CN102901735B - System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer - Google Patents
System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer Download PDFInfo
- Publication number
- CN102901735B CN102901735B CN201210313331.1A CN201210313331A CN102901735B CN 102901735 B CN102901735 B CN 102901735B CN 201210313331 A CN201210313331 A CN 201210313331A CN 102901735 B CN102901735 B CN 102901735B
- Authority
- CN
- China
- Prior art keywords
- workpiece
- defect
- certified products
- parameter
- fission
- 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.)
- Active
Links
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a system for carrying out automatic detections upon workpiece defect, cracking, and deformation by using a computer. With a computer image identification technology, three flaws of a workpiece, such as defect, cracking and deformation, can be automatically identified. First, a sample is sampled; qualified product parameter thresholds are obtained through training results of previous qualified products, or qualified product parameters are obtained through spot training; and qualification conditions of subsequent inputted workpieces are determined with the thresholds or the parameters as standards. The invention provides different algorithms aiming at different flaws. With the consideration of the differences in workpiece photographing situations, parameter adaptive adjustments are added into the algorithms, such that different photographing light intensities can be adapted to. Detection rates and missing rates of the three algorithms are respectively higher than 95% and lower than 5%, such that the effect is better than all previous algorithms.
Description
Technical field
The present invention relates to field of computer technology, specifically utilize computing machine to carry out the automatic system detected to workpiece defect, fission, distortion.
Background technology
At present, the processing of domestic part can the robotization of basic guarantee manufacturing procedure, but for the part defect occurred in process, i.e. substandard product, or depend on artificial screening in a large number.The disadvantage of this mode mainly contains:
Need very many manpowers.Along with the progressively rising of domestic human cost, the cost of part also can increase thereupon.
The subjectivity of artificial screening is strong.There is higher loss.
Lack defective data support, part processing enterprise is inconvenient to recall analyzing defect Producing reason
Therefore, image recognition is utilized to carry out to part the trend that fully-automated synthesis is development at present.
Summary of the invention
The present invention is directed to above shortcomings in prior art, a kind of computing machine that utilizes is provided the defect of workpiece, fission, distortion to be carried out to the system automatically detected, utilize computer vision technique, automatically detect the defect of workpiece, distortion and the algorithm of fission and the automatic checkout system framework based on this algorithm realization.While guarantee detects flaw article as much as possible, avoid false retrieval certified products.
For achieving the above object, the technical solution adopted in the present invention is as follows:
Utilize computing machine to carry out the automatic system detected to workpiece defect, fission, distortion, comprise concentrated collection end, certified products parameter training module, conventional data end for process, exclusive data end for process and final TB control module, wherein:
-concentrated collection end, blames workpiece data sampling, and delivers to system after carrying out automatic classification and process.Because the position of workpiece, defect is different, defect must be accomplished to sample into picture at collection terminal.
-conventional data end for process, for not specific component and the not detection of ad-hoc location and process;
This part is mainly for the defect of entirety and the detection of fission and process.
-exclusive data control end, the defect for occurring for specific component carries out detecting and processing;
This part carries out detecting and processing mainly for the defect in workpiece deformation.
Result is given TB control module by-described conventional data end for process and exclusive data end for process, exports the error message of workpiece by the process of TB control module in charge.
Described certified products parameter training module is by carrying out image procossing to certified products, extract characteristic parameter, utilize law of great numbers, judge that it meets normal distribution, the variance being added and subtracted 3 times by mean value is obtained between certified products parameter region, and all can be considered unacceptable product not in this parameter distribution.
Described conventional data control end, by processing the not specific component of input and the image of not ad-hoc location, judges whether it is unacceptable product.
Described conventional data end for process comprises with lower device: defect judge module, for judging this workpiece whether defect; Fission judge module, for judging whether this workpiece fissions.
Defect judge module in conventional data end for process, first according to the automatic computed segmentation parameter of the gray-scale map of photo current, the size calculating largest connected region by binaryzation obtains the area of workpiece, and train the parameter obtained to compare with by certified products, if be less than, workpiece defect can be judged.Then result is sent to TB control module.
Fission judge module in conventional data end for process, mainly for the fission in surface of the work, namely the silver layer cracking of surface of the work exposes layers of copper etc.The first same saturation degree space according to picture of this module, obtain subregion easy to crack, because cracking part is different from the saturation degree space of the part for ftractureing, to can find after image binaryzation that obvious black and white is distinguished, calculate the area in largest connected region, train the parameter obtained to compare with by certified products, if be greater than this value, then think and fission.Result is directly sent to TB control module.
Described exclusive data control end is processed by the image of the specific component to input, judges whether it is unacceptable product.
Described exclusive data end for process comprises distortion judge module: for judging workpiece whether angular distortion.
Distortion judge module in exclusive data end for process, judges namely whether there is angular distortion mainly for the planarization in workpiece.The image needed due to this module is generally the side image of workpiece, so need to work in exclusive data end for process.This module is first according to input picture, image is divided into multiple part, after utilizing skeleton thinning algorithm to carry out refinement to each part, remove noise, the skeleton utilizing hough to convert for refinement subsequently obtains near linear, carries out differential comparison, the results contrast of the result obtained and certified products training module to the slope of different piece straight line, if the absolute value of each differential seat angle is greater than the parameter value of certified products, be then judged as angular distortion.Then result is delivered to TB control module.
When the present invention works, if status conditions is taken in previous shooting situation and this time change, then first with concentrated collection end, the photo of certified products is issued certified products parameter training module, allow it carry out parameter and automatically train.Complete or when not needing to carry out parameter training at parameter training, native system life's work.First by concentrated collection end, workpiece is taken, and by photo automatic classification, to the overall workpiece judged be needed to deliver to conventional data end for process, deliver to exclusive data end for process by what need to take privileged sites (namely angular distortion needs shooting workpiece angled portion).Conventional data end for process, by built-in algorithm and train the parameter obtained before, carries out defect judgement to workpiece photo respectively and fission judges, if find mistake, mistake is delivered to TB control module.Exclusive data end for process, by built-in algorithm and train the parameter obtained before, carries out the judgement of angular distortion respectively to workpiece photo, if find mistake, mistake is delivered to TB control module.Final TB control module, exports defective for workpiece type.
Compared with prior art, the invention employ parameter adaptive design, the function of the automatic identification workpiece, defect that utilized computer vision technique really to accomplish, compensate for existing deficiency of manually carrying out workpiece, defect detection.By detecting great amount of samples, utilization result of the present invention is quite outstanding, and the defect of every type all reaches the verification and measurement ratio of more than 95% and the fallout ratio of less than 5%.
Accompanying drawing explanation
Make a detailed description technical solution of the present invention below by way of accompanying drawing, by accompanying drawing, technical solution of the present invention is described in order to clearer, following accompanying drawing all have employed the background color of band gray scale:
Fig. 1 is system framework figure of the present invention;
Fig. 2 ~ Fig. 4 be the concentrated collection end of the embodiment of the present invention collect correspond respectively to defect, the defect ware sample of fission and angular distortion and certified products sample graph;
Fig. 5 is the gray-scale map of defect defect ware in Fig. 2;
Fig. 6 is the binary map of Fig. 5;
Fig. 7 is the fission region of the Fig. 3 extracted;
Fig. 8 is the binary map of the fission defect ware form one of Fig. 7;
Fig. 9 is the binary map of the fission defect ware form two of Fig. 7;
Figure 10 is the binary map of certified products of fissioning in the embodiment of the present invention;
Figure 11 is the fission defect ware binary map in the embodiment of the present invention after scan-line algorithm is extracted;
Figure 12 is the binary map of the distortion defect ware of Fig. 4;
Figure 13 is the string diagram that Figure 12 obtains after skeletal extraction algorithm;
Figure 14 be Figure 13 is divided into three parts carry out hough conversion respectively after near linear figure.
Embodiment
Elaborate to embodiments of the invention below in conjunction with accompanying drawing, the present embodiment is implemented under premised on invention technical scheme, give detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
The task of the present embodiment workpiece is carried out to the detection of three types.
As shown in Figure 1, the present invention includes 5 modules: concentrated collection end, certified products parameter training module, conventional data end for process, exclusive data end for process and TB control module.
By concentrated collection end, obtain three samples pictures, the respectively defect ware sample (the right figure in Fig. 2) corresponding to defect as shown in Figure 2 and certified products sample (the left figure in Fig. 2), the defect ware sample (the right figure in Fig. 3) corresponding to fission as shown in Figure 3 and certified products sample (the left figure in Fig. 3) and the defect ware sample (the right figure in Fig. 4) corresponding to angular distortion as shown in Figure 4 and certified products sample (the left figure in Fig. 4).
As shown in Figure 2, left figure is certified products, and right figure has defect ware.Right figure can see that there is defect in the lower left corner significantly.Be described by the flow process of legend for defect product below.
As shown in Figure 5, this figure is the gray-scale map of the defect ware in Fig. 2, by extracting the mean value of gray-scale map, being multiplied by the fixed constant after a certain training, after binaryzation, obtaining binary map as shown in Figure 6.The reason that extraction mean value is multiplied by fixed constant is, prevents because shooting light is different, the gray-scale value deviation caused, due to each gray-scale value even variation, admittedly use the method can accomplish binaryzation threshold self-adaptative adjustment.Now according to the binary map that obtains as shown in Figure 6, calculate largest connected region, the number of largest connected white pixel, train the parameter obtained to compare with certified products before, then can be judged to be defect product.
As shown in Figure 7, this figure is the fission region extracted according to workpiece size, in fact, if fission region is positioned at whole workpiece, also can not extract region, in this example, because fission is only present on the silver layer of workpiece, therefore extracts region enhancing specific aim.Average is utilized to be multiplied by fixed constant as the binary map obtained after the threshold of binaryzation as shown in Figure 8 equally.Here we need to extract real fission region, and reason be the to fission paint on normally upper strata falls to exposing the color of bottom, and in this example, bottom is copper, and what expose is copper equally, therefore need to extract silver layer position thus remove incoherent copper face.What take here is scan-line algorithm, both started from the bottom up with one with sweep trace scanning, when this be scanned across line meet below two conditions for the moment, we think that this line is the cut-off rule of silver-colored face and copper face: 1. the pixel of the unnecessary white of the pixel of black; 2. the block number of black region is greater than a certain predetermined value.If if this algorithm considers that cracking part and copper face are not wanted to connect, as shown in Figure 8, then scheme 1 meets.If cracking part is connected with copper face, as shown in Figure 9, then scheme 2 meets.The correctness of this algorithm ftractures based on the copper flat smooth in complete copper face the desultory phenomenon of copper of part.From test result, this algorithm is effective.As shown in Figure 10, the silver-colored face portion of certified products is smooth.As shown in figure 11, to calculate in the cross section extracted through scan-line algorithm the area of white, train the value obtained to think by certified products to fission if be greater than.
As shown in figure 12, this figure is the binary map after the self adaptive adjustment of threshold.Figure 13 is the result that this binary map obtains after skeletal extraction algorithm.Shown in Figure 14, the lines in Figure 13 are divided into three parts, carry out hough(Hough respectively) conversion, grey parts is the straight line extracted.The angle of the straight line obtained is subtracted each other, and compares with the parameter of certified products, the Part III in Figure 14 can be found, obviously do not become 90 degree with the Part II in Figure 14, then think angular distortion.
Finally result is all delivered to TB control module, the type of TB control module output error.
Above specific embodiments of the invention are described.It is to be appreciated that the present invention is not limited to above-mentioned particular implementation, those skilled in the art can make various distortion or amendment within the scope of the claims, and this does not affect flesh and blood of the present invention.
Claims (3)
1. the system utilizing computing machine to carry out automatically detecting to workpiece defect, fission, distortion, it is characterized in that, comprise concentrated collection end, certified products parameter training module, conventional data control end, exclusive data control end and final TB control module, wherein:
-concentrated collection end, for being responsible for workpiece data sampling, and delivering to system after carrying out automatic classification and processes;
-certified products parameter training module, for automatically training the parameters of certified products, by carrying out image procossing to certified products, extract characteristic parameter, utilize law of great numbers, judge that it meets normal distribution, the variance being added and subtracted 3 times by mean value is obtained between certified products parameter region, and all can be considered unacceptable product not in this parameter distribution;
-conventional data control end, for processing the not specific component of input and the image of not ad-hoc location, judges whether it is unacceptable product;
-exclusive data control end, the image for the specific component to input processes, and judges whether it is unacceptable product;
-TB control module, result is given TB control module by described conventional data end for process and exclusive data end for process, exports the error message of workpiece by the process of TB control module in charge.
2. the computing machine that utilizes according to claim 1 carries out the automatic system detected to workpiece defect, fission, distortion, and it is characterized in that, described conventional data control end comprises with lower device:
Defect judge module, for judging this workpiece whether defect;
Described defect judge module is first according to the automatic computed segmentation parameter of the gray-scale map of photo current, the size calculating largest connected region by binaryzation obtains the area of workpiece, and train the parameter obtained to compare with by certified products, if be less than, workpiece defect can be judged, result be sent to TB control module;
Fission judge module, for judging whether this workpiece fissions;
Described fission judge module is mainly for the fission in surface of the work, first according to the saturation degree space of picture, obtain subregion easy to crack, because cracking part is different from the saturation degree space of the part that do not ftracture, by finding after image binaryzation that obvious black and white is distinguished, calculate the area in largest connected region, the parameter obtained is trained to compare with by certified products, if be greater than this value, then think and fission, result is directly sent to TB control module.
3. the computing machine that utilizes according to claim 1 carries out the system automatically detected to workpiece defect, fission, distortion, and it is characterized in that, described exclusive data control end comprises distortion judge module, for judging workpiece whether angular distortion;
Described distortion judge module is first according to input picture, image is divided into multiple part, after utilizing skeleton thinning algorithm to carry out refinement to each part, remove noise, the skeleton utilizing hough to convert for refinement subsequently obtains near linear, carries out differential comparison to the slope of different piece straight line, the results contrast of the result obtained and certified products training module, if the absolute value of each differential seat angle is greater than the parameter value of certified products, be then judged as angular distortion, result delivered to TB control module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210313331.1A CN102901735B (en) | 2012-08-29 | 2012-08-29 | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210313331.1A CN102901735B (en) | 2012-08-29 | 2012-08-29 | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102901735A CN102901735A (en) | 2013-01-30 |
| CN102901735B true CN102901735B (en) | 2015-02-25 |
Family
ID=47574088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210313331.1A Active CN102901735B (en) | 2012-08-29 | 2012-08-29 | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102901735B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104048968A (en) * | 2014-06-04 | 2014-09-17 | 上海美迪索科电子科技有限公司 | Industrial processing part automatic defect identification system |
| CN104197836A (en) * | 2014-09-13 | 2014-12-10 | 江南大学 | Vehicle lock assembly size detection method based on machine vision |
| JP2018179698A (en) * | 2017-04-11 | 2018-11-15 | オムロン株式会社 | Sheet inspection device |
| CN109255787B (en) * | 2018-10-15 | 2021-02-26 | 杭州慧知连科技有限公司 | System and method for detecting scratch of silk ingot based on deep learning and image processing technology |
| CN109463894A (en) * | 2018-12-27 | 2019-03-15 | 蒋梦兰 | Configure the full water-proof type toothbrush of half-moon-shaped brush head |
| CN111667094A (en) * | 2020-04-22 | 2020-09-15 | 深圳市吉迩科技有限公司 | Automatic detection method, system and device |
| CN112720500B (en) * | 2020-12-30 | 2022-07-01 | 深兰智能科技(上海)有限公司 | Control method and device for manipulator, pickup device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221135A (en) * | 2008-01-17 | 2008-07-16 | 中国电子科技集团公司第四十五研究所 | Printed circuit board image skeletonization method based on FPGA |
| CN201229307Y (en) * | 2008-07-18 | 2009-04-29 | 深圳市联君科技有限公司 | Novel cigarette package intelligent detection device |
| CN101799431A (en) * | 2010-04-08 | 2010-08-11 | 湖南大学 | Machine visual on-line detection method and equipment for tank cover quality in high-speed production line |
| CN102095733A (en) * | 2011-03-02 | 2011-06-15 | 上海大学 | Machine vision-based intelligent detection method for surface defect of bottle cap |
| CN102253050A (en) * | 2011-03-14 | 2011-11-23 | 广州市盛通建设工程质量检测有限公司 | Automatic detection method and device for magnetic tile surface defect based on machine vision |
| CN102621156A (en) * | 2012-03-07 | 2012-08-01 | 武汉理工大学 | Image-processing-based automatic micro part sorting system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS56161651A (en) * | 1980-05-15 | 1981-12-12 | Mitsubishi Electric Corp | Malfunction analysing method of semiconductor element |
| JP2003329596A (en) * | 2002-05-10 | 2003-11-19 | Mitsubishi Rayon Co Ltd | Apparatus and method for inspecting defect |
-
2012
- 2012-08-29 CN CN201210313331.1A patent/CN102901735B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101221135A (en) * | 2008-01-17 | 2008-07-16 | 中国电子科技集团公司第四十五研究所 | Printed circuit board image skeletonization method based on FPGA |
| CN201229307Y (en) * | 2008-07-18 | 2009-04-29 | 深圳市联君科技有限公司 | Novel cigarette package intelligent detection device |
| CN101799431A (en) * | 2010-04-08 | 2010-08-11 | 湖南大学 | Machine visual on-line detection method and equipment for tank cover quality in high-speed production line |
| CN102095733A (en) * | 2011-03-02 | 2011-06-15 | 上海大学 | Machine vision-based intelligent detection method for surface defect of bottle cap |
| CN102253050A (en) * | 2011-03-14 | 2011-11-23 | 广州市盛通建设工程质量检测有限公司 | Automatic detection method and device for magnetic tile surface defect based on machine vision |
| CN102621156A (en) * | 2012-03-07 | 2012-08-01 | 武汉理工大学 | Image-processing-based automatic micro part sorting system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102901735A (en) | 2013-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| CN101995223B (en) | Chip appearance detection method and system | |
| WO2023221801A1 (en) | Image processing method and apparatus, computer-readable storage medium, and electronic device | |
| CN107389701A (en) | A kind of PCB visual defects automatic checkout system and method based on image | |
| CN108982512A (en) | A kind of circuit board detecting system and method based on machine vision | |
| CN105046700A (en) | Brightness correction and color classification-based fruit surface defect detection method and system | |
| CN111289538A (en) | PCB element detection system and detection method based on machine vision | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| CN106251333B (en) | Element reverse detection method and system | |
| CN111524101A (en) | Electronic screen defect detection method based on machine vision technology | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
| CN114636706A (en) | Comprehensive method and device for image detection of solar cell after film coating | |
| CN106228541A (en) | Screen positioning method and device in visual inspection | |
| CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
| WO2017071406A1 (en) | Method and system for detecting pin of gold needle element | |
| CN109870463B (en) | Electronic chip fault detection device | |
| CN115170501A (en) | Defect detection method, system, electronic device and storage medium | |
| CN114972204A (en) | Steel product surface crack detection method and equipment | |
| CN111724375B (en) | Screen detection method and system | |
| WO2023168984A1 (en) | Area-array camera-based quality inspection method and system for cathode copper | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN106353340A (en) | Surface defect detection method for rod-like high-reflectance part |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |