CN104155306A - Soldering lug defect detection method for single-soldering-lug lamp cap - Google Patents
Soldering lug defect detection method for single-soldering-lug lamp cap Download PDFInfo
- Publication number
- CN104155306A CN104155306A CN201410349516.7A CN201410349516A CN104155306A CN 104155306 A CN104155306 A CN 104155306A CN 201410349516 A CN201410349516 A CN 201410349516A CN 104155306 A CN104155306 A CN 104155306A
- Authority
- CN
- China
- Prior art keywords
- weld tabs
- lamp holder
- defect
- soldering lug
- image
- 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.)
- Granted
Links
- 230000007547 defect Effects 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000005476 soldering Methods 0.000 title abstract 17
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000007689 inspection Methods 0.000 claims description 13
- 230000008034 disappearance Effects 0.000 claims description 11
- 229910052701 rubidium Inorganic materials 0.000 claims description 4
- IGLNJRXAVVLDKE-UHFFFAOYSA-N rubidium atom Chemical compound [Rb] IGLNJRXAVVLDKE-UHFFFAOYSA-N 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 abstract 2
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012372 quality testing Methods 0.000 description 3
- 230000004438 eyesight Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a soldering lug defect detection method for a single-soldering-lug lamp cap. The soldering lug defect detection mainly refers to defect detection of soldering lug missing, soldering lug deficiency, soldering lug plugging and soldering lug misplacement. The method comprises the following steps: firstly, placing a lamp cap on a green matte background zone and collecting a lamp cap image through a monocular industrial color camera with a light source; then segmenting the image and separating the lamp cap and a soldering lug from the image respectively; marking elements of a binary image of the soldering lug to determine whether the soldering lug missing defect exists or not, judging a statistical threshold value of the number of pixels of the binary image of the soldering lug to determine whether the soldering lug deficiency defect exists or not, judging a statistical threshold value of the number of pixels of a center hole of the soldering lug to determine whether the soldering lug plugging defect exists or not, judging the centroid consistency of the segmented lamp cap and soldering lug images to determine whether the soldering lug misplacement defect exists or not. Compared with prior art, the soldering lug defect detection method is capable of replacing manual detection and is high in detection speed and high in accuracy, the working efficiency is improved and considerable economic benefits are generated.
Description
Technical field
The present invention relates to lamp holder product quality detection technique field, be specifically related to a kind of single weld tabs lamp holder weld tabs defect inspection method.
Background technology
Lamp holder is the interface of lamp luminescence body and power supply, and as the main support parts of electric light source products, its quality testing occupies critical role in the production run of electric light source, has also directly determined the total quality level of light fixture.China's lamp holder product quality testing in process of production at present mainly still relies on people's vision and subjective judgement ability and takes the method for artificial sampling observation or full inspection to ensure the quality of product, take a large amount of manpowers, human cost is more and more higher, and owing to being subject to the impact of the factors such as individual eyesight, mood, fatigue, light, inefficiency, sorting difference is large, and this pattern has not met the requirement of the modern industry production automation, has already become enterprise and has raised the efficiency and the bottleneck of benefit.The quality testing of lamp holder is mainly for the detection of lamp holder weld tabs defect, single weld tabs lamp holder weld tabs defect comprises weld tabs disappearance, weld tabs is damaged, overfill, the stifled eye of weld tabs and weld tabs dislocation defect, these defects make produced electric light source products defective, cannot use, replace traditional detection method in the urgent need to studying a kind of new detection method for this reason, increase work efficiency.
Summary of the invention
For above-mentioned defect, the object of this invention is to provide a kind of single weld tabs lamp holder weld tabs defect inspection method, can automatically detect lamp holder weld tabs defect, thereby improve the detection efficiency of lamp holder product quality.
For achieving the above object, the technical solution used in the present invention is, a kind of single weld tabs lamp holder weld tabs defect inspection method, and its operation steps is as follows:
1). lamp holder image acquisition: lamp holder is placed on green sub-light background band, by automatic light source monocular industry color camera collection lamp holder image;
2). lamp holder image is cut apart: first adopt the fixed threshold dividing method based on color characteristic that lamp holder is separated from green background, then adopt the dynamic threshold segmentation method based on color characteristic to isolate weld tabs;
3). weld tabs disappearance defects detection: by weld tabs bianry image being carried out to rubidium marking to determine whether to exist weld tabs disappearance defect;
4). weld tabs defect flaw detects: judge to determine whether to exist weld tabs defect flaw by weld tabs bianry image pixel count statistical threshold;
5). the stifled eye of weld tabs defects detection: judge to determine whether to exist the stifled eye of weld tabs defect by weld tabs center hole pixel count statistical threshold;
6). weld tabs dislocation defects detection: by the judgement consistent with the weld tabs image centre of form of the lamp holder after cutting apart to determine whether to exist the weld tabs defect that misplaces.
The invention has the beneficial effects as follows: compared with prior art, the present invention is based on the weld tabs defect problem of machine vision non-contact detecting list weld tabs lamp holder, exempt the uncertain factor that manpower detects, the accuracy in detection of raising lamp holder product and efficiency, reduction business manpower cost, obtained good economic benefit.
Brief description of the drawings
Below in conjunction with drawings and Examples, concrete grammar of the present invention and principle of work are described in further detail.
Fig. 1 is overhaul flow chart of the present invention.
Fig. 2 is the instance graph in five kinds of situations of single weld tabs lamp holder weld tabs defect of the present invention.
Fig. 3 is the bianry image of Fig. 2 after image dividing processing step.
Fig. 4 is that the present invention blocks up by weld tabs the center hole image that eye defect detection procedure obtains.
In Fig. 2, when a. weld tabs disappearance, when b. weld tabs is damaged, c. weld tabs is stifled at the moment, when the dislocation of d. weld tabs.
In Fig. 3, bianry image when a1. weld tabs disappearance, bianry image when b1. weld tabs is damaged, the stifled eye of c1. weld tabs
Time bianry image, d1. weld tabs when dislocation bianry image.
Embodiment
Below in conjunction with drawings and Examples, embodiments of the present invention are further described.
Referring to Fig. 1, a kind of single weld tabs lamp holder weld tabs defect inspection method, its operation steps is as follows:
1). lamp holder image acquisition step: lamp holder is placed on green sub-light background band, and with automatic light source monocular industry color camera collection lamp holder picture, camera is apart from 10 centimetres, lamp holder.In gatherer process, camera automatic light source is opened, and the image of collection is colored RGB image (as Fig. 2); Image size is 320*240 pixel, to improve follow-up image processing speed.
2). lamp holder image segmentation step: because image background is green, obvious with lamp holder contrast, in this step, first adopt the fixed threshold dividing method based on green characteristic that lamp holder is separated from green background, then adopt the dynamic threshold segmentation method based on R-B color characteristic to isolate weld tabs.
3). weld tabs disappearance defect detection procedure: as shown in Figure 3, the weld tabs image after cutting apart is converted to bianry image, weld tabs bianry image is carried out to rubidium marking, if mark mark is not equal to 1, weld tabs disappearance.
4). weld tabs defect flaw detecting step: the pixel count to weld tabs bianry image is added up, according to the threshold value minimum value of the qualified lamp holder setting of standard weld tabs pixel, if statistical number is less than this threshold value minimum value, weld tabs is damaged.
5). the stifled eye of weld tabs defect detection procedure: as shown in Figure 4, weld tabs center is circular opening, hole is blocked as stifled eye defect, first hole is filled to overflow water filling algorithm, then image and original image after filling subtract each other and obtain hole image, hole bianry image are carried out to pixel count statistics, according to the threshold value minimum value of the qualified lamp holder setting of standard weld tabs center hole pixel, if statistical number is less than this threshold value minimum value, there is the stifled eye of weld tabs defect.
6). weld tabs dislocation defects detection: single weld tabs lamp holder that standard is qualified, in its image, the center of lamp holder and weld tabs overlaps, otherwise has weld tabs dislocation defect, therefore lamp holder and weld tabs image is carried out to center locating, if the elements of a fix are inconsistent, weld tabs dislocation.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention.All any amendments of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (7)
1. a single weld tabs lamp holder weld tabs defect inspection method, is characterized in that, described detection method comprises following operation steps:
1). lamp holder image acquisition: lamp holder is placed on green sub-light background band, by automatic light source monocular industry color camera collection lamp holder image;
2). lamp holder image is cut apart: lamp holder image is carried out to image and cut apart, lamp holder and weld tabs are separated respectively from image;
3). weld tabs disappearance defects detection: by weld tabs bianry image being carried out to rubidium marking to determine whether to exist weld tabs disappearance defect;
4). weld tabs defect flaw detects: judge to determine whether to exist weld tabs defect flaw by weld tabs bianry image pixel count statistical threshold;
5). the stifled eye of weld tabs defects detection: judge to determine whether to exist the stifled eye of weld tabs defect by weld tabs center hole pixel count statistical threshold;
6). weld tabs dislocation defects detection: by the judgement consistent with weld tabs picture centre of the lamp holder to after cutting apart to determine whether to exist the weld tabs defect that misplaces.
2. single weld tabs lamp holder weld tabs defect inspection method according to claim 1, is characterized in that: described lamp holder image acquisition step will be placed on lamp holder on green sub-light background band, use be automatic light source monocular industry color camera.
3. single weld tabs lamp holder weld tabs defect inspection method according to claim 1, it is characterized in that: described lamp holder image segmentation step first adopts the fixed threshold dividing method based on color characteristic that lamp holder is separated from green background, then adopt the dynamic threshold segmentation method based on color characteristic to isolate weld tabs.
4. single weld tabs lamp holder weld tabs defect inspection method according to claim 1, is characterized in that: the method that what described weld tabs disappearance defect detection procedure adopted is carries out rubidium marking to weld tabs bianry image detects weld tabs disappearance defect.
5. single weld tabs lamp holder weld tabs defect inspection method according to claim 1, is characterized in that: what described weld tabs defect flaw detecting step adopted is that the method that weld tabs bianry image pixel count statistical threshold is judged detects weld tabs defect flaw.
6. single weld tabs lamp holder weld tabs defect inspection method according to claim 1, is characterized in that: what the stifled eye of described weld tabs defect detection procedure adopted is that the method that weld tabs centre of form hole pixel count statistical threshold is judged detects the stifled eye of weld tabs defect.
7. the single weld tabs lamp holder of one according to claim 1 weld tabs defect inspection method, is characterized in that, what described weld tabs dislocation defects detection adopted is that the method for the judgement consistent with weld tabs picture centre of the lamp holder after cutting apart is detected weld tabs dislocation defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410349516.7A CN104155306B (en) | 2014-07-22 | 2014-07-22 | A kind of list weld tabs lamp cap weld tabs defect inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410349516.7A CN104155306B (en) | 2014-07-22 | 2014-07-22 | A kind of list weld tabs lamp cap weld tabs defect inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104155306A true CN104155306A (en) | 2014-11-19 |
| CN104155306B CN104155306B (en) | 2019-02-12 |
Family
ID=51880865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410349516.7A Expired - Fee Related CN104155306B (en) | 2014-07-22 | 2014-07-22 | A kind of list weld tabs lamp cap weld tabs defect inspection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104155306B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472767A (en) * | 2018-09-07 | 2019-03-15 | 浙江大丰实业股份有限公司 | Stage lamp miss status analysis system |
| 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 |
| CN110866916A (en) * | 2019-11-29 | 2020-03-06 | 广州大学 | Machine vision-based photovoltaic cell black-core black-corner detection method, device and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
| 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 |
| CN103471515A (en) * | 2013-09-10 | 2013-12-25 | 镇江胡氏光电科技有限公司 | Method for detecting double-soldering-lug lamp cap baldheaded defect |
-
2014
- 2014-07-22 CN CN201410349516.7A patent/CN104155306B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
| 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 |
| CN103471515A (en) * | 2013-09-10 | 2013-12-25 | 镇江胡氏光电科技有限公司 | Method for detecting double-soldering-lug lamp cap baldheaded defect |
Non-Patent Citations (3)
| Title |
|---|
| 王琪,陈路,乔兵: "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》 * |
| 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》 * |
| 胡鹏，王琪，乔兵: "全自动灯头质量机器视觉检测系统", 《灯与照明》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109472767A (en) * | 2018-09-07 | 2019-03-15 | 浙江大丰实业股份有限公司 | Stage lamp miss status analysis system |
| CN109472767B (en) * | 2018-09-07 | 2022-02-08 | 浙江大丰实业股份有限公司 | Stage lamp missing state analysis system |
| 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 |
| CN110866916A (en) * | 2019-11-29 | 2020-03-06 | 广州大学 | Machine vision-based photovoltaic cell black-core black-corner detection method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104155306B (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105548216B (en) | A kind of semi-finished product battery apparent visual detection method | |
| CN109406533A (en) | A kind of detection system and method for surface defects of products | |
| CN106238350B (en) | A kind of solar battery sheet method for separating and system based on machine vision | |
| CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
| CN109084957A (en) | The defects detection and color sorting process and its system of photovoltaic solar crystal-silicon battery slice | |
| CN107516308B (en) | Battery cap front side visual detection method | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN104010190B (en) | Method for automatically detecting dead pixels of mobile phone screen before assembling | |
| CN110434090A (en) | A kind of carrot surface flaw detecting method | |
| CN103529053B (en) | Bottle mouth defect detection method | |
| CN111766245B (en) | Button cell negative electrode shell defect detection method based on machine vision | |
| CN105466938B (en) | A kind of fabric defects detection information management system and method based on C/S structure | |
| CN103743757A (en) | Device and method for detecting foreign matters on inner wall of glass bottle | |
| CN104155306A (en) | Soldering lug defect detection method for single-soldering-lug lamp cap | |
| CN104118609A (en) | Labeling quality detecting method and device | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN104568989A (en) | Glass substrate defect detecting method | |
| CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
| CN108844961A (en) | A kind of temperature controller case vision detection system and method | |
| CN106596562A (en) | Magnet ring appearance quality on-line detection apparatus based on machine visual sense and method thereof | |
| CN104181167A (en) | Soldering lug defect detection method for bayonet double-soldering-lug lamp cap | |
| CN111008960B (en) | Aluminum electrolytic capacitor bottom appearance detection method and device based on machine vision | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN103163156A (en) | Automatic grading method of lens defects based on machine vision technology | |
| CN105092589A (en) | Detection method for defects of capsule head |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190212 |