CN102042812A - Visual machine detection method - Google Patents
Visual machine detection method Download PDFInfo
- Publication number
- CN102042812A CN102042812A CN 201010283688 CN201010283688A CN102042812A CN 102042812 A CN102042812 A CN 102042812A CN 201010283688 CN201010283688 CN 201010283688 CN 201010283688 A CN201010283688 A CN 201010283688A CN 102042812 A CN102042812 A CN 102042812A
- Authority
- CN
- China
- Prior art keywords
- gray
- scale value
- detected
- image
- detection method
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a visual machine detection method. The method comprises the following steps of: (1) image acquisition: carrying out shooting or scanning on a device to be detected to obtain an image to be detected; (2) gray value calculation: calculating the gray value of the image to be detected; (3) gray value comparison: operating an obtained gray value and a gray value of a standard image; and (4) area calculation: calculating the area of a region of which the gray value is larger than a threshold value in an operating result, and judging the device to be detected to be a good product or a defective product. The invention overcomes the defects of the prior art and provides a visual machine detection method capable of automatically carrying out appearance detection.
Description
Technical field
The present invention relates to a kind of machine vision detection method.
Background technology
The literal of outward appearances such as mobile phone, automobile, computer all needs to produce by spraying coating process, in the housing spraying production run of mobile phone, automobile etc., for guaranteeing to spray quality, need carry out outward appearance to the shell that spraying finishes and detect.At present, the outward appearance detection mode that producer adopts all is desk checking, and the desk checking result is often uncertain, and whether product is all place one's entire reliance upon workman's working experience of the judgement of non-defective unit and defective products, causes the product quality instability.On the other hand, the workman is repeating high-intensity work every day, and they accomplish can both accomplish to judge accurately to be impossible to each product to want requirement, therefore, because artificial carelessness probably causes the customer complaint and the return of goods, this can bring the very big money and the loss of fame to company.The efficient of desk checking simultaneously is low, need take great amount of manpower and time.And the literal of not only spraying needs outward appearance to detect, and whether the led lamp defective such as can light smoothly all needs personnel to detect.
Summary of the invention
Can automatically carry out the machine vision detection method that outward appearance detects in order to overcome the deficiency that prior art exists, to the object of the present invention is to provide.
For reaching above purpose, the invention provides a kind of machine vision detection method, comprise the steps:
(1) image acquisition step is treated detection means and is obtained image to be detected by taking pictures, make a video recording or scanning;
(2) gray-scale value calculation procedure is calculated the gray-scale value of image to be detected;
(3) gray-scale value contrast step is carried out computing with the gray-scale value that calculates and the gray-scale value of standard picture;
(4) area calculation procedure is calculated the area of gray-scale value among the result of computing greater than the zone of threshold value, judges that by area result of calculation device to be detected is non-defective unit or defective products.
Further improvement of the present invention is, between described image acquisition step and gray-scale value calculation procedure, also be provided with the block partiting step, described block partiting step is a block with image division, each block independently carries out described gray-scale value calculation procedure, gray-scale value contrast step and area calculation procedure, each block is independently discerned and is calculated, can effectively reduce mistake identification, also can accelerate the speed of computing.
Further improvement of the present invention is, between described image acquisition step and gray-scale value calculation procedure, also be provided with the RGB extraction step, R, G, the B value of the coloured image taken are extracted, by the RBG extraction step, can analyze the image of colour, even can be used for the LED-backlit detection.
Further improvement of the present invention is that in described gray-scale value contrast step, described computing is for subtracting computing.
The invention has the beneficial effects as follows: 1, by obtaining the product appearance picture, and the mode that picture carries out analyzing and processing obtained the testing result of product appearance, can carry out the detection of product appearance automatically, save manpower; 2, except that picture is calculated, can be provided with the area calculation procedure, by calculating the area in defective zone, whether the judgement product is qualified, prevents from the specification product erroneous judgement is substandard product, and testing result is more rationally with accurate.
Embodiment
Below preferred embodiment of the present invention is described in detail, thereby protection scope of the present invention is made more explicit defining so that advantages and features of the invention can be easier to be it will be appreciated by those skilled in the art that.
In the present embodiment, be example, principle of work of the present invention is described in detail in detail with the spraying printed words of sense colors.A kind of machine vision detection method comprises
(1) image acquisition step is treated detection means and is used camera to take pictures, and obtains the outward appearance picture of device to be detected, carries out subsequent step with this outward appearance picture as image to be detected.For the effect that guarantees that outward appearance detects, this step is carried out in a confined space, an annular lamp is set directly over device to be detected provides brightness as light source, and the center that camera is arranged on annular lamp is treated detection means and taken pictures.This mode can prevent that external light source from treating the lighting angle of detection means, brightness etc. and disturbing, and obtains the picture to be detected of unified illumination and lighting angle.
It should be noted that especially that for full-automatic board outward appearance detects board, and need to embed board inner and form interlock with the equipment of upstream and downstream, finishes the fully-automatic production process of product.In this case, can adopt scanner, the first-class device of shooting to speed time of shooting, obtain the picture of device to be detected.The Image Acquisition mode has multiple, and Image Acquisition mode to be detected does not limit protection scope of the present invention.
(2) block partiting step is with 9 blocks of image division to be detected for evenly arranging.9 blocks are independently carried out following steps.Certainly most of images to be detected part to be detected all is arranged in the centre of image, at this moment detect with regard to the edge that need not to treat detected image, and the zone line that only needs to treat detected image is divided, even each the pattern zone that can also treat detected image is divided.The partitioned mode of image to be detected does not limit protection scope of the present invention.
(3) RGB extraction step extracts R, G, the B value of the coloured image of 9 blocks.
(4) gray-scale value calculation procedure is calculated 9 each gray values of pixel points of block successively according to the R that extracts, G, B value.
(5) gray-scale value contrast step subtracts computing with the gray-scale value that calculates and the gray-scale value of standard picture; If wait upon detection means is specification product, the gray-scale value of the central area of printed words is identical with the gray-scale value of standard picture, fringe region compare with standard picture have fuzzy, so the gray-scale value of fringe region can be less than the gray-scale value of standard picture, the calculated value that subtracts the pattern central area of calculated result is 0 just, and the value that obtains is the gray-scale value after the computing of fringe region entirely.
If device to be detected is a substandard product, the central area that first kind of situation is printed words has disappearance or fuzzy, subtract calculated result after for the corresponding computing in disappearance zone gray-scale value and the gray-scale value after the computing of fringe region.Second kind of edge disappearance that situation is printed words, the result who at this moment subtracts computing is the gray-scale value of the corresponding standard picture in disappearance edge and the gray-scale value behind the remaining edge region-operation.The third situation be for should also occur printed words for the zone of blank, and at this moment operation result is the gray-scale value after the fringe region computing and the gray-scale value of white space.
(6) area calculation procedure, the area of gray-scale value among the result of computing greater than 180 zone calculated, if gray-scale value is greater than 180, expression printed words spraying too unclear or even do not spray out printed words, area is set at 5 pixels in the present embodiment, if monolithic area grayscale value surpasses 5 pixels greater than 180 area, the disappearance area of that spraying is excessive, will not accept, be judged to be defective products.Judge in human eye zone not easy to identify below the pixel if the area of disappearance is 5, be judged to be non-defective unit.
Can carry out different settings according to different products as the gray-scale value (as 180 in the present embodiment) of threshold value and area (as 5 pixels in the present embodiment); the yield and the fineness of the product that the difference of setting obtains are also inequality, do not limit protection scope of the present invention as the gray-scale value of threshold value and the variation of area.
By above embodiment as can be seen, the present invention is a kind of machine vision detection method that can automatically carry out the outward appearance detection.
Above embodiment only is explanation technical conceive of the present invention and characteristics; its purpose is to allow the people that is familiar with this technology understand content of the present invention and is implemented; can not limit protection scope of the present invention with this, all equivalences that spirit is done according to the present invention change or modification all is encompassed in protection scope of the present invention.
Claims (4)
1. a machine vision detection method is characterized in that: comprise the steps:
(1) image acquisition step is treated detection means and is obtained image to be detected by taking pictures, make a video recording or scanning;
(2) gray-scale value calculation procedure is calculated the gray-scale value of image to be detected;
(3) gray-scale value contrast step is carried out computing with the gray-scale value that calculates and the gray-scale value of standard picture;
(4) area calculation procedure is calculated the area of gray-scale value among the result of computing greater than the zone of threshold value, judges that by area result of calculation device to be detected is non-defective unit or defective products.
2. machine vision detection method according to claim 1, it is characterized in that: between described image acquisition step and gray-scale value calculation procedure, also be provided with the block partiting step, described block partiting step is a block with image division, and each block independently carries out described gray-scale value calculation procedure, gray-scale value contrast step and area calculation procedure.
3. machine vision detection method according to claim 1 is characterized in that: also be provided with the RGB extraction step between described image acquisition step and gray-scale value calculation procedure, R, G, the B value of the coloured image taken are extracted.
4. machine vision detection method according to claim 1 is characterized in that: in described gray-scale value contrast step, described computing is for subtracting computing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010283688 CN102042812A (en) | 2010-09-15 | 2010-09-15 | Visual machine detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010283688 CN102042812A (en) | 2010-09-15 | 2010-09-15 | Visual machine detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102042812A true CN102042812A (en) | 2011-05-04 |
Family
ID=43909172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010283688 Pending CN102042812A (en) | 2010-09-15 | 2010-09-15 | Visual machine detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102042812A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102621445A (en) * | 2012-03-31 | 2012-08-01 | 科络普线束技术(太仓)有限公司 | Device for detecting connecting terminal of automobile entertainment system |
| CN102854193A (en) * | 2012-08-30 | 2013-01-02 | 苏州天准精密技术有限公司 | Detection method and detection system used for image defect detection |
| 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 |
| CN105021624A (en) * | 2015-06-30 | 2015-11-04 | 中国人民解放军装甲兵工程学院 | Evaluation method of blockage of diamond grinding wheels in grinding ceramic |
| CN105184599A (en) * | 2014-05-12 | 2015-12-23 | 格瑞斯通数据技术有限公司 | Method of Remotely Determining the Condition of a Used Electronic Device |
| CN106546539A (en) * | 2016-09-19 | 2017-03-29 | 嘉兴科瑞迪医疗器械有限公司 | A kind of automatic blood type analytical instrument intelligent vision scanning system |
| CN109215026A (en) * | 2018-09-29 | 2019-01-15 | 广东工业大学 | A kind of accurate LED defect inspection method of high speed based on machine vision |
| CN109425426A (en) * | 2017-08-30 | 2019-03-05 | 南京钧乔行汽车灯具有限公司 | A kind of automobile lamp light detection method |
| CN109991237A (en) * | 2019-03-14 | 2019-07-09 | 上汽大通汽车有限公司 | Painting dressing automobiles skirt glue vision detection system and method |
| CN110441714A (en) * | 2019-07-31 | 2019-11-12 | Tcl王牌电器(惠州)有限公司 | Detection method, device and the computer readable storage medium of indicator light |
| CN110824105A (en) * | 2018-08-14 | 2020-02-21 | 领凡新能源科技(北京)有限公司 | Colloid detection method and colloid detection system |
| CN111835956A (en) * | 2019-04-16 | 2020-10-27 | 北京地平线机器人技术研发有限公司 | Camera control method and device, image acquisition equipment and electronic equipment |
| CN112945149A (en) * | 2021-01-26 | 2021-06-11 | 宁波诺视智能科技有限公司 | Detection device and detection method for riveting area of chain rivet |
| CN113029504A (en) * | 2021-03-04 | 2021-06-25 | 中国航空工业集团公司西安航空计算技术研究所 | Quantitative detection system and method for cooling air stagnation area of low-profile-rate gradually-expanding channel |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05209844A (en) * | 1992-01-30 | 1993-08-20 | Matsushita Electric Ind Co Ltd | Inspecting apparatus of wiring pattern |
| CN1653975A (en) * | 2005-01-06 | 2005-08-17 | 重庆大学 | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity |
| CN1801433A (en) * | 2006-01-11 | 2006-07-12 | 彩虹集团电子股份有限公司 | Plasma display screen fault checking method |
| CN101093246A (en) * | 2006-06-22 | 2007-12-26 | 上海理工大学 | Intellectualized online system for testing illuminating quality of headlight of an automobile built from LED |
| CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
-
2010
- 2010-09-15 CN CN 201010283688 patent/CN102042812A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05209844A (en) * | 1992-01-30 | 1993-08-20 | Matsushita Electric Ind Co Ltd | Inspecting apparatus of wiring pattern |
| CN1653975A (en) * | 2005-01-06 | 2005-08-17 | 重庆大学 | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity |
| CN1801433A (en) * | 2006-01-11 | 2006-07-12 | 彩虹集团电子股份有限公司 | Plasma display screen fault checking method |
| CN101093246A (en) * | 2006-06-22 | 2007-12-26 | 上海理工大学 | Intellectualized online system for testing illuminating quality of headlight of an automobile built from LED |
| CN101799434A (en) * | 2010-03-15 | 2010-08-11 | 深圳市中钞科信金融科技有限公司 | Printing image defect detection method |
Non-Patent Citations (1)
| Title |
|---|
| 《计算机工程与应用》 20051231 张宜生 等 基于图象比对技术的柔性印刷电路板检测系统 220-222 1-4 , 第2期 2 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102621445A (en) * | 2012-03-31 | 2012-08-01 | 科络普线束技术(太仓)有限公司 | Device for detecting connecting terminal of automobile entertainment system |
| CN102854193A (en) * | 2012-08-30 | 2013-01-02 | 苏州天准精密技术有限公司 | Detection method and detection system used for image defect detection |
| CN105184599A (en) * | 2014-05-12 | 2015-12-23 | 格瑞斯通数据技术有限公司 | Method of Remotely Determining the Condition of a Used Electronic Device |
| 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 |
| 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 |
| 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 |
| CN105021624A (en) * | 2015-06-30 | 2015-11-04 | 中国人民解放军装甲兵工程学院 | Evaluation method of blockage of diamond grinding wheels in grinding ceramic |
| CN106546539A (en) * | 2016-09-19 | 2017-03-29 | 嘉兴科瑞迪医疗器械有限公司 | A kind of automatic blood type analytical instrument intelligent vision scanning system |
| CN109425426A (en) * | 2017-08-30 | 2019-03-05 | 南京钧乔行汽车灯具有限公司 | A kind of automobile lamp light detection method |
| CN110824105A (en) * | 2018-08-14 | 2020-02-21 | 领凡新能源科技(北京)有限公司 | Colloid detection method and colloid detection system |
| CN109215026B (en) * | 2018-09-29 | 2022-02-11 | 广东工业大学 | High-speed accurate LED defect detection method based on machine vision |
| CN109215026A (en) * | 2018-09-29 | 2019-01-15 | 广东工业大学 | A kind of accurate LED defect inspection method of high speed based on machine vision |
| CN109991237A (en) * | 2019-03-14 | 2019-07-09 | 上汽大通汽车有限公司 | Painting dressing automobiles skirt glue vision detection system and method |
| CN111835956A (en) * | 2019-04-16 | 2020-10-27 | 北京地平线机器人技术研发有限公司 | Camera control method and device, image acquisition equipment and electronic equipment |
| CN111835956B (en) * | 2019-04-16 | 2022-07-12 | 北京地平线机器人技术研发有限公司 | Camera control method and device, image acquisition equipment and electronic equipment |
| CN110441714A (en) * | 2019-07-31 | 2019-11-12 | Tcl王牌电器(惠州)有限公司 | Detection method, device and the computer readable storage medium of indicator light |
| CN110441714B (en) * | 2019-07-31 | 2023-03-14 | Tcl王牌电器(惠州)有限公司 | Method and device for detecting indicator light and computer readable storage medium |
| CN112945149A (en) * | 2021-01-26 | 2021-06-11 | 宁波诺视智能科技有限公司 | Detection device and detection method for riveting area of chain rivet |
| CN113029504A (en) * | 2021-03-04 | 2021-06-25 | 中国航空工业集团公司西安航空计算技术研究所 | Quantitative detection system and method for cooling air stagnation area of low-profile-rate gradually-expanding channel |
| CN113029504B (en) * | 2021-03-04 | 2023-08-04 | 中国航空工业集团公司西安航空计算技术研究所 | Quantitative detection system and method for cooling air stagnation area of low-profile gradually-expanding channel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102042812A (en) | Visual machine detection method | |
| JP6325520B2 (en) | Unevenness inspection system, unevenness inspection method, and unevenness inspection program | |
| CN109916910B (en) | Photovoltaic glass edge defect detection system and corresponding method | |
| CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
| US12025564B2 (en) | Automated inspection of foreign materials, cracks and other surface anomalies | |
| CN102520537B (en) | Automatic optical inspection method and automatic optical inspection equipment | |
| CN102262093A (en) | Machine vision-based on-line detection method for printing machine | |
| US20130215261A1 (en) | Method For Detecting Defects In Glassware Articles, And Installation For Implementing Said Method | |
| CN104135660A (en) | Detection method of contamination of image pickup module and detection system | |
| CN104777172B (en) | A kind of quick, intelligent detection device of optical lens substandard products and method | |
| CN107144993B (en) | Display panel detection method and device | |
| CN106228541A (en) | Screen positioning method and device in visual inspection | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN108072664B (en) | Appearance detection system and method | |
| CN107219229A (en) | A kind of panel filtering dust method and device | |
| CN105510429B (en) | Fluorescent magnetic particle flaw detection detection method based on image procossing and detecting system | |
| CN104637425A (en) | Assembly-line LED (light emitting diode) display unit uniformity detection method, system and device | |
| CN105303565A (en) | Product appearance LOGO detection method | |
| CN209387542U (en) | A kind of detection device for eliminating material shade | |
| CN104977154A (en) | Defect classification method of spatial light modulator with sub pixel structures | |
| CN111238777A (en) | Display screen lighting defect detection method based on deep learning | |
| Tzu et al. | Non-uniformity evaluation of flat panel display by automatic optical detection | |
| CN108956628A (en) | Plastic cover plate defect imaging detection system | |
| CN108174199A (en) | The intelligent measurement and alignment system of a kind of view-based access control model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent for invention or patent application | ||
| CB02 | Change of applicant information |
Address after: Suzhou City, Jiangsu province 215122 Loufeng town Suzhou Industrial Park venture industrial square No. 17 factory Applicant after: Suzhou Linktron Electronic System Co., Ltd. Address before: Suzhou Industrial Park Suzhou city Jiangsu province 215000 Tang Zhuang Road No. 88 Building No. 1 Applicant before: Suzhou Linktron Electronic System Co., Ltd. |
|
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110504 |