CN100593716C - On-line detecting method of machine vision system for printed calico flaw - Google Patents

On-line detecting method of machine vision system for printed calico flaw Download PDF

Info

Publication number
CN100593716C
CN100593716C CN200710135139A CN200710135139A CN100593716C CN 100593716 C CN100593716 C CN 100593716C CN 200710135139 A CN200710135139 A CN 200710135139A CN 200710135139 A CN200710135139 A CN 200710135139A CN 100593716 C CN100593716 C CN 100593716C
Authority
CN
China
Prior art keywords
image
calico
standard picture
real
flaw
Prior art date
Application number
CN200710135139A
Other languages
Chinese (zh)
Other versions
CN101158650A (en
Inventor
董仲伟
庞彦清
Original Assignee
无锡东望科技有限公司
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 无锡东望科技有限公司 filed Critical 无锡东望科技有限公司
Priority to CN200710135139A priority Critical patent/CN100593716C/en
Publication of CN101158650A publication Critical patent/CN101158650A/en
Application granted granted Critical
Publication of CN100593716C publication Critical patent/CN100593716C/en

Links

Abstract

The invention relates to an online detecting method of a machine vision system for detecting blemishes of a printed cloth. The invention aims at solving the problem that the labor intensity of manualonline detecting blemishes of the printed cloth is high, and the detecting quality is bad. Clear and thorough, and spotless graphs are shot on the running printed cloth through industrial camera. Theclear and thorough, and spotless graphs are stored in the calculating machine as a standard graph molding board. The blemish area and graphic gray value are taken as the detecting parameter of the blemish. The precision scope of the detecting parameter is arranged according to the requirement of the consumer. The graphs of the running printed cloth are shot in real-time, and are conveyed to the calculating machine. The real-timely shot graphs are compared with the standard graph molding board and are dealt with. If a blemish appears, the operating personnel are indicated to deal with the blemish of the printed cloth through an alarm. The alarm is started through the calculating machine. The invention can carry out light intensity self-compensating of the standard graph molding board, and dynamically correcting the shift of the pixel of the real-timely shot printed cloth graphs. The invention has the advantages of high precision and fast speed of detecting blemishes of the printed cloth, and greatly reduced labor intensity of manual detecting.

Description

Utilize Vision Builder for Automated Inspection that the calico flaw is carried out on-line detection method
Technical field
The present invention relates to utilize Vision Builder for Automated Inspection to carry out the technical field of online detection, relate in particular to, utilize Vision Builder for Automated Inspection that the flaw of calico is carried out on-line detection method in the calico production scene.
Background technology
At the workshop scene of line production printing and dyeing calico, need carry out online detection to the flaw of calico.In the prior art, the online detection of calico flaw relied on manually detect, be provided with 2-4 people in the both sides of printing machine the flaw of calico is estimated and handled, and establish tracking, the detection that 1 people carries out product quality at oven dry cropping place.The shortcoming of its existence has: on-the-spot humiture is very high, and workman's testing environment is abominable, and labour intensity is big; The workman works long hours and is easy to generate visual fatigue, can't guarantee to detect quality, therefore can't guarantee the qualification rate of product export.
Summary of the invention
Big and be easy to generate visual fatigue, can't guarantee to detect quality and the low problem of product export qualification rate at prior art to the online manual detection labour intensity of calico flaw, the invention provides the online test method of a kind of Vision Builder for Automated Inspection to the calico flaw, it reduces workman's detection labour intensity greatly, the degree of accuracy height of Defect Detection, the qualification rate of the product that can effectively guarantee to dispatch from the factory.
The technical scheme of the inventive method is as follows:
A kind of Vision Builder for Automated Inspection of utilizing is carried out on-line detection method to the calico flaw, may further comprise the steps:
(1). utilize industrial camera and control the image that described industrial camera is taken the on-line operation calico by outer triggering signal;
(2). according to the requirement of user, adjust aperture size, time shutter and the amount of gain of described industrial camera, so that the calico image of shooting clear to calico color, decorative pattern size and fineness;
(3). select complete display, flawless calico image is stored in computing machine as the standard picture template, every described industrial camera stores a width of cloth standard picture template;
(4). flaw area and gradation of image value are set at the detection parameter of calico flaw, and the accuracy rating of described detection parameter is set according to customer requirements;
(5). control described industrial camera by outer triggering signal, take the image of on-line operation calico in real time, and the image of taking is transferred to computing machine for detecting;
Meanwhile, by following step described standard picture template of (3) step is carried out the dynamic auto compensation of image intensity: the gradation of image mean value of the on-line operation calico image that above-mentioned real-time shooting is obtained compares with (3) the gradation of image mean value that goes on foot the standard picture template, variation has taken place in the gradation of image mean value that obtains as real-time shooting, then the gradation of image value with described standard picture template multiply by the luminosity compensation coefficient automatically, be stored in computing machine as new standard picture template, enter following (6) step again, contrast is used when detecting the calico image of taking in real time for (6) step, and wherein the luminosity compensation coefficient is the ratio of the average gray of the average gray of real-time photographic images and standard picture template image; Do not change as gradation of image mean value, then the standard picture template is not carried out the compensation of image intensity, directly enter following (6) step;
And meanwhile, proofread and correct the displacement of taking on-line operation calico image pixel in real time dynamically by following step:
A). the position of image pixel compares in the position of the on-line operation calico image pixel that described real-time shooting is obtained and described (3) the step reference image template, judge whether to occur the displacement of real-time photographic images pixel location, if displacement, then turn to following b) to c) step, otherwise the correction that is not shifted directly enters following (6) step;
B). will judge that the coordinate position of the real-time photographic images pixel of displacement appears in the back through a) step, by Computing, in (3) step standard picture template the coordinate position of corresponding pixel move;
C). by b) step moves after the pixel coordinates position, the pixel location in the standard picture template that obtains with above-mentioned (3) step compares again, and still whether the pixel location of judging calico displacement, if no longer displacement then enters described (6) step; If still displacement then continues above b) step, the pixel location in the standard picture template that obtains with (3) step relatively back does not have displacement, and the correction that then no longer is shifted enters following (6) step then;
(6). process the image intensity that the real-time shooting that computing machine obtained for (5) step and the image of calibrated pixel shift and (5) step obtain compensates standard picture template afterwards automatically and compares, analyzes, differentiates, occur if any the flaw outside the detection parameter accuracy rating of (4) step setting, then by the computer starting warning device, alert is handled the calico flaw, continues the operation in (5) step afterwards; As do not have above-mentioned flaw appearance, then directly continue the operation in (5) step.
The technique effect of the inventive method:
The present invention adopts Vision Builder for Automated Inspection that the calico flaw is carried out online detection, replace manual detection, occur if any flaw, then in image, identify the position of flaw by friendly man-machine interface, and give the acousto-optic electric alarm, alert is carried out the flaw processing, reduces workman's detection labour intensity greatly; According to customer requirements on the calico of operation, select complete display, flawless image is stored in computing machine as the standard picture template, rather than set up complicated flaw model storehouse in advance as the standard picture template according to customer requirements, more suit the actual conditions that consumer products detects, improve the accuracy and the qualification rate of user's calico Defect Detection; Flaw area and gradation of image value are set at the detection parameter of calico flaw, and the accuracy rating of described detection parameter is set according to customer requirements, and avoid setting up various Defect Detection parameter, can reach customer requirements, can effectively improve detection speed again, check speed can reach the 100m/ branch; When taking the intensity of illumination variation of on-line operation calico image in real time, the inventive method can be carried out the automatic compensation of image intensity to the standard picture template, thereby can guarantee the accuracy of standard picture template, can accurately judge product defect; When the calico of on-line operation is mobile all around when real-time the shooting, make easily the image pixel of clapping displacement, with the pixel of standard picture template relatively the time, influence the accuracy of Defect Detection, the inventive method can be taken the displacement of on-line operation calico image pixel in real time from normal moveout correction, realize taking in real time the automatic contraposition of on-line operation calico image pixel, the image and (5) that real-time shooting and calibrated pixel are shifted goes on foot the automatic compensation of the process image intensity that obtains standard picture template afterwards and carries out correct contrast, analyze and differentiation, effectively improve accuracy the calico Defect Detection.
Description of drawings
Fig. 1 is the pattern of calico standard picture template;
Fig. 2 is " dislocation " flaw pattern in the calico image;
Fig. 3 is " disappearance " flaw pattern in the calico image;
Fig. 4 is " stain " flaw pattern in the calico image;
Fig. 5 is the synoptic diagram of the automatic contraposition of calico image;
Fig. 6 is a process sequence diagram of the present invention.
Embodiment
Below to the detection of calico flaw for example, further specify the inventive method.
Embodiment 1, to the detection of " dislocation " flaw in the calico image:
A. adopt white cotton, image as shown in Figure 1, as detecting embodiment cloth.
B. with 4 of the sincere 1300UM type industry in Xi'an side cameras, laterally evenly arrange stuck-at-.5m height along calico, camera uses 8mmCOMPUTAR type camera lens, aperture is transferred to maximal value, and the time shutter is adjusted to 0.58ms, and yield value (the contrast effect of its decision image) is adjusted to 0; Adopt the white light source of 2.65MHZ, directly over irradiation so that to the irradiation relative insensitivity of the color and the decorative pattern of cloth, and to the irradiation sensitivity of flaw; The power supply of display light source is a constant pressure and flow, is the stabilized light source that tool does not become frequently or high frequency becomes, so that can photograph flaw image clearly more stablely, and is shown in the screen of computing machine.
C. start external trigger and control signal automatically by computing machine, start camera and take the image of the calico of on-line operation, select calico image complete display, flawless to be stored in the computing machine by operating personnel as the standard picture template, every camera is taken respectively simultaneously and is stored a width of cloth standard picture template (see Fig. 1, calculating in 4 cameras respectively by computing machine in the present embodiment, the standard picture average gray as shown in Figure 1 of storage is respectively 127) in the memory of computing machine;
D. flaw area and gradation of image value are set at two of flaw and detect parameters, getting calico, to walk cloth speed be 100 meters/minute, the accuracy rating that the detection of flaw area is set according to customer requirements is 3 square millimeters, the accuracy rating of gradation of image value is 50, the difference that is the flaw area gradation of image value that surpasses 3 square millimeters or gradation of image value and standard picture template then is judged to be underproof flaw above 50;
E. start outer triggering signal automatically by computing machine and control described shooting camera, take the image of on-line operation calico in real time, meanwhile, respectively the image of standard picture template and shooting is in real time handled by following step:
A, light intensity when the standard picture template is taken is carried out dynamic auto compensation: the gradation of image mean value during to real-time photographic images (the gradation of image mean value when calculating 4 real-time photographic images of camera by computing machine in the present embodiment is respectively 75) compares with above-mentioned standard picture template image average gray (127), because variation has taken place in gradation of image mean value, the gradation of image value of described each pixel of standard picture template be multiply by luminosity compensation coefficient 75/127 respectively automatically, as new standard picture template be stored in computing machine in, at this moment, the gradation of image mean value of new standard picture template is compensated for as 75 (that is: 127 * 75/127) automatically; (annotate: do not change as light intensity, then need not the standard picture template is carried out the compensation of image intensity, the image that computing machine will be taken in real time compares, analyzes and differentiate with standard picture template for the first time.The flaw that detects outside the parameter accuracy rating if any two of above-mentioned setting occurs, and then by the computer starting warning device, after alert is handled the calico flaw, continues to take in real time the image of calico; As do not have the flaw that two of above-mentioned setting detects outside the parameter accuracy ratings and occur, then continue to take in real time the image of calico).
B, proofread and correct the position of real-time photographic images pixel as follows, to carry out the automatic contraposition of image pixel in the real-time photographic images:
A). the pixel location that will take in real time in the standard picture template that pixel location in the whole breadth image of calico and top a step obtain compares, judge whether to occur the displacement of pixel location, if displacement shown in Figure 5, then turn to following b) to c) step carries out automatic contraposition, otherwise directly enters described (6) step;
B). with the coordinate position of the pixel of the appearance of above-mentioned shooting displacement, the computerized algorithm X by known technology (i, j)=X (i+1, j) and X (i, j)=X (i, j+1) loop computation in the standard picture template the coordinate position of corresponding pixel move;
C). by b) step moves after the pixel coordinates position, the pixel location in the standard picture template that obtains with above-mentioned a step compares again, and still whether the pixel location of judging calico displacement, if no longer displacement then enters described (6) step; If still displacement then continues above b) step, the pixel location in the standard picture template that obtains with a step relatively back does not have displacement, enters described (6) step then.
In the present embodiment,, the displacement of image pixel position do not occur, therefore directly enter described (6) step through after the above-mentioned a) step:
The standard picture template that the on-line operation calico image taken in real time and above-mentioned a step are obtained compares, analyzes and differentiates, wherein camera photographs " dislocation " flaw image of calico pattern shown in Figure 2, and the dash area among Fig. 2 in the dashed region is the dislocation defect areas.By COMPUTER CALCULATION and the gradation of image mean value that demonstrates each pixel in " dislocation " shown in Figure 2 flaw is 138, the difference of the gradation of image value 75 of itself and above-mentioned new standard picture template is 63, the flaw area is 9 square millimeters, surpass the accuracy rating that sets, this moment is by the computer starting warning device, operating personnel after the flaw defective that causes this calico flaw is handled, continue to take in real time the image of calico by checking.(annotate: in the difference and flaw area two parameters as above-mentioned gradation of image value, only a parameter surpasses accuracy rating, and computing machine also can start warning device.)
The control system (hardware and software) of image acquisition of using in the present embodiment (shooting) and storage device (camera, radiation source, power supply etc.), image processing equipment (hardware of image processor and software), image display (hardware and software), warning device and each part mentioned above all adopts prior art to design and produce or directly adopts the commercially available prod, the above-mentioned Related product that for example DVT, SONY, Siemens, NI, CCS, Xi'an Fang Cheng, Beijing are littlely looked, the big identical company in Beijing produces.
Embodiment 2: to the detection of calico pattern " disappearance " flaw:
It is identical with embodiment 1 to detect embodiment cloth, capture apparatus and operation steps.With 4 in Xi'an side's sincere 1300UM type camera, laterally evenly to arrange along calico, stuck-at-.5m height, camera use 8mmCOMPUTAR type camera lens, and aperture is transferred to 2/3 position, and the time shutter is adjusted to 0.8ms, and yield value is adjusted to 100.
In real-time shooting process, the dynamic auto compensation situation of standard picture template light intensity and also identical with embodiment 1 to the correction situation of real-time photographic images pixel displacement.Photograph calico pattern shown in Figure 3 and exceed " disappearance " flaw image of accuracy requirement, part among Fig. 3 in the dashed region is the disappearance zone, computer screen displayed map 3 images " disappearance " flaw area value is that 20 square millimeters and gradation of image are 240, and the difference of display image average gray is 165, surpass the accuracy rating that sets, reported to the police by computer controlled automatic acousto-optic electric alarm device this moment, operating personnel handle the calico flaw, continue to take in real time the image of on-line operation embodiment calico afterwards.
Remaining explanation is identical with embodiment 1.
Embodiment 3: to the detection of calico pattern " stain " flaw:
It is identical with embodiment 1 to detect embodiment cloth, capture apparatus and operation steps.With 4 in Xi'an side's sincere 1300UM type camera, laterally evenly to arrange along calico, stuck-at-.5m height, camera use 8mmCOMPUTAR type camera lens, and aperture is transferred to 1/3 position, and the time shutter is adjusted to 1ms, and yield value is 50.
In real-time shooting process, the dynamic auto compensation situation of standard picture template light intensity and also identical with embodiment 1 to the correction situation of real-time photographic images pixel displacement.Get access to calico pattern shown in Figure 4 and exceed " stain " flaw image of accuracy requirement, dash area is the stain zone among Fig. 4, the gradation of image value is 5, and the difference of display image gray-scale value is 70, " stain " flaw area is 5 square millimeters, surpasses the accuracy rating that sets, and reported to the police by computer controlled automatic acousto-optic electric alarm device this moment, operating personnel handle the calico flaw, continue to take in real time the image of on-line operation embodiment calico afterwards.Remaining explanation is identical with embodiment 1.
The above processing step is shown in Fig. 6.

Claims (1)

1, a kind of Vision Builder for Automated Inspection of utilizing is carried out on-line detection method to the calico flaw, it is characterized in that may further comprise the steps:
(1). utilize industrial camera and control the image that described industrial camera is taken the on-line operation calico by outer triggering signal;
(2). according to the requirement of user, adjust aperture size, time shutter and the amount of gain of described industrial camera, so that the calico image of shooting clear to calico color, decorative pattern size and fineness;
(3). select complete display, flawless calico image is stored in computing machine as the standard picture template, every described industrial camera stores a width of cloth standard picture template;
(4). flaw area and gradation of image value are set at the detection parameter of calico flaw, and the accuracy rating of described detection parameter is set according to customer requirements;
(5). control described industrial camera by outer triggering signal, take the image of on-line operation calico in real time, and the image of taking is transferred to computing machine for detecting;
Meanwhile, by following step described standard picture template of (3) step is carried out the dynamic auto compensation of image intensity: the gradation of image mean value of the on-line operation calico image that above-mentioned real-time shooting is obtained compares with (3) the gradation of image mean value that goes on foot the standard picture template, variation has taken place in the gradation of image mean value that obtains as real-time shooting, then the gradation of image value with described standard picture template multiply by the luminosity compensation coefficient automatically, be stored in computing machine as new standard picture template, enter following (6) step again, contrast is used when detecting the calico image of taking in real time for (6) step, and wherein the luminosity compensation coefficient is the ratio of the average gray of the average gray of real-time photographic images and standard picture template image; Do not change as gradation of image mean value, then the standard picture template is not carried out the compensation of image intensity, directly enter following (6) step;
And meanwhile, proofread and correct the displacement of taking on-line operation calico image pixel in real time dynamically by following step:
A). the position of image pixel compares in the position of the on-line operation calico image pixel that described real-time shooting is obtained and described (3) the step reference image template, judge whether to occur the displacement of real-time photographic images pixel location, if displacement, then turn to following b) to c) step, otherwise the correction that is not shifted directly enters following (6) step;
B). will judge that the coordinate position of the real-time photographic images pixel of displacement appears in the back through a) step, by Computing, in (3) step standard picture template the coordinate position of corresponding pixel move;
C). by b) step moves after the pixel coordinates position, the pixel location in the standard picture template that obtains with above-mentioned (3) step compares again, and still whether the pixel location of judging calico displacement, if no longer displacement then enters described (6) step; If still displacement then continues above b) step, the pixel location in the standard picture template that obtains with (3) step relatively back does not have displacement, and the correction that then no longer is shifted enters following (6) step then;
(6). process the image intensity that the real-time shooting that computing machine obtained for (5) step and the image of calibrated pixel shift and (5) step obtain compensates standard picture template afterwards automatically and compares, analyzes, differentiates, occur if any the flaw outside the detection parameter accuracy rating of (4) step setting, then by the computer starting warning device, alert is handled the calico flaw, continues the operation in (5) step afterwards; As do not have above-mentioned flaw appearance, then directly continue the operation in (5) step.
CN200710135139A 2007-11-09 2007-11-09 On-line detecting method of machine vision system for printed calico flaw CN100593716C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN200710135139A CN100593716C (en) 2007-11-09 2007-11-09 On-line detecting method of machine vision system for printed calico flaw

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN200710135139A CN100593716C (en) 2007-11-09 2007-11-09 On-line detecting method of machine vision system for printed calico flaw

Publications (2)

Publication Number Publication Date
CN101158650A CN101158650A (en) 2008-04-09
CN100593716C true CN100593716C (en) 2010-03-10

Family

ID=39306810

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200710135139A CN100593716C (en) 2007-11-09 2007-11-09 On-line detecting method of machine vision system for printed calico flaw

Country Status (1)

Country Link
CN (1) CN100593716C (en)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101592672B (en) * 2008-05-30 2011-10-26 安徽宏实光机电高科有限公司 Alignment method of shooting line and object moving direction based on linear array CCD camera velocity measurement
CN101865819B (en) * 2009-04-14 2012-01-25 上海天祥质量技术服务有限公司 Test method of textile printing fastness
CN102221559B (en) * 2011-03-05 2012-08-29 河海大学常州校区 Online automatic detection method of fabric defects based on machine vision and device thereof
CN102673177B (en) * 2011-03-16 2016-01-20 杭州宏华数码科技股份有限公司 A kind of based on cloth textured textile design Method of printing
CN102288615B (en) * 2011-07-12 2015-08-26 王万年 The detection method of middle line adhesive on filter rod
CN103234980B (en) * 2012-08-20 2015-07-29 苏州大学 A kind of online fabric defects testing and alarm system based on machine vision
CN103226106B (en) * 2013-03-15 2016-02-24 江南大学 Based on the bearing dustproof cover quality monitoring method of machine vision
FR3005042B1 (en) * 2013-04-26 2016-01-01 Snecma WEAVING OR WINDING MACHINE FOR FIBROUS TEXTURE FOR ANOMALY CONTROL BY IMAGE ANALYSIS
CN103451846B (en) * 2013-09-13 2015-11-18 福州大学 A kind of grey cloth broken yarn online test method based on computer vision and system
CN104749181A (en) * 2013-12-27 2015-07-01 波司登羽绒服装有限公司 Fabric examination system for identifying defect point of fabric
CN104346807A (en) * 2014-06-05 2015-02-11 苏州大学 Detection method for machine-vision-based online fabric defect detection and alarming system
CN106276372A (en) * 2016-10-11 2017-01-04 凌云光技术集团有限责任公司 A kind of method and device positioning package packaging defect
CN107643297B (en) * 2017-08-08 2018-07-20 广州森展纺织品有限公司 A kind of method of real-time monitoring quality of textile products
CN108449525B (en) * 2018-03-26 2019-06-28 京东方科技集团股份有限公司 The acquisition methods and automatic optical checking equipment of automatic visual inspection Plays image
CN108956614B (en) * 2018-05-08 2020-12-29 太原理工大学 Mining steel wire rope dynamic flaw detection method and device based on machine vision
CN109765174A (en) * 2018-12-29 2019-05-17 莱茵技术(上海)有限公司 A kind of printing in textiles fastness to washing performance test methods
CN109916907A (en) * 2019-03-04 2019-06-21 播种者工业智能科技(苏州)有限公司 A kind of positioning control system of fabric flaw point
CN109916913A (en) * 2019-04-04 2019-06-21 哈尔滨理工大学 A kind of intelligence manufacture product identification and detection method based on machine vision
CN109975323A (en) * 2019-04-08 2019-07-05 中原工学院 Line based on automatic optics inspection knits tissue and printing design matching system
CN110570397B (en) * 2019-08-13 2020-12-04 创新奇智(重庆)科技有限公司 Method for detecting ready-made clothes printing defects based on deep learning template matching algorithm
CN110672209A (en) * 2019-10-24 2020-01-10 福建屹立智能化科技有限公司 Online detection method for warp knitting cloth color difference

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0741290A1 (en) * 1995-05-04 1996-11-06 Mahlo GmbH & Co. KG Method and apparatus for determining the distortion angles on moving fabrics or the like
CN101059451A (en) * 2007-05-15 2007-10-24 上海多路信息技术有限公司 On-line flaw real-time detection system of printing machine based on machine vision

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0741290A1 (en) * 1995-05-04 1996-11-06 Mahlo GmbH & Co. KG Method and apparatus for determining the distortion angles on moving fabrics or the like
CN101059451A (en) * 2007-05-15 2007-10-24 上海多路信息技术有限公司 On-line flaw real-time detection system of printing machine based on machine vision

Also Published As

Publication number Publication date
CN101158650A (en) 2008-04-09

Similar Documents

Publication Publication Date Title
CN101660894B (en) Device and method for multi-vision visual detection based on parallel light illumination
CN103885217B (en) A kind of method detecting liquid crystal panel cylindrical spacer defect and device
US20160343122A1 (en) Method and device for sealant coating inspection
CN104914111B (en) A kind of steel strip surface defect online intelligent recognition detecting system and its detection method
CN101858734B (en) Method for detecting PET bottleneck quality
JP4881158B2 (en) Tire inspection apparatus and method
EP1995553B1 (en) System and method for identifying a feature of a workpiece
Lahajnar et al. Machine vision system for inspecting electric plates
CN204479490U (en) A kind of laser marking On-line Product testing and analysis system
CN104441526B (en) Mould in-service monitoring protection system and method based on appearance profile coupling
CN105784716B (en) Friction plate Quality Inspection System
CN103644852B (en) Eyeglass film thickness automatic checkout system
US20110249700A1 (en) Method for detecting defect in material and system for the method
JPH0736001B2 (en) Bottle defect inspection method
CN106226157B (en) Concrete structure member crevices automatic detection device and method
CN107014822B (en) Non-woven fabric mask defect visual detection system and method
EP3176537B1 (en) System for automated in-process inspection of welds
CN103940350B (en) Coating machine online pole plate measuring thickness device and thickness measuring method of adjustment
WO2017080282A1 (en) Circuit board inspection method and apparatus
CN101320004A (en) Bamboo strip defect on-line detection method based on machine vision
CN106248686A (en) Glass surface defects based on machine vision detection device and method
CN106226325B (en) A kind of seat surface defect detecting system and its method based on machine vision
US20030151739A1 (en) Method and apparatus for measuring ripple and distortion in a transparent material
CN104574389A (en) Battery piece chromatism selection control method based on color machine vision
CN102221559A (en) Online automatic detection method of fabric defects based on machine vision and device thereof

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
C14 Grant of patent or utility model
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20100310

Termination date: 20111109

C17 Cessation of patent right