intensity of pixels within said window are below a predetermined upper threshold:
means for determining if pixels found to be below said predetermined~upper threshold are connected to the center pixel, and for labelling those pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled, and for labelling those pixels also;
means for determining the center of the group of labeled pixels; and means for displaying the coordinate location oP said center.
~; `~ ``' ,,~, ., :' .. .. ~:
. ~
,... . . . .
2~29~0 5a A system for automatically determining the position of features in an image, said system comprising:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected feature location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to featur0 pixels and for labelling tho~e a~ f~ature pixels; .
means for determining if pixels found to be below ths predetermined upper threshold are connected to any pixels previously labelled ~eature pixels, and labelling those pixels also as feature pixels;
means for determining the center of the group of the feature pixels; and means for displaying the coordinate location of said center.
A system for testing printed circuit boards for solder joint locations by analyzing an X-ray image of the printed circuit board, said system comprlsing:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
~. ~
` 2~29~40 5b means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected joint location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to joint pixels and for labelling those joint pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also joint pixels;
means for determining the center of the group of the joint pixels; and means for displaying the coordinate location of said center.
A method for automatically determining the position of features in an image, said method comprising the steps of:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected feature location at i~s center pixel;
- ' .
:. ~
`^~ 202g~40 5c dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
determining the center of the group of the feature pixels; and displaying the coordinate location of said center.
A method for automatically testing a printed circuit board to determine the position of solder joints in a tilted view X-ray image of the printed circuit joint or circuit board, said method comprising:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected joint location at its center pixel;
dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
determining the average intensity of pixels within each of said sub-windows;
`-~ 2~29~0 5d determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said upper threshold are connected to joint pixels and for labeling those joint pixels;
determining if pixels found to be below the threshold are connected to any pixels previously labeled feature pixels, and labeling those pixels also joint pixels;
determining the center of the group of the joint pixels; and displaying the coordinate location of said center.
BRIEF DESCRIPTION OF THE DP~AWINGS
The various advantages of the present invention will become apparent to one skilled in the art, by reading the following specification and by reference to the drawings in which:
FIG. 1 is a perspective view of a printed circuit board showing portions of the underside in phantom;
FIG. 2 is a perspective view of a portion of the printed circuit board shown in FIG. 1;
FIG. 3 is a flowchart of the process steps to detect solder joints in performed in accordance with the present invention;
FIG. 4 is a flowchart showing the process steps to ~et the adaptive threshold in accordance with the pr~sent invention; and FIG. 5 is a block diagram of a microprocessor controlled version of one embodiment of the present invention.
FIG. 6 is a perspective view of a PC board including two solder joints, the board bein~ tilted 40 from the vertical.
FIG. 7 is a perspective view of a window in the \ board of FIG. 6 including a plurality of subwindows.
, .
. . . . . .
.
- 202~0 The basic approach for locating features in an image according to the present invention, will be illustrated as they are applied to the task of locating solder joints in a PC board for automatic inspection procedures. FIG. 1 illustrates a conventional printed circuit board 10 which is a ~ypical copper clad dielectric material printed wiring board. The circuit board 10 includes a top surface 12 and a bottom surface 14 with conventional conductors 16 etched on both the top and bottom surfaces 12, 14.
The printed circuit board 10 includes a number of plated-through holes 18 which provide electrical continuity between the two sides 12, 14. The plated-through holes 18 are created by drilling a hole through the circuit board 10 and the cylindrical surface formed thereby is plated by a chemical deposition process, and then electro-plated to form the interconnections between the top and bottom layers 12 and 14, or for mounting of electronic parts.
Electrical components may include, for example, integrated circuits 20 or discrete components 22, such as resistors and diodes. These components 20, 22 are generally mounted onto the printed circuit board 10 by placing conductive leads 24 through the plated-through holes 18 so that a portion of the leads 24 extends through the bottom layer 14 of the PC board 10. Next, solder 26 is applied to the plated-through hole 18 and conductive lead 24 to create a solder joint, 28 as best illustrated in FIG. 2. FIG. 2 also illustrates that each solder joint 28 further includes a pair of conductive pads 30 which are in electrical contact with the printed wires 16 and are placed on the top surface 12 as well as the bottom surface 14 of the 2Q~ O
1 printed circuit board 10. The solder 26 if properly applied, fills the plated-through hole 18 and adheres to the pad 28 as well as the component lead 24.
In order to insure that printed circuit boards 10 are properly manufactured, a number of automatic testing systems exist. An initial step in many of these testing procedures is to take an X-ray image of the printed circuit board 10 and then to analyze this image for defects that may be apparent in the image.
Once this analysis is complete, actual testing of electrical continuity and electrical function of the board may then follow. In such automatic testing systems, one of the first tests is to determine with accuracy, the location of solder joints.
A tilted view X-ray image of a portion of PC
board 10 may appear similar to the view in FIG. 2, minus the shading. It will be appreciated that a tilted view is preferable to straight on view since a straight-on, or vertical, view would~reveal the top pad and lower pads 30 superimposed on each other and one would not be able to distinguish the two, as is possible with a tilted view.
For automatic analysis of the X-ray image of the PC board 10, it is desired to locate the center of the solder joint, shown by cross 32 in FIG. 2. Cross 32 therefore ideally lies at the theoretical center of the barrel shaped plated-through hole 18. Thus, the present invention provides a system, and method, for determining this theoretical center of the plated-through hole 18 so that subsequent image processing techniques can be used to analyze, in great detail, the integrity of the solder joint 26. In particular, these procedures will look for defects, such as voids in the solder 26, defects in the pad 30, : . ` .
.. .,, ., . . ~ -8 2~29~0 1 improper placement of the lead 24, empty plated-through holes 18, etc.
In accordance with the present invention, the expected center location 32 is established from known dimensions in the PC board 10 and test X-ray image.
The system in accordance with the present invention will then determine with greater accuracy the true location of the center of the hole 32.
It is assumed that the expected center will be somewhere within the solder joint. If it does not, however, the expected center is so far off that the present invention will probably not be able to find it. For such cases, the present invention will likely detect that something is wrong and will abort the test. See, for example, FIG. 3 and accompanying discussion below.
Referring now to FIG.'s 4, 6 and 7, a method, in accordance with the present invention, for finding the center 32 of a solder joint, will now be described. In block 34 the processing begins. In the first step 36 the tilted view X-ray image 37 of the PC board is received. This image will comprise discrete pixels; in general, the image will contain m x n pixels. Next, the intensity of each pixel is mPasured and this intensity value is stored. (step 38) Next, a "window" 39 is defined such that a predetermined expected solder joint location 41 is at its center. This center pixel 43 is labelled a "joint pixel". (step 40) An ob~ect 45 other than a solder joint 41 is shown in window 39 for purposes of comparison.
It will be appreciated that there will be a desired location for the solder joint in the PC board and that this known location can be coordinated with a given pixel in the image. For Pxample, solder joint locations can be assigned X,Y coordinate locations, and the PC board image can then be related to these ~ coordinate locations to determine which pixel in the :: .
.
....
.
9 2~29~40 1 image is expected to be at the center of each solder joint location.
The upper intensity threshold T is then set.
(step 42) This may be preferably an adaptive threshold which is set in accordance with the process described below in connection with FIG. 4. However, a nonadaptive threshold could be set which would simply be an estimated upper limit of the possible intensity value for a joint pixel. Next, the window 39 is subdivided into R subwindows. (step 44) This step speeds up the processing by analyzing groups of pixels rather than each pixel individually. However, it will be appreciated that individual pixels could be analyzed, and in some applications it may be desirable to do so depending on the desired resolution and speed of processing.
In accordance with a preferred embodiment, the subwindows consist of a square area within the windo~
of nine pixels having a single pixel at its center.
Next, each subwindow is analyzed individually until the entire window has been processed. It may be accomplished by assigning each subwindow an index number N from one to R. This index is first set to zero (step 46) and is then incremented by one each time step 48 is carried out. Next, the average intensity of all the pixels in the subwindow N is measured. (step 50) Then, the average intensity of the subwindow is compared to the upper threshold T in step 52. If this average intensity is not less than or equal to T, then the subwindow is considered to be not part of the solder joint and the process proceeds to step 54 to determine if there are any further subwindows that have not yet been processed. If there are, that is, if N is not equal to R, step 54 directs --` 2~29~Q
1 the process back to step 48 to proceed to the next numerically consecutive subwindow.
If, on the other hand, step 52 determines that the average intensity is less than or equal to T, step 56 is performed, which determines whether the subwindow N is "connected" to any "joint pixels". It will be appreciated that a number of different -criteria could be used to determine if pixels are "connected." Preferably this criteria will require more than a single side to be connected, or touching.
This will avoid the connection of two separate features by a thin string of pixels. For example, the criteria preferred is that three sides touch to establish connectedness. It should also be noted that in step 40, the center pixel was labeled a joint pixel, and that the processing will proceed on subwindows that are "connected" to the center pixel and proceed outward until all of the subwindows in the window have been analyzed. If, in step 56 it is determined that the subwindow N, which had its intensity less than or equal to T, is not connected a "joint pixel", then that subwindow is considered to be not part of the joint. For example, this may represent a dark area corresponding to an electrical component that is not part of the particular solder joint. Alternatively, it may represent a completely different solder joint that is within the window. It should be noted that the other solder joints will be ignored at this point, but will be processed at a later time when a different window is selected having the expected center joint of that solder joint at its center.
Accordingly, step 56, having determined that a window is not connected to a joint window, will direct the system to step 54, where, as described above, it .
.
11 2Q295~0 1 will be detPrmlned whether there are additional subwindows to analyze. If there are, the process will proceed to step 48. If, on the other hand, step 56 determines that the subwindow is connected to a joint pixel, then the pixels in that subwindow is labeled a "joint pixels". (step 58) It will be appreciated that subwindows with pixels labeled "joint pixels", may be connected to the center pixel, or may it be connected to other subwindows previously determined to be connected to the center window, or to other subwindows labeled "joint pixels".
After 58, step 54 is again performed to determined if there are additional subwindows not yet processed. If there are not, that is, if N is equal to R, then step 60 is performed to begin a centering routine. That is, the above steps will have determined all subwindows that are connected to each other and below or equal to threshold T and labeled those pixels joint pixels. The subwindows at this p~int, should define the generally cylindrical or barrel shape of the solder joint 28. It will be appreciated that given this cylindrical shape, one can easily determine the center of this shape. For example, a procedure may employ averaging techniques whereby the average location is determined. In particular, such a centering technique may proceed as follows. Initially, each subwindow is assigned an X-Y
value corresponding to the center of the subwindow.
The X,Y value of all "joint" subwindows are then 3~ averaged separately to given an overall joint ~,Y.
Optionally, additional procedures may be performed to check the shape of the group of joint pixels before the centering routine is begun. For example, in accordance with conventional image processing "' ;
12 2029~0 1 techniques, the joint pixels may be analyzed to see if they generally form a rectangular shape.
Having found the center of the solder joint 41, the coordinate~ of the center pixel ~3 are now determined and are transmitted for display, or for use by subsequent processing systems (Step 62). At this point the processing, is complete (step 64). All of the above steps, 34 - 64, may be repeated for other solder joints 28 in the PC board 10. Alternatively, different features besides solder joints, may be analyzed in accordance with the above steps.
Referring now to FIG. 4, the preferred method for setting an adaptive threshold, in accordance with step 42 above, will now be described. The procedure for setting the adaptive threshold begins with the measurement of the intensity of a calibration strip of the solder on the PC board 10. (steps 66 and 68) This calibration strip is preferably contained within the window defined in step 40 of FIG. 3. This is because the threshold is reset for each window.
Alternatively, since the adaptive threshold also depends on the intensity in the neighborhood of the center pixel, there could be only a single calibration strip in the entire PC board, in which case the measurement taken in step ~8 is used for each window in the entire image.
The threshold is initially set to be the intensity of the solder strip measured in step 68 (step 70). This is because the calibration strip, measured in step 68, is chosen to yield an intensity value that would represent the lightest acceptable value for a solder joint area. Next, measurements are taken of the intensity of several pixels in the neighborhood of the center pixel defined in step 40.
(step 72) Next, the darkest of these pixels is ' ' '~' ~
~, ! ' '' ' ' ." . ' , , ''' ' . ' '' .
". ' ' , , .
~o~ o 1 selected (step 74). The darkest pixel is then compared to the threshold set in step 70. (step 76) If this darkest pixel is lighter than the threshold, the joint is labeled defective. (step 78) This is because the calibration solder strip is as light as a solder joint should be. If it is lighter there is a problem, such as a void in the joint, and the joint is labeled defective and the processing stops as shown in step 78. On the other hand, if the darkest pixel is not found to be lighter in step 76, the threshold is set to a new value which is equal to the darkest pixel plus some predefined constant value, C. (steps 79 and 80) Referring now to FIG. 5, a preferred embodiment of the hardware according to the present invention is shown. A solder joint locator system 82 includes a sensor 84 which may comprise, for example, a CCD array for detecting the intensity of the individual pixels in an image, such as an X-ray image 86 of a PC board.
The information frcm the CCD array is fed along bus 88 to a microcontroller 90. Microcontroller 90 comprises a conventional programmable microprocessor capable of receiving the pixel data ~rom CCD array 84 and storing and processing this information. In particular, microcontroller 90 is programmed to perform all of the steps 34 through 64 in FIG. 3, as well as the adaptive threshold setting steps 66 80 in FIG. 4. Finally, microcontroller 90 is connected, by means of bus 92, to a postprocessing system 94 which uses the coordinate locations of the solder joint centers found by the microcontroller 90 to perform additional tests on the PC board image 86. In addition, direct tests to the actual PC board may then also be performed.
It will be appreciated that in some circumstances desired features will be lighter rather 2~9~0 ~
l than darker than the background. In such cases, the invention will be adapted to set lower thresholds and to look for pixels that are lighter than the lower thresholds. Alternatively, an intensity band, rather than an upper or lower threshold, may be set. In which case the invention may be adapted to look for pixels that fall within this band. It should also be recognized that the joint locator system 82 and the processes described in FIGS 3 and 4, can also be employed in other image processing applications besides locating joints in ~C boards. For instance, the present invention could be used in target acquisition where, for example, the image is an infrared image and the image processing task is tracking of bright spots in the image. The present invention could then be used to sort out and track separate spots in such an image. In general, the present invention can be used in a wide variety of image processing applications where the center of an object in a field is desired and the field is cluttered with other things that will obscure the task of finding the center of the object. While the above description constitutes the preferred embodiments of the present invention, it will be appreciated that the invention is susceptible to modifications, variation and change without departing from the proper scope and fair meaning of the accompanying claims.
. ;' ' ' .
' ,' .
1. Technical Field This invention relates to systems and methods for analyzing images, and more particularly, to system for locating features in an image.
2. Discussion One of the primary goals of image processing is to automatically recognize certain features or textures within an image. in typical image processing systems, fields of picture elements (pixels) are automatically scanned, and some algorithm is chosen to analyze the image to recognize particular features.
One approach is to arbitrarily select a given region, or window, in the image and to analyze the pixels within the window to detect the particular features.
For example, one previous approach is to calculate a centroid, or weighted centroid, on all of the pixels within a window that are below a certain fixed threshold, where the desired feature is known to have an intensity below the threshold. This kind of approach, however, often causes adjacent objects, that are not sought to be detected, to add errors to the calculation when they fall below the threshold. In addition, often such thresholds must be set somewhat ~k :
:- ' ~2~5~
1 higher than desirable to account for variability in the desired features. This higher intensity threshold often can allow for even more errors from adjacent objects. Thus, it would be desirable to provide an image processor which is less prone to detect unwanted features adjacent to the desired features to more accurately analyze the desired features. In addition, it would be desirable to provide an image processor in which the threshold used to detect the features is adaptable to particular portions of the image, and not fixed. In this way the threshold may be set more closely approximate the intensity of the feature.
One image processing application of particular concern, is the task of automatically inspecting printed circuit boards. This task is made more complicated because the mechanical systems employed in the manufacture of printed circuit boards do not always position solder joints in exactly the same place every time. In addition, a the number of features of the board vary from board to board.
An early step in such automatic inspection systems is to analyze an image of the printed circuit board. For example, this may be an X-ray image. As a result of inaccuracies in manufacturing, when an automatic inspection system attempts to inspect a particular feature on the ~oard, such as a solder joint, the physical appearance of the joint in the image does not match from one board to the next, or from one production run to the next. Thus, to accomplish automatic inspection of printed circuit boards, there is needed a way to find the physical position of the joint in an image accurately enough to perform all of the subsequent tests. If the feature, such as the solder joint is not accurately located, the subsequent testing will give faulty results.
"'` ` -2~29~0 1 For example, if the system is looking for an area that should have substantial amounts of solder but the test system is slightly offset so that it does not look at the center of the solder joint, the system may assume that there should be solder where it should not be and classify a good joint as a bad joint.
Conversely, this problem may also cause the system to label a bad joint, a good joint.
Thus, it would be desirable to provide an image processing system which can accurately find the center of features on a printed circuit board, such as solder joints, to improve the accuracy of automatic testing systems.
:
:
, .' ' . - ~ '', -.
~029~0 l SUMMARY OF THE INV~NTION
Pursuant to the present invention, a method and system is provided for automatically detecting features in an image. The system comprises a means for measuring and storing the intensity of pixels in the image, and a means for defining a window within the image. This window is selected so that the center of the window is coincident with the expected center of the feature to be located. The system also includes a means for determining which pixels in the window are below a predetermined upper threshold of intensity. The system also determines if pixels found below the threshold are connected to the center pixel and labels those pixels as feature pixels. Also, the system determines if pixels found to below the threshold are connected to any pixels previously labeled feature pixels, and labels those pixels also feature pixels. Finally, the system determines the ~0 center of the group of feature pixels and displays the coordinate location of this cen~er.
To further improve the ability to recognize desired features, in accordance with a second embodiment of the present invention, there is provided a means for adaptively setting the threshold for each window that is analyzed. This is done by providing a means for measuring the intensity of a solder strip of known thickness in the image. The system then can set a threshold that is equal to this measured intensity of the solder strip. The system further measures the intensity of several pixels in the vicinity of the center pixel and determine the darkest of these pixels. The system then will determine if this darkest pixel is lighter than the previously set threshold. If it is, the system stops because this `` 2~9~9LQ
would mean that the feature ~alls outside the acceptable range. For example, this could mean a defective solder joint. On the other hand, if the darkest pixel is not lighter than the threshold, then a new threshold is set that is equal to the value of this darkest pixel plus a predefined margin. As a result, the threshold used by the system is adapted for each window to be closely calibrated to the particular intensity of the feature to be analyzed.
In this way, there is less likelihood of the system mistakenly identi~ying a nonfeature as a feature.
Other aspects of this invention are as follows:
A system ~or automatically detecting Peatures in an image, said system comprising:
means for measuring the intensity of pixels in said image, each pixel having a coordinate location;
means for storing said measured intensity values;
means for defining a window within said image, the window having one of said predetermined expected feature locations at its center pixel;
means for labeling the center pixel;
means for determining if the intensity of pixels within said window are below a predetermined upper threshold:
means for determining if pixels found to be below said predetermined~upper threshold are connected to the center pixel, and for labelling those pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled, and for labelling those pixels also;
means for determining the center of the group of labeled pixels; and means for displaying the coordinate location oP said center.
~; `~ ``' ,,~, ., :' .. .. ~:
. ~
,... . . . .
2~29~0 5a A system for automatically determining the position of features in an image, said system comprising:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected feature location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to featur0 pixels and for labelling tho~e a~ f~ature pixels; .
means for determining if pixels found to be below ths predetermined upper threshold are connected to any pixels previously labelled ~eature pixels, and labelling those pixels also as feature pixels;
means for determining the center of the group of the feature pixels; and means for displaying the coordinate location of said center.
A system for testing printed circuit boards for solder joint locations by analyzing an X-ray image of the printed circuit board, said system comprlsing:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
~. ~
` 2~29~40 5b means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected joint location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to joint pixels and for labelling those joint pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also joint pixels;
means for determining the center of the group of the joint pixels; and means for displaying the coordinate location of said center.
A method for automatically determining the position of features in an image, said method comprising the steps of:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected feature location at i~s center pixel;
- ' .
:. ~
`^~ 202g~40 5c dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
determining the center of the group of the feature pixels; and displaying the coordinate location of said center.
A method for automatically testing a printed circuit board to determine the position of solder joints in a tilted view X-ray image of the printed circuit joint or circuit board, said method comprising:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected joint location at its center pixel;
dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
determining the average intensity of pixels within each of said sub-windows;
`-~ 2~29~0 5d determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said upper threshold are connected to joint pixels and for labeling those joint pixels;
determining if pixels found to be below the threshold are connected to any pixels previously labeled feature pixels, and labeling those pixels also joint pixels;
determining the center of the group of the joint pixels; and displaying the coordinate location of said center.
BRIEF DESCRIPTION OF THE DP~AWINGS
The various advantages of the present invention will become apparent to one skilled in the art, by reading the following specification and by reference to the drawings in which:
FIG. 1 is a perspective view of a printed circuit board showing portions of the underside in phantom;
FIG. 2 is a perspective view of a portion of the printed circuit board shown in FIG. 1;
FIG. 3 is a flowchart of the process steps to detect solder joints in performed in accordance with the present invention;
FIG. 4 is a flowchart showing the process steps to ~et the adaptive threshold in accordance with the pr~sent invention; and FIG. 5 is a block diagram of a microprocessor controlled version of one embodiment of the present invention.
FIG. 6 is a perspective view of a PC board including two solder joints, the board bein~ tilted 40 from the vertical.
FIG. 7 is a perspective view of a window in the \ board of FIG. 6 including a plurality of subwindows.
, .
. . . . . .
.
- 202~0 The basic approach for locating features in an image according to the present invention, will be illustrated as they are applied to the task of locating solder joints in a PC board for automatic inspection procedures. FIG. 1 illustrates a conventional printed circuit board 10 which is a ~ypical copper clad dielectric material printed wiring board. The circuit board 10 includes a top surface 12 and a bottom surface 14 with conventional conductors 16 etched on both the top and bottom surfaces 12, 14.
The printed circuit board 10 includes a number of plated-through holes 18 which provide electrical continuity between the two sides 12, 14. The plated-through holes 18 are created by drilling a hole through the circuit board 10 and the cylindrical surface formed thereby is plated by a chemical deposition process, and then electro-plated to form the interconnections between the top and bottom layers 12 and 14, or for mounting of electronic parts.
Electrical components may include, for example, integrated circuits 20 or discrete components 22, such as resistors and diodes. These components 20, 22 are generally mounted onto the printed circuit board 10 by placing conductive leads 24 through the plated-through holes 18 so that a portion of the leads 24 extends through the bottom layer 14 of the PC board 10. Next, solder 26 is applied to the plated-through hole 18 and conductive lead 24 to create a solder joint, 28 as best illustrated in FIG. 2. FIG. 2 also illustrates that each solder joint 28 further includes a pair of conductive pads 30 which are in electrical contact with the printed wires 16 and are placed on the top surface 12 as well as the bottom surface 14 of the 2Q~ O
1 printed circuit board 10. The solder 26 if properly applied, fills the plated-through hole 18 and adheres to the pad 28 as well as the component lead 24.
In order to insure that printed circuit boards 10 are properly manufactured, a number of automatic testing systems exist. An initial step in many of these testing procedures is to take an X-ray image of the printed circuit board 10 and then to analyze this image for defects that may be apparent in the image.
Once this analysis is complete, actual testing of electrical continuity and electrical function of the board may then follow. In such automatic testing systems, one of the first tests is to determine with accuracy, the location of solder joints.
A tilted view X-ray image of a portion of PC
board 10 may appear similar to the view in FIG. 2, minus the shading. It will be appreciated that a tilted view is preferable to straight on view since a straight-on, or vertical, view would~reveal the top pad and lower pads 30 superimposed on each other and one would not be able to distinguish the two, as is possible with a tilted view.
For automatic analysis of the X-ray image of the PC board 10, it is desired to locate the center of the solder joint, shown by cross 32 in FIG. 2. Cross 32 therefore ideally lies at the theoretical center of the barrel shaped plated-through hole 18. Thus, the present invention provides a system, and method, for determining this theoretical center of the plated-through hole 18 so that subsequent image processing techniques can be used to analyze, in great detail, the integrity of the solder joint 26. In particular, these procedures will look for defects, such as voids in the solder 26, defects in the pad 30, : . ` .
.. .,, ., . . ~ -8 2~29~0 1 improper placement of the lead 24, empty plated-through holes 18, etc.
In accordance with the present invention, the expected center location 32 is established from known dimensions in the PC board 10 and test X-ray image.
The system in accordance with the present invention will then determine with greater accuracy the true location of the center of the hole 32.
It is assumed that the expected center will be somewhere within the solder joint. If it does not, however, the expected center is so far off that the present invention will probably not be able to find it. For such cases, the present invention will likely detect that something is wrong and will abort the test. See, for example, FIG. 3 and accompanying discussion below.
Referring now to FIG.'s 4, 6 and 7, a method, in accordance with the present invention, for finding the center 32 of a solder joint, will now be described. In block 34 the processing begins. In the first step 36 the tilted view X-ray image 37 of the PC board is received. This image will comprise discrete pixels; in general, the image will contain m x n pixels. Next, the intensity of each pixel is mPasured and this intensity value is stored. (step 38) Next, a "window" 39 is defined such that a predetermined expected solder joint location 41 is at its center. This center pixel 43 is labelled a "joint pixel". (step 40) An ob~ect 45 other than a solder joint 41 is shown in window 39 for purposes of comparison.
It will be appreciated that there will be a desired location for the solder joint in the PC board and that this known location can be coordinated with a given pixel in the image. For Pxample, solder joint locations can be assigned X,Y coordinate locations, and the PC board image can then be related to these ~ coordinate locations to determine which pixel in the :: .
.
....
.
9 2~29~40 1 image is expected to be at the center of each solder joint location.
The upper intensity threshold T is then set.
(step 42) This may be preferably an adaptive threshold which is set in accordance with the process described below in connection with FIG. 4. However, a nonadaptive threshold could be set which would simply be an estimated upper limit of the possible intensity value for a joint pixel. Next, the window 39 is subdivided into R subwindows. (step 44) This step speeds up the processing by analyzing groups of pixels rather than each pixel individually. However, it will be appreciated that individual pixels could be analyzed, and in some applications it may be desirable to do so depending on the desired resolution and speed of processing.
In accordance with a preferred embodiment, the subwindows consist of a square area within the windo~
of nine pixels having a single pixel at its center.
Next, each subwindow is analyzed individually until the entire window has been processed. It may be accomplished by assigning each subwindow an index number N from one to R. This index is first set to zero (step 46) and is then incremented by one each time step 48 is carried out. Next, the average intensity of all the pixels in the subwindow N is measured. (step 50) Then, the average intensity of the subwindow is compared to the upper threshold T in step 52. If this average intensity is not less than or equal to T, then the subwindow is considered to be not part of the solder joint and the process proceeds to step 54 to determine if there are any further subwindows that have not yet been processed. If there are, that is, if N is not equal to R, step 54 directs --` 2~29~Q
1 the process back to step 48 to proceed to the next numerically consecutive subwindow.
If, on the other hand, step 52 determines that the average intensity is less than or equal to T, step 56 is performed, which determines whether the subwindow N is "connected" to any "joint pixels". It will be appreciated that a number of different -criteria could be used to determine if pixels are "connected." Preferably this criteria will require more than a single side to be connected, or touching.
This will avoid the connection of two separate features by a thin string of pixels. For example, the criteria preferred is that three sides touch to establish connectedness. It should also be noted that in step 40, the center pixel was labeled a joint pixel, and that the processing will proceed on subwindows that are "connected" to the center pixel and proceed outward until all of the subwindows in the window have been analyzed. If, in step 56 it is determined that the subwindow N, which had its intensity less than or equal to T, is not connected a "joint pixel", then that subwindow is considered to be not part of the joint. For example, this may represent a dark area corresponding to an electrical component that is not part of the particular solder joint. Alternatively, it may represent a completely different solder joint that is within the window. It should be noted that the other solder joints will be ignored at this point, but will be processed at a later time when a different window is selected having the expected center joint of that solder joint at its center.
Accordingly, step 56, having determined that a window is not connected to a joint window, will direct the system to step 54, where, as described above, it .
.
11 2Q295~0 1 will be detPrmlned whether there are additional subwindows to analyze. If there are, the process will proceed to step 48. If, on the other hand, step 56 determines that the subwindow is connected to a joint pixel, then the pixels in that subwindow is labeled a "joint pixels". (step 58) It will be appreciated that subwindows with pixels labeled "joint pixels", may be connected to the center pixel, or may it be connected to other subwindows previously determined to be connected to the center window, or to other subwindows labeled "joint pixels".
After 58, step 54 is again performed to determined if there are additional subwindows not yet processed. If there are not, that is, if N is equal to R, then step 60 is performed to begin a centering routine. That is, the above steps will have determined all subwindows that are connected to each other and below or equal to threshold T and labeled those pixels joint pixels. The subwindows at this p~int, should define the generally cylindrical or barrel shape of the solder joint 28. It will be appreciated that given this cylindrical shape, one can easily determine the center of this shape. For example, a procedure may employ averaging techniques whereby the average location is determined. In particular, such a centering technique may proceed as follows. Initially, each subwindow is assigned an X-Y
value corresponding to the center of the subwindow.
The X,Y value of all "joint" subwindows are then 3~ averaged separately to given an overall joint ~,Y.
Optionally, additional procedures may be performed to check the shape of the group of joint pixels before the centering routine is begun. For example, in accordance with conventional image processing "' ;
12 2029~0 1 techniques, the joint pixels may be analyzed to see if they generally form a rectangular shape.
Having found the center of the solder joint 41, the coordinate~ of the center pixel ~3 are now determined and are transmitted for display, or for use by subsequent processing systems (Step 62). At this point the processing, is complete (step 64). All of the above steps, 34 - 64, may be repeated for other solder joints 28 in the PC board 10. Alternatively, different features besides solder joints, may be analyzed in accordance with the above steps.
Referring now to FIG. 4, the preferred method for setting an adaptive threshold, in accordance with step 42 above, will now be described. The procedure for setting the adaptive threshold begins with the measurement of the intensity of a calibration strip of the solder on the PC board 10. (steps 66 and 68) This calibration strip is preferably contained within the window defined in step 40 of FIG. 3. This is because the threshold is reset for each window.
Alternatively, since the adaptive threshold also depends on the intensity in the neighborhood of the center pixel, there could be only a single calibration strip in the entire PC board, in which case the measurement taken in step ~8 is used for each window in the entire image.
The threshold is initially set to be the intensity of the solder strip measured in step 68 (step 70). This is because the calibration strip, measured in step 68, is chosen to yield an intensity value that would represent the lightest acceptable value for a solder joint area. Next, measurements are taken of the intensity of several pixels in the neighborhood of the center pixel defined in step 40.
(step 72) Next, the darkest of these pixels is ' ' '~' ~
~, ! ' '' ' ' ." . ' , , ''' ' . ' '' .
". ' ' , , .
~o~ o 1 selected (step 74). The darkest pixel is then compared to the threshold set in step 70. (step 76) If this darkest pixel is lighter than the threshold, the joint is labeled defective. (step 78) This is because the calibration solder strip is as light as a solder joint should be. If it is lighter there is a problem, such as a void in the joint, and the joint is labeled defective and the processing stops as shown in step 78. On the other hand, if the darkest pixel is not found to be lighter in step 76, the threshold is set to a new value which is equal to the darkest pixel plus some predefined constant value, C. (steps 79 and 80) Referring now to FIG. 5, a preferred embodiment of the hardware according to the present invention is shown. A solder joint locator system 82 includes a sensor 84 which may comprise, for example, a CCD array for detecting the intensity of the individual pixels in an image, such as an X-ray image 86 of a PC board.
The information frcm the CCD array is fed along bus 88 to a microcontroller 90. Microcontroller 90 comprises a conventional programmable microprocessor capable of receiving the pixel data ~rom CCD array 84 and storing and processing this information. In particular, microcontroller 90 is programmed to perform all of the steps 34 through 64 in FIG. 3, as well as the adaptive threshold setting steps 66 80 in FIG. 4. Finally, microcontroller 90 is connected, by means of bus 92, to a postprocessing system 94 which uses the coordinate locations of the solder joint centers found by the microcontroller 90 to perform additional tests on the PC board image 86. In addition, direct tests to the actual PC board may then also be performed.
It will be appreciated that in some circumstances desired features will be lighter rather 2~9~0 ~
l than darker than the background. In such cases, the invention will be adapted to set lower thresholds and to look for pixels that are lighter than the lower thresholds. Alternatively, an intensity band, rather than an upper or lower threshold, may be set. In which case the invention may be adapted to look for pixels that fall within this band. It should also be recognized that the joint locator system 82 and the processes described in FIGS 3 and 4, can also be employed in other image processing applications besides locating joints in ~C boards. For instance, the present invention could be used in target acquisition where, for example, the image is an infrared image and the image processing task is tracking of bright spots in the image. The present invention could then be used to sort out and track separate spots in such an image. In general, the present invention can be used in a wide variety of image processing applications where the center of an object in a field is desired and the field is cluttered with other things that will obscure the task of finding the center of the object. While the above description constitutes the preferred embodiments of the present invention, it will be appreciated that the invention is susceptible to modifications, variation and change without departing from the proper scope and fair meaning of the accompanying claims.
. ;' ' ' .
' ,' .
Claims (16)
1. A system for automatically detecting features in an image, said system comprising:
means for measuring the intensity of pixels in said image, each pixel having a coordinate location;
means for storing said measured intensity values;
means for defining a window within said image, the window having one of said predetermined expected feature locations at its center pixel;
means for labeling the center pixel;
means for determining if the intensity of pixels within said window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to the center pixel, and for labelling those pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled, and for labelling those pixels also;
means for determining the center of the group of labeled pixels; and means for displaying the coordinate location of said center.
means for measuring the intensity of pixels in said image, each pixel having a coordinate location;
means for storing said measured intensity values;
means for defining a window within said image, the window having one of said predetermined expected feature locations at its center pixel;
means for labeling the center pixel;
means for determining if the intensity of pixels within said window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to the center pixel, and for labelling those pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled, and for labelling those pixels also;
means for determining the center of the group of labeled pixels; and means for displaying the coordinate location of said center.
2. The system of Claim 1 further comprising:
means for determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
means for determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
3. The system of Claim 2 wherein said means for determining the upper threshold further comprises means for identifying the feature if said darkest pixel is lighter than the calibration portion.
4. The system of Claim 1 wherein said image is a tilted view X-ray image of a printed circuit board.
5. The system of Claim 4 wherein said feature is a solder joint in a plated-through hole in said printed circuit board.
6. A system for automatically determining the position of features in an image, said system comprising:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected feature location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
means for determining the center of the group of the feature pixels; and means for displaying the coordinate location of said center.
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected feature location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
means for determining the center of the group of the feature pixels; and means for displaying the coordinate location of said center.
7. The system of Claim 6 further comprising:
means for determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
means for determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
8. The system of Claim 7 wherein said means for determining the upper threshold further comprises means for identifying the feature if said darkest pixel is lighter than the calibration portion.
9. The system of Claim 6 wherein said image is a tilted view X-ray image of a printed circuit board.
10. The system of Claim 9 wherein said feature is a solder joint in a plated-through hole in said printed circuit board.
11. A system for testing printed circuit boards for solder joint locations by analyzing an X-ray image of the printed circuit board, said system comprising:
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected joint location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to joint pixels and for labelling those joint pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also joint pixels;
means for determining the center of the group of the joint pixels; and means for displaying the coordinate location of said center.
means for measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
means for storing said measured intensity values;
means for defining a window within said image having a predetermined expected joint location at its center pixel;
means for dividing said window into a plurality of sub-windows;
means for labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
means for determining the average intensity of pixels within each of said sub-windows;
means for determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
means for determining if pixels found to be below said predetermined upper threshold are connected to joint pixels and for labelling those joint pixels;
means for determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also joint pixels;
means for determining the center of the group of the joint pixels; and means for displaying the coordinate location of said center.
12. The system of Claim 11 further comprising:
means for determining said upper threshold further comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
means for determining said upper threshold further comprising means for measuring the intensity of a calibration portion of said image;
means for determining the darkest pixel in the neighborhood of the center pixel;
means for comparing said darkest pixel with the calibration portion; and means for setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
13. A method for automatically determining the position of features in an image, said method comprising the steps of:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected feature location at its center pixel;
dividing said window into a plurality of sub-windows:
labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
determining the center of the group of the feature pixels; and displaying the coordinate location of said center.
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected feature location at its center pixel;
dividing said window into a plurality of sub-windows:
labeling the pixels in the sub-window surrounding the center of the window as feature pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said predetermined upper threshold are connected to feature pixels and for labelling those as feature pixels;
determining if pixels found to be below the predetermined upper threshold are connected to any pixels previously labelled feature pixels, and labelling those pixels also as feature pixels;
determining the center of the group of the feature pixels; and displaying the coordinate location of said center.
14. The system of Claim 13 further comprising:
determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
determining the darkest pixel in the neighborhood of the center pixel;
comparing said darkest pixel with the calibration portion; and setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
determining said upper threshold comprising means for measuring the intensity of a calibration portion of said image;
determining the darkest pixel in the neighborhood of the center pixel;
comparing said darkest pixel with the calibration portion; and setting the upper threshold equal to said darkest pixel plus a predetermined constant if it is darker than the calibration portion.
15. The system of Claim 13 wherein determining the upper threshold further comprises stopping the system and identifying the feature if said darkest pixel is lighter than the calibration portion.
16. A method for automatically testing a printed circuit board to determine the position of solder joints in a tilted view X-ray image of the printed circuit joint or circuit board, said method comprising:
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected joint location at its center pixel;
dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said upper threshold are connected to joint pixels and for labeling those joint pixels;
determining if pixels found to be below the threshold are connected to any pixels previously labeled feature pixels, and labeling those pixels also joint pixels;
determining the center of the group of the joint pixels; and displaying the coordinate location of said center.
measuring the intensity of pixels in said image, said pixels having coordinate locations in said image;
storing said measured intensity values;
defining a window within said image having a predetermined expected joint location at its center pixel;
dividing said window into a plurality of sub-windows;
labeling the pixels in the sub-window surrounding the center of the window as joint pixels;
determining the average intensity of pixels within each of said sub-windows;
determining if the average intensity of pixels within each sub-window are below a predetermined upper threshold;
determining if pixels found to be below said upper threshold are connected to joint pixels and for labeling those joint pixels;
determining if pixels found to be below the threshold are connected to any pixels previously labeled feature pixels, and labeling those pixels also joint pixels;
determining the center of the group of the joint pixels; and displaying the coordinate location of said center.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US454,804 | 1989-12-21 | ||
| US07/454,804 US5164994A (en) | 1989-12-21 | 1989-12-21 | Solder joint locator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CA2029540A1 CA2029540A1 (en) | 1991-06-22 |
| CA2029540C true CA2029540C (en) | 1994-05-24 |
Family
ID=23806172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002029540A Expired - Fee Related CA2029540C (en) | 1989-12-21 | 1990-11-09 | Solder joint locator |
Country Status (8)
| Country | Link |
|---|---|
| US (1) | US5164994A (en) |
| EP (1) | EP0433803A1 (en) |
| JP (1) | JPH04120403A (en) |
| KR (1) | KR940000029B1 (en) |
| CA (1) | CA2029540C (en) |
| IL (1) | IL96335A0 (en) |
| NO (1) | NO905397L (en) |
| TR (1) | TR25247A (en) |
Families Citing this family (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5621811A (en) * | 1987-10-30 | 1997-04-15 | Hewlett-Packard Co. | Learning method and apparatus for detecting and controlling solder defects |
| US6067379A (en) * | 1988-12-09 | 2000-05-23 | Cognex Corporation | Method and apparatus for locating patterns in an optical image |
| FR2683647B1 (en) * | 1991-11-13 | 1994-02-25 | Sodern Etudes Realisa Nucleaires | IMAGE READING AND ANALYSIS DEVICE. |
| US5555316A (en) * | 1992-06-30 | 1996-09-10 | Matsushita Electric Industrial Co., Ltd. | Inspecting apparatus of mounting state of component or printing state of cream solder in mounting line of electronic component |
| US5991435A (en) * | 1992-06-30 | 1999-11-23 | Matsushita Electric Industrial Co., Ltd. | Inspecting apparatus of mounting state of component or printing state of cream solder in mounting line of electronic component |
| JP3051279B2 (en) * | 1993-05-13 | 2000-06-12 | シャープ株式会社 | Bump appearance inspection method and bump appearance inspection device |
| JP3205432B2 (en) * | 1993-06-10 | 2001-09-04 | 松下電器産業株式会社 | Mounting component inspection device and mounting component inspection method |
| CA2113752C (en) * | 1994-01-19 | 1999-03-02 | Stephen Michael Rooks | Inspection system for cross-sectional imaging |
| US5500886A (en) * | 1994-04-06 | 1996-03-19 | Thermospectra | X-ray position measuring and calibration device |
| US6084986A (en) * | 1995-02-13 | 2000-07-04 | Eastman Kodak Company | System and method for finding the center of approximately circular patterns in images |
| US6026176A (en) * | 1995-07-25 | 2000-02-15 | Cognex Corporation | Machine vision methods and articles of manufacture for ball grid array inspection |
| US5872870A (en) * | 1996-02-16 | 1999-02-16 | Cognex Corporation | Machine vision methods for identifying extrema of objects in rotated reference frames |
| US5909504A (en) * | 1996-03-15 | 1999-06-01 | Cognex Corporation | Method of testing a machine vision inspection system |
| US6259827B1 (en) | 1996-03-21 | 2001-07-10 | Cognex Corporation | Machine vision methods for enhancing the contrast between an object and its background using multiple on-axis images |
| US6298149B1 (en) | 1996-03-21 | 2001-10-02 | Cognex Corporation | Semiconductor device image inspection with contrast enhancement |
| US5978502A (en) * | 1996-04-01 | 1999-11-02 | Cognex Corporation | Machine vision methods for determining characteristics of three-dimensional objects |
| US5703394A (en) * | 1996-06-10 | 1997-12-30 | Motorola | Integrated electro-optical package |
| US6137893A (en) * | 1996-10-07 | 2000-10-24 | Cognex Corporation | Machine vision calibration targets and methods of determining their location and orientation in an image |
| US5960125A (en) | 1996-11-21 | 1999-09-28 | Cognex Corporation | Nonfeedback-based machine vision method for determining a calibration relationship between a camera and a moveable object |
| US5953130A (en) * | 1997-01-06 | 1999-09-14 | Cognex Corporation | Machine vision methods and apparatus for machine vision illumination of an object |
| US6075881A (en) * | 1997-03-18 | 2000-06-13 | Cognex Corporation | Machine vision methods for identifying collinear sets of points from an image |
| US5974169A (en) * | 1997-03-20 | 1999-10-26 | Cognex Corporation | Machine vision methods for determining characteristics of an object using boundary points and bounding regions |
| ATE246803T1 (en) * | 1997-05-05 | 2003-08-15 | Macrotron Process Technologies | METHOD AND CIRCUIT ARRANGEMENT FOR TESTING SOLDER JOINTS |
| US6141033A (en) * | 1997-05-15 | 2000-10-31 | Cognex Corporation | Bandwidth reduction of multichannel images for machine vision |
| US6608647B1 (en) | 1997-06-24 | 2003-08-19 | Cognex Corporation | Methods and apparatus for charge coupled device image acquisition with independent integration and readout |
| US5978080A (en) * | 1997-09-25 | 1999-11-02 | Cognex Corporation | Machine vision methods using feedback to determine an orientation, pixel width and pixel height of a field of view |
| US6025854A (en) * | 1997-12-31 | 2000-02-15 | Cognex Corporation | Method and apparatus for high speed image acquisition |
| US6236769B1 (en) | 1998-01-28 | 2001-05-22 | Cognex Corporation | Machine vision systems and methods for morphological transformation of an image with zero or other uniform offsets |
| US6282328B1 (en) | 1998-01-28 | 2001-08-28 | Cognex Corporation | Machine vision systems and methods for morphological transformation of an image with non-uniform offsets |
| US6381375B1 (en) | 1998-02-20 | 2002-04-30 | Cognex Corporation | Methods and apparatus for generating a projection of an image |
| US6215915B1 (en) | 1998-02-20 | 2001-04-10 | Cognex Corporation | Image processing methods and apparatus for separable, general affine transformation of an image |
| US6633663B1 (en) * | 1998-05-05 | 2003-10-14 | International Business Machines Corporation | Method and system for determining component dimensional information |
| US6314201B1 (en) | 1998-10-16 | 2001-11-06 | Agilent Technologies, Inc. | Automatic X-ray determination of solder joint and view delta Z values from a laser mapped reference surface for circuit board inspection using X-ray laminography |
| US6526165B1 (en) * | 1998-11-30 | 2003-02-25 | Cognex Corporation | Methods and apparatuses for refining a geometric description of an object having a plurality of extensions |
| US6687402B1 (en) | 1998-12-18 | 2004-02-03 | Cognex Corporation | Machine vision methods and systems for boundary feature comparison of patterns and images |
| US6381366B1 (en) | 1998-12-18 | 2002-04-30 | Cognex Corporation | Machine vision methods and system for boundary point-based comparison of patterns and images |
| KR100339008B1 (en) * | 1999-04-12 | 2002-05-31 | 구자홍 | Method for cross sectional inspection of PCB using X-ray |
| US6813377B1 (en) * | 1999-08-06 | 2004-11-02 | Cognex Corporation | Methods and apparatuses for generating a model of an object from an image of the object |
| US6898333B1 (en) | 1999-08-06 | 2005-05-24 | Cognex Corporation | Methods and apparatus for determining the orientation of an object in an image |
| GB9918681D0 (en) * | 1999-08-09 | 1999-10-13 | Smithkline Beecham Plc | Novel method |
| GB9923795D0 (en) | 1999-10-09 | 1999-12-08 | British Aerospace | Micropositioning system |
| US6684402B1 (en) | 1999-12-01 | 2004-01-27 | Cognex Technology And Investment Corporation | Control methods and apparatus for coupling multiple image acquisition devices to a digital data processor |
| US6748104B1 (en) | 2000-03-24 | 2004-06-08 | Cognex Corporation | Methods and apparatus for machine vision inspection using single and multiple templates or patterns |
| US6744913B1 (en) * | 2000-04-18 | 2004-06-01 | Semiconductor Technology & Instruments, Inc. | System and method for locating image features |
| US6459807B1 (en) | 2000-06-13 | 2002-10-01 | Semiconductor Technologies & Instruments, Inc. | System and method for locating irregular edges in image data |
| US7024031B1 (en) * | 2001-10-23 | 2006-04-04 | August Technology Corp. | System and method for inspection using off-angle lighting |
| US6847900B2 (en) * | 2001-12-17 | 2005-01-25 | Agilent Technologies, Inc. | System and method for identifying solder joint defects |
| JP3974022B2 (en) * | 2002-11-21 | 2007-09-12 | 富士通株式会社 | Feature amount calculation method and apparatus for soldering inspection, and program for executing the method |
| US7773270B2 (en) * | 2004-01-07 | 2010-08-10 | Hewlett-Packard Development Company, L.P. | Image scanner feature detection |
| US8111904B2 (en) | 2005-10-07 | 2012-02-07 | Cognex Technology And Investment Corp. | Methods and apparatus for practical 3D vision system |
| US8162584B2 (en) | 2006-08-23 | 2012-04-24 | Cognex Corporation | Method and apparatus for semiconductor wafer alignment |
| US7529336B2 (en) | 2007-05-31 | 2009-05-05 | Test Research, Inc. | System and method for laminography inspection |
| CN104535587A (en) * | 2014-12-23 | 2015-04-22 | 安徽科鸣三维科技有限公司 | PCBA solder joint inspection method based on machine vision |
Family Cites Families (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4103287A (en) * | 1973-12-17 | 1978-07-25 | Bell Telephone Laboratories, Incorporated | Variable length codes for high quality image encoding |
| US4508452A (en) * | 1975-08-27 | 1985-04-02 | Robotic Vision Systems, Inc. | Arrangement for sensing the characteristics of a surface and determining the position of points thereon |
| US4183013A (en) * | 1976-11-29 | 1980-01-08 | Coulter Electronics, Inc. | System for extracting shape features from an image |
| US4189711A (en) * | 1977-11-08 | 1980-02-19 | Bell Telephone Laboratories, Incorporated | Multilevel processing of image signals |
| US4472056A (en) * | 1980-07-23 | 1984-09-18 | Hitachi, Ltd. | Shape detecting apparatus |
| US4415980A (en) * | 1981-03-02 | 1983-11-15 | Lockheed Missiles & Space Co., Inc. | Automated radiographic inspection system |
| US4427880A (en) * | 1981-06-29 | 1984-01-24 | Westinghouse Electric Corp. | Non-contact visual proximity sensing apparatus |
| US4445137A (en) * | 1981-09-11 | 1984-04-24 | Machine Intelligence Corporation | Data modifier apparatus and method for machine vision systems |
| US4499597A (en) * | 1982-03-29 | 1985-02-12 | Hughes Aircraft Company | Small-object location utilizing centroid accumulation |
| US4650333A (en) * | 1984-04-12 | 1987-03-17 | International Business Machines Corporation | System for measuring and detecting printed circuit wiring defects |
| JPS61237002A (en) * | 1985-04-13 | 1986-10-22 | Matsushita Electric Works Ltd | Hole position detector in multi-layer printed circuit substrate with metallic core material |
| US4791676A (en) * | 1985-09-12 | 1988-12-13 | International Business Machines Corporation | Method and means for efficiently handling boundary conditions in connected component labeling |
| US4756696A (en) * | 1985-12-06 | 1988-07-12 | Amp Incorporated | Solder joint inspection feature for surface mount connectors |
| EP0236738A3 (en) * | 1986-02-05 | 1988-12-21 | OMRON Corporation | Input method for reference printed circuit board assembly data to an image processing printed circuit board assembly automatic inspection apparatus |
| US4809308A (en) * | 1986-02-20 | 1989-02-28 | Irt Corporation | Method and apparatus for performing automated circuit board solder quality inspections |
| JPS62209304A (en) * | 1986-03-10 | 1987-09-14 | Fujitsu Ltd | Method for measuring dimension |
| JPS62267610A (en) * | 1986-05-16 | 1987-11-20 | Fuji Electric Co Ltd | Detecting system for rotational angle of object pattern |
| US4955062A (en) * | 1986-12-10 | 1990-09-04 | Canon Kabushiki Kaisha | Pattern detecting method and apparatus |
| JPS647176A (en) * | 1987-06-29 | 1989-01-11 | Meidensha Electric Mfg Co Ltd | Outline detection device |
| US4926452A (en) * | 1987-10-30 | 1990-05-15 | Four Pi Systems Corporation | Automated laminography system for inspection of electronics |
| US4910757A (en) * | 1987-11-06 | 1990-03-20 | Hitachi, Ltd. | Method and apparatus for X-ray imaging |
| US4876455A (en) * | 1988-02-25 | 1989-10-24 | Westinghouse Electric Corp. | Fiber optic solder joint inspection system |
| US4852131A (en) * | 1988-05-13 | 1989-07-25 | Advanced Research & Applications Corporation | Computed tomography inspection of electronic devices |
-
1989
- 1989-12-21 US US07/454,804 patent/US5164994A/en not_active Expired - Lifetime
-
1990
- 1990-11-09 CA CA002029540A patent/CA2029540C/en not_active Expired - Fee Related
- 1990-11-13 IL IL96335A patent/IL96335A0/en active IP Right Review Request
- 1990-12-07 EP EP90123578A patent/EP0433803A1/en not_active Withdrawn
- 1990-12-13 NO NO90905397A patent/NO905397L/en unknown
- 1990-12-18 TR TR90/1226A patent/TR25247A/en unknown
- 1990-12-20 KR KR1019900021149A patent/KR940000029B1/en not_active IP Right Cessation
- 1990-12-21 JP JP2413356A patent/JPH04120403A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| NO905397L (en) | 1991-06-24 |
| KR910012993A (en) | 1991-08-08 |
| CA2029540A1 (en) | 1991-06-22 |
| NO905397D0 (en) | 1990-12-13 |
| US5164994A (en) | 1992-11-17 |
| EP0433803A1 (en) | 1991-06-26 |
| KR940000029B1 (en) | 1994-01-05 |
| JPH04120403A (en) | 1992-04-21 |
| IL96335A0 (en) | 1991-08-16 |
| TR25247A (en) | 1993-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2029540C (en) | Solder joint locator | |
| EP0385474B1 (en) | Method of and apparatus for inspecting printed circuit boards | |
| US5455870A (en) | Apparatus and method for inspection of high component density printed circuit board | |
| US6496270B1 (en) | Method and system for automatically generating reference height data for use in a three-dimensional inspection system | |
| CA1285661C (en) | Automatic visual measurement of surface mount device placement | |
| US7181058B2 (en) | Method and system for inspecting electronic components mounted on printed circuit boards | |
| US6249598B1 (en) | Solder testing apparatus | |
| JPH0499950A (en) | Soldering inspection apparatus | |
| EP0341806A2 (en) | Apparatus for inspecting circuit boards with surface mounted components | |
| Takagi et al. | Visual inspection machine for solder joints using tiered illumination | |
| Mahon et al. | Automated visual inspection of solder paste deposition on surface mount technology PCBs | |
| US20070217675A1 (en) | Z-axis optical detection of mechanical feature height | |
| US6516086B2 (en) | Method and apparatus for distinguishing regions where a material is present on a surface | |
| Matsuyama et al. | Automated solder joint inspection system using optical 3-D image detection | |
| JPH09321500A (en) | Appearance inspecting method in soldered state | |
| JPH04355946A (en) | Inspection of soldered part of electronic component | |
| KR0141154B1 (en) | The test method of inserting for electronic elements on pcb(printed circuit board) | |
| KR100325998B1 (en) | solder ball inspection system and inspection method thereof | |
| KR19980072951A (en) | Device and method for inspecting error of cream solder coating state of printed circuit board | |
| Park et al. | Automatic inspection of assembled PC board via highlight separation and dual channel processing | |
| JPH0310151A (en) | Object inspecting device | |
| Koezuka et al. | I/O pin solder-point inspection system | |
| JPH028705A (en) | Inspection of soldered part of mounted component | |
| Keeler | Machine vision | |
| JPH0619252B2 (en) | Soldering inspection device for printed wiring boards |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| MKLA | Lapsed |