CN104568978A - Lamp holder optical head defect detection method - Google Patents
Lamp holder optical head defect detection method Download PDFInfo
- Publication number
- CN104568978A CN104568978A CN201310501458.0A CN201310501458A CN104568978A CN 104568978 A CN104568978 A CN 104568978A CN 201310501458 A CN201310501458 A CN 201310501458A CN 104568978 A CN104568978 A CN 104568978A
- Authority
- CN
- China
- Prior art keywords
- lamp holder
- image
- optical head
- edge
- contour
- 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.)
- Pending
Links
Abstract
The invention discloses a lamp holder optical head defect detection method in lamp holder product detection. Lamp holder optical head defects mainly refer to bayonet type double soldering lug lamp holder products. For the detection of the double soldering lug lamp holder optical head detect, the method comprises the following steps: gathering a lamp holder image through an image gathering process, performing smoothing processing on the image through an smoothing process, so as to eliminate high-frequency noise in the image, performing cutting process on the lamp holder image through a cutting process, and performing erosion and dilation operation, performing edge extraction on the lamp holder image through an optical head defect detection process, then obtaining the contour code at the edge in the outmost layer of the lamp holder image through contour tracing, calculating the distance between each pixel at the edge of a lamp holder and the center according to the obtained contour code, finding out the maximum distance value, comparing the maximum distance value with a qualified lamp holder standard value, and detecting whether optical head defects exist. The method is high in capacity of resisting disturbance and good in reliability and maintainability, and can replace the traditional manual detection method.
Description
Technical field
The present invention relates to the automatic testing method of lamp holder product quality problem, in particular to the bare headed defect problem in single, double weld tabs lamp holder product quality problem, this bare headed defect inspection method can be applied to the coherent detection field of lamp holder product automatic detection system and other product quality problem of appearance.
Background technology
Electric light source is as daily necessities requisite in mankind's daily life, and its annual use and quantity consumed are very huge, and in electric light source production run, have consequence as the quality testing of the critical piece lamp holder of electric light source products.The inspection of current China lamp holder product is main still by means of vision and the subjective judgement ability of people, thus a large amount of manual labor is occupied, and owing to being subject to the eyesight of individual, mood, tired, the impact of the factors such as light, inefficiency, go-on-go difference is large, Detection results is limited, particularly along with the raising of lamp holder production efficiency and production automation level, output is multiplied, then need to drop into more human resources to carry out the quality testing of product, this materially increases the operation cost of manufacturing enterprise, become enterprise to enhance productivity and take into account the bottleneck of benefit.
Summary of the invention
Lamp holder shaven head defect refers to the bayonet socket terminal defect of lamp holder, and this defect will cause the electric light source products produced to install and use.For solving this problem, the object of the invention is to introduce a kind of lamp holder shaven head defect inspection method, improving lamp holder product automatic detection system to the detection efficiency of product quality problem and precision, reduce the operation cost of the examination and test of products, improve the production efficiency of product.
The present invention is achieved by the following technical programs:
1) image acquisition step: based on monocular vision collecting fruit image;
2) image smoothing step: the flat algorithm in the field based on Gaussian template carrys out the high frequency noise in removal of images to the smoothing process of image;
3) image segmentation step: adopt Otsu threshold algorithm to the process of lamp holder Image Segmentation Using, extract weld tabs;
4) bare headed defect detection procedure: first adopt the method emptying internal point to carry out edge extracting to lamp holder image, then the contour code of lamp holder image outermost edge is obtained by Contour extraction, the distance of each pixel in lamp holder edge apart from center is obtained according to the contour code obtained, find out distance maximal value wherein, this value and qualified lamp holder standard value are compared detection and whether there is bare headed defect.
The invention has the beneficial effects as follows: under the condition of manual detection, due to the speed of artificial screening and precision on the low side, need to take a large amount of manual labor, this constrains production efficiency and the economic benefit of enterprise greatly simultaneously.The present invention is exactly how research solve the bare headed defect problem in lamp holder product quality problem on-line checkingi and screening problem at industry spot applied for machines vision technique, and be applied to the artificial screening work of production scene replacement inefficiency, detection efficiency and the precision of product can be improved greatly compared with manual detection; This detection method will play an important role in lamp holder automatic detection system, and the successful development of this detection system simultaneously will be subject to the manufacturing very big welcome of lamp holder.
Accompanying drawing explanation
Fig. 1 is lamp holder product automatic detection system organizational structure design schematic diagram.
Fig. 2 is product image to be checked.
Fig. 3 lamp holder shaven head defects detection process flow diagram.
Fig. 4 edge extracting figure.
Embodiment
Below in conjunction with the drawings and specific embodiments, illustrate the present invention further, these embodiments should be understood only be not used in for illustration of the present invention and limit the scope of the invention, after having read the present invention, the amendment of those skilled in the art to the various equivalent form of value of the present invention has all fallen within the application's claims limited range.
As shown in Figure 1, two weld tabs lamp holder shaven head defect inspection method is in lamp holder product automatic detection system, substandard products mainly for bare headed defect situation detect: lamp holder product carries out ordered arrangement by vibration feeder, by belt feeding workbench in order by lamp holder product place to be checked, when lamp holder product runs to product place to be checked, be arranged on proximity switch near product place to be checked by generation pulse signal, this signal sends into PC by switch card, PC controls image pick-up card and gathers lamp holder product image to internal memory by industrial camera after receiving signal, then image recognition processing software carries out analyzing and processing to lamp holder image, differentiate whether this lamp holder is specification product, as the situation that weld tabs defect lacks appears in lamp holder product, then identify its defect type and send rejecting signal by switch card to corresponding rejecting mechanism and carry out classification rejecting, not constantly running like this.
As shown in Figure 2, carrying out in Product checking process, in the process that lamp holder image is gathered, in order to reduce the discrimination of the interference of background, outstanding lamp holder to be checked, raising image, the background designs at place to be checked for lamp holder is become black, namely lamp holder image gathers under black background, the extraction of be more convenient for so follow-up lamp holder image procossing and lamp holder feature.
Figure 3 shows that lamp holder shaven head defects detection process flow diagram.The process of two weld tabs lamp holder shaven head defects detection is as follows:
(1) image acquisition step: based on monocular vision collecting fruit image;
(2) image smoothing step: the flat algorithm in the field based on Gaussian template carrys out the high frequency noise in removal of images to the smoothing process of image;
(3) image segmentation step: adopt Otsu threshold algorithm to the process of lamp holder Image Segmentation Using, and carry out corrosion expansive working;
(4) bare headed defect detection procedure: first adopt the method emptying internal point to carry out edge extracting to lamp holder image, edge extracting figure is as Fig. 4, and detailed process is as follows:
S1: obtain the first address of original image pixel and the height and width of figure;
S2: open up one piece of core buffer, source image pixels is kept in internal memory;
S3: 8 field pixels of pixel read in array, if the pixel value in each field is identical with the pixel value of central point, then puts this pixel white (black) in the buffer, otherwise remains unchanged;
S4: repeat (3), processes each pixel;
S5: by the data Replica in internal memory in original image.
Then the contour code of lamp holder image outermost edge is obtained by Contour extraction, the distance of each pixel in lamp holder edge apart from center is obtained according to the contour code obtained, find out distance maximal value wherein, this value and qualified lamp holder standard value are compared detection and whether there is bare headed defect.
Claims (2)
1. a lamp holder shaven head defect inspection method, is characterized in that comprising the following steps:
Image acquisition step: based on monocular vision collecting fruit image;
Image smoothing step: the smoothing process of image is carried out to the high frequency noise in removal of images;
Image segmentation step: to the process of lamp holder Image Segmentation Using, and carry out corrosion expansive working;
Shaven head defect detection procedure: edge extracting is carried out to lamp holder image, then the contour code of lamp holder image outermost edge is obtained by Contour extraction, the distance of each pixel in lamp holder edge apart from center is obtained according to the contour code obtained, find out distance maximal value wherein, this value and qualified lamp holder standard value are compared detection and whether there is bare headed defect.
2. a kind of lamp holder shaven head defect inspection method according to claim 1, it is characterized in that, first the method emptying internal point is adopted to carry out edge extracting to lamp holder image in shaven head defect detection procedure, then the contour code of lamp holder image outermost edge is obtained by Contour extraction, the distance of each pixel in lamp holder edge apart from center is obtained according to the contour code obtained, find out distance maximal value wherein, this value and qualified lamp holder standard value are compared detection and whether there is bare headed defect.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310501458.0A CN104568978A (en) | 2013-10-22 | 2013-10-22 | Lamp holder optical head defect detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310501458.0A CN104568978A (en) | 2013-10-22 | 2013-10-22 | Lamp holder optical head defect detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104568978A true CN104568978A (en) | 2015-04-29 |
Family
ID=53085545
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310501458.0A Pending CN104568978A (en) | 2013-10-22 | 2013-10-22 | Lamp holder optical head defect detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104568978A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109544547A (en) * | 2018-11-30 | 2019-03-29 | 湘潭大学 | A kind of bayonet type autobulb lamp cap top open defect detection method |
CN113436207A (en) * | 2021-06-28 | 2021-09-24 | 江苏特威机床制造有限公司 | Method for quickly and accurately extracting line structure light stripe center of regular surface |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7295314B1 (en) * | 1998-07-10 | 2007-11-13 | Nanometrics Incorporated | Metrology/inspection positioning system |
CN102221557A (en) * | 2011-03-31 | 2011-10-19 | 南京航空航天大学 | Automatic detecting device and detection method for quality of lamp holder based on machine vision |
-
2013
- 2013-10-22 CN CN201310501458.0A patent/CN104568978A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7295314B1 (en) * | 1998-07-10 | 2007-11-13 | Nanometrics Incorporated | Metrology/inspection positioning system |
CN102221557A (en) * | 2011-03-31 | 2011-10-19 | 南京航空航天大学 | Automatic detecting device and detection method for quality of lamp holder based on machine vision |
Non-Patent Citations (3)
Title |
---|
王琪: "基于机器视觉的灯头产品质量检验系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
王琪等: "基于机器视觉的灯头产品质量在线检验系统研究", 《计算机测量与控制》 * |
胡鹏等: "全自动灯头质量机器视觉检测系统", 《灯与照明》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109544547A (en) * | 2018-11-30 | 2019-03-29 | 湘潭大学 | A kind of bayonet type autobulb lamp cap top open defect detection method |
CN113436207A (en) * | 2021-06-28 | 2021-09-24 | 江苏特威机床制造有限公司 | Method for quickly and accurately extracting line structure light stripe center of regular surface |
CN113436207B (en) * | 2021-06-28 | 2024-01-23 | 江苏特威机床制造有限公司 | Method for rapidly and accurately extracting line structure light stripe center of regular surface |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107742286B (en) | Method for detecting EL test crack defects of polycrystalline silicon solar cell | |
CN102680414B (en) | Automatic grading device for red globe grapes based on machine vision and method thereof | |
CN205643194U (en) | Touch -control ITO film conducting layer defect detection system based on machine vision | |
CN105044126A (en) | Visual detection system for large-width continuous surface defects | |
CN103473778B (en) | Detecting method for eccentrically-inserting defect of LED luminous chip | |
CN107101598B (en) | Automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheet | |
CN104614379A (en) | Plate surface defect detection system and method | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
CN110288584A (en) | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision | |
CN107490584A (en) | A kind of disconnected grid defect inspection method of solar battery sheet EL tests | |
CN106248680A (en) | A kind of engine commutator quality detecting system based on machine vision and detection method | |
CN110517233A (en) | A kind of defect classification learning system and its classification method based on artificial intelligence | |
CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
CN112529884A (en) | Welding spot quality evaluation method based on indentation characteristic image recognition | |
CN106353340A (en) | Surface defect detection method for rod-like high-reflectance part | |
CN104568978A (en) | Lamp holder optical head defect detection method | |
CN202700832U (en) | Dynamic identification device of inferior products in production | |
CN104833925A (en) | Fuel cell bipolar plate detection method and system based on machine vision | |
CN104568974A (en) | Area-comparison-algorithm-based soldering lug defect and missing detection method | |
CN106370673A (en) | Automatic lens flaw detection method | |
CN103471515A (en) | Method for detecting double-soldering-lug lamp cap baldheaded defect | |
CN202171575U (en) | Machine vision detection device for detecting optics lens appearance | |
JP2013205320A (en) | Inspection condition determination method, inspection method, and inspection device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150429 |