CN103471515A - Method for detecting double-soldering-lug lamp cap baldheaded defect - Google Patents

Method for detecting double-soldering-lug lamp cap baldheaded defect Download PDF

Info

Publication number
CN103471515A
CN103471515A CN2013104149203A CN201310414920A CN103471515A CN 103471515 A CN103471515 A CN 103471515A CN 2013104149203 A CN2013104149203 A CN 2013104149203A CN 201310414920 A CN201310414920 A CN 201310414920A CN 103471515 A CN103471515 A CN 103471515A
Authority
CN
China
Prior art keywords
lamp holder
lamp cap
image
defect
images
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
Application number
CN2013104149203A
Other languages
Chinese (zh)
Inventor
吕建明
谢明宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZHENJIANG HU'S OPTOELECTRONIC CO Ltd
Original Assignee
ZHENJIANG HU'S OPTOELECTRONIC CO Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZHENJIANG HU'S OPTOELECTRONIC CO Ltd filed Critical ZHENJIANG HU'S OPTOELECTRONIC CO Ltd
Priority to CN2013104149203A priority Critical patent/CN103471515A/en
Publication of CN103471515A publication Critical patent/CN103471515A/en
Pending legal-status Critical Current

Links

Images

Abstract

The invention discloses a method for detecting the double-soldering-lug lamp cap baldheaded defect in the lamp cap product inspection process. The lamp cap baldheaded defect mainly relates to bayonet type double-soldering-lug lamp cap products. The method includes the steps that lamp cap images are acquired through the image acquisition step; smoothing is conducted on the images through the image smoothing step to eliminate high-frequency noise in the images; segmentation processing is conducted on the lamp cap images through the image segmentation step and then corrosion expansion is conducted on the images; the centroid coordinates of lamp cap soldering lugs are acquired through the centroid coordinate calculation step; the inclination angle between the connecting line between the centroid coordinates and the horizontal direction is utilized through the baldheaded defect detection step to conduct rotation processing on the lamp cap images, then, the centroid connecting line of the two soldering lugs of a rotated lamp cap is made to be located in the horizontal position, the uppermost edge position and lowermost edge position of a bayonet terminal of the lamp cap are looked for in the images, the distance between the two positions is calculated and then is compared with the standard distance of a qualified lamp cap, and then whether the baldheaded defect exists in the lamp cap is detected. The method is high in detection antijamming capacity, and good in reliability and maintainability, and can replace a traditional manual detection method.

Description

A kind of pair of weld tabs lamp holder shaven head defect inspection method
Technical field
The present invention relates to the automatic testing method of lamp holder product quality problem, particularly the bare headed defect problem in two weld tabs lamp holder product quality problems.This shaven head 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 requisite daily necessities in mankind's daily life, and the use in its every year and quantity consumed are very huge, and in the electric light source production run, consequence is arranged as the quality testing of the critical piece lamp holder of electric light source products.The at present check of China's lamp holder product is main or by means of people's vision and subjective judgement ability, thereby taken a large amount of hand labor power, and owing to being subject to individual eyesight, mood, tired, the impact of the factors such as light, inefficiency, go-on-go difference is large, the detection effect is limited, particularly along with the raising of lamp holder production efficiency and production automation level, output is multiplied, need to drop into more human resources and carry out the quality testing of product, this has increased the operation cost of manufacturing enterprise to a great extent, becoming enterprise enhances productivity and takes into account the bottleneck of benefit.
Summary of the invention
Two weld tabs lamp holder shaven head defects refer to that the bayonet socket terminal of lamp holder is damaged, and this defect will cause the electric light source products of producing to install and use.The objective of the invention is to introduce a kind of pair of weld tabs lamp holder shaven head defect inspection method, improve detection efficiency and the precision of lamp holder product automatic detection system to product quality problem, reduce the operation cost of the examination and test of products, improve the production efficiency of product.
Detection algorithm of 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 Gauss's template carries out smoothing processing to image and carrys out the high frequency noise in removal of images;
3) image segmentation step: adopt the Otsu threshold algorithm to process the lamp holder Image Segmentation Using, and corroded expansive working;
4) centre of form coordinate calculation procedure: by all pixel coordinates in zone being averaged to obtain the centre of form coordinate of lamp holder weld tabs;
5) bare headed defect detection procedure: utilize line between centre of form coordinate and the angle of inclination of horizontal direction to be rotated processing to the lamp holder image, the centre of form line that rotates two weld tabs of rear lamp holder is horizontal, then adopt the highest and lowest marginal position of lamp holder bayonet socket terminal in the scanning algorithm searching image, calculate two distances between position, then compare with the gauged distance of qualified lamp holder, detect the whether bare headed defect of lamp holder.
The invention has the beneficial effects as follows: under the condition of manual detection, because speed and the precision of artificial screening are on the low side, need to take a large amount of hand labor power, this has restricted production efficiency and the economic benefit of enterprise greatly simultaneously.The present invention is exactly how online detection and the screening problem of the bare headed defect problem in industry spot applied for machines vision technique solves the lamp holder product quality problem of research, and is applied to the on-the-spot artificial screening work that replaces inefficiency of production.Compare with manual detection, can improve greatly detection efficiency and the precision of product.This detection method will play an important role in the 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.
The 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 is two weld tabs lamp holder shaven head defects detection process flow diagrams.
Fig. 4 is that image is cut apart figure.
Fig. 5 is the image rotation schematic diagram.
Embodiment
Below in conjunction with the drawings and specific embodiments, further illustrate the present invention, should understand these embodiment only is not used in and limits the scope of the invention for the present invention is described, after having read the present invention, those skilled in the art all fall within the application's claims limited range to the modification of the various equivalent form of values of the present invention.
As shown in Figure 1, two weld tabs lamp holder shaven head defect inspection methods, in lamp holder product automatic detection system, are mainly the substandard products detections for bare headed defect situation.The lamp holder product carries out ordered arrangement by vibration feeder, by the belt feeding workbench, passes through in order lamp holder product place to be checked.When the lamp holder product runs to product place to be checked, be arranged near the approach switch in product place to be checked and will produce a pulse signal, this signal is sent into PC by switch card, after PC is received signal, the control image pick-up card gathers lamp holder product image to internal memory by industrial camera, then image recognition processing software carries out analyzing and processing to the lamp holder image, whether differentiate this lamp holder is specification product, as the situation of the damaged disappearance of weld tabs appears in the lamp holder product, identify its defect type and send and reject the signal rejecting of classifying to corresponding rejecting mechanism by switch card, the row of so not stopping transport.
As shown in Figure 2, in carrying out the product testing process, in the process that the lamp holder image is gathered, for interference, the outstanding lamp holder to be checked that reduces background, the discrimination that improves image, the background designs at lamp holder place to be checked is become to black, be that the lamp holder image gathers under black background, the extraction of be more convenient for so follow-up lamp holder image processing and lamp holder feature.
Figure 3 shows that two weld tabs lamp holder shaven head defects detection process flow diagrams.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 Gauss's template carries out smoothing processing to image and carrys out the high frequency noise in removal of images;
(3) image segmentation step: adopt the Otsu threshold algorithm to process the lamp holder Image Segmentation Using, and corroded expansive working, as Fig. 4;
(4) centre of form coordinate calculation procedure: by all pixel coordinates in zone are averaged to obtain the centre of form coordinate of lamp holder weld tabs, computing formula as shown in the formula;
x = Σ i , j ∈ Ω i n , y = Σ i , j ∈ Ω j n
(5) bare headed defect detection procedure: at first by the centre of form coordinate of two weld tabs, calculate the slope of its line with respect to horizontal direction, then utilize this slope to calculate angle of inclination the lamp holder image is rotated to processing, the centre of form line that rotates two weld tabs of rear lamp holder is horizontal, as Fig. 5, in Fig. 5 (a), θ is the anglec of rotation.Now lamp holder bayonet socket terminal position is arranged in the top at picture lamp holder edge and below, now by the highest and lowest marginal position of lamp holder in the scanning algorithm searching image, calculate two distances between position, then compare with the gauged distance of qualified lamp holder, detect the whether bare headed defect of lamp holder.In Fig. 5 (b), the diameter that the Edge Distance up and down of qualified lamp holder image should equal the lamp end adds the big or small d of two screens terminals, and exists the Edge Distance up and down of the lamp holder image of bare headed defect should equal the diameter d ' of lamp end cylindrical.

Claims (2)

1. a two weld tabs lamp holders 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: image is carried out to smoothing processing and carry out the high frequency noise in removal of images;
Image segmentation step: the lamp holder Image Segmentation Using is processed, and corroded expansive working;
Centre of form coordinate calculation procedure: the centre of form coordinate that obtains the lamp holder weld tabs;
Shaven head defect detection procedure: utilize line between centre of form coordinate and the angle of inclination of horizontal direction to be rotated processing to the lamp holder image, the centre of form line that rotates two weld tabs of rear lamp holder is horizontal; The highest and lowest marginal position of lamp holder bayonet socket terminal in searching image, calculate two distances between position, then with the gauged distance of qualified lamp holder, compares, and detects the whether bare headed defect of lamp holder.
2. a kind of pair of weld tabs lamp holder shaven head defect inspection method according to claim 1, it is characterized in that: in bare headed defect detection procedure, at first by the centre of form coordinate of two weld tabs, calculate the slope of its line with respect to horizontal direction, then utilize this slope to calculate angle of inclination the lamp holder image is rotated to processing, the centre of form line that rotates two weld tabs of rear lamp holder is horizontal, now lamp holder bayonet socket terminal position is arranged in the top at picture lamp holder edge and below, highest and lowest marginal position by lamp holder in the scanning algorithm searching image, calculate two distances between position, then with the gauged distance of qualified lamp holder, compare, detect the whether bare headed defect of lamp holder.
CN2013104149203A 2013-09-10 2013-09-10 Method for detecting double-soldering-lug lamp cap baldheaded defect Pending CN103471515A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2013104149203A CN103471515A (en) 2013-09-10 2013-09-10 Method for detecting double-soldering-lug lamp cap baldheaded defect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2013104149203A CN103471515A (en) 2013-09-10 2013-09-10 Method for detecting double-soldering-lug lamp cap baldheaded defect

Publications (1)

Publication Number Publication Date
CN103471515A true CN103471515A (en) 2013-12-25

Family

ID=49796469

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2013104149203A Pending CN103471515A (en) 2013-09-10 2013-09-10 Method for detecting double-soldering-lug lamp cap baldheaded defect

Country Status (1)

Country Link
CN (1) CN103471515A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155306A (en) * 2014-07-22 2014-11-19 河南工业职业技术学院 Soldering lug defect detection method for single-soldering-lug lamp cap
CN104181167A (en) * 2014-07-22 2014-12-03 河南工业职业技术学院 Soldering lug defect detection method for bayonet double-soldering-lug lamp cap

Citations (2)

* Cited by examiner, † Cited by third party
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

Patent Citations (2)

* Cited by examiner, † Cited by third party
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 (1)

* Cited by examiner, † Cited by third party
Title
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》, vol. 17, no. 3, 31 March 2009 (2009-03-31), pages 455 - 457 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155306A (en) * 2014-07-22 2014-11-19 河南工业职业技术学院 Soldering lug defect detection method for single-soldering-lug lamp cap
CN104181167A (en) * 2014-07-22 2014-12-03 河南工业职业技术学院 Soldering lug defect detection method for bayonet double-soldering-lug lamp cap
CN104155306B (en) * 2014-07-22 2019-02-12 河南工业职业技术学院 A kind of list weld tabs lamp cap weld tabs defect inspection method
CN104181167B (en) * 2014-07-22 2019-03-12 河南工业职业技术学院 A kind of double weld tabs lamp cap weld tabs defect inspection methods of bayonet

Similar Documents

Publication Publication Date Title
TWI557650B (en) System and method for identifying defects in a material
CN102680414B (en) Automatic grading device for red globe grapes based on machine vision and method thereof
CN107966454A (en) A kind of end plug defect detecting device and detection method based on FPGA
CN103808730B (en) Engine cam component surface defect inspection method
CN104502356A (en) Automatic detection method for defects of inner surface of sliding bearing on basis of computer vision
CN203376271U (en) Machine vision-based non-continuous product online detection system
CN205643194U (en) Touch -control ITO film conducting layer defect detection system based on machine vision
CN206113866U (en) Six automatic check out test sets of inductance
CN208313802U (en) A kind of chip pin defect detecting system based on machine vision
CN101221134A (en) Method and device for detecting tiny bearing surface defect by computer vision technology
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN102890093B (en) Machine vision detecting device of surface quality of master cylinder piston of automobile brake
CN106248680A (en) A kind of engine commutator quality detecting system based on machine vision and detection method
WO2012027869A1 (en) Online quality detection method for closure assembly
CN210071686U (en) Fruit grading plant based on orthogonal binocular machine vision
CN109507205A (en) A kind of vision detection system and its detection method
CN104990511A (en) Threaded hole structure quality detection method
CN106353340B (en) A kind of rodlike high reflectance surface defects of parts detection method
CN104315977A (en) Rubber plug quality detection device and method
CN109324056B (en) Sewing thread trace measuring method based on machine vision
CN106018422A (en) Matching-based visual outline defect inspection system and method for specially-shaped stamping parts
CN108844961A (en) A kind of temperature controller case vision detection system and method
Fu et al. Medicine glass bottle defect detection based on machine vision
Li et al. The method for glass bottle defects detecting based on machine vision
CN103091330A (en) Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20131225