CN110108712A - Multifunctional visual sense defect detecting system - Google Patents

Multifunctional visual sense defect detecting system Download PDF

Info

Publication number
CN110108712A
CN110108712A CN201910320820.1A CN201910320820A CN110108712A CN 110108712 A CN110108712 A CN 110108712A CN 201910320820 A CN201910320820 A CN 201910320820A CN 110108712 A CN110108712 A CN 110108712A
Authority
CN
China
Prior art keywords
image
detection
light source
workpiece
detecting system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910320820.1A
Other languages
Chinese (zh)
Inventor
谭良
李清顺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongguan Zhongke Blue Sea Intelligent Vision Technology Co Ltd
Original Assignee
Dongguan Zhongke Blue Sea Intelligent Vision Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dongguan Zhongke Blue Sea Intelligent Vision Technology Co Ltd filed Critical Dongguan Zhongke Blue Sea Intelligent Vision Technology Co Ltd
Priority to CN201910320820.1A priority Critical patent/CN110108712A/en
Publication of CN110108712A publication Critical patent/CN110108712A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8854Grading and classifying of flaws
    • G01N2021/8874Taking dimensions of defect into account
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)

Abstract

The present invention relates to the technical field of vision detection of product, refer in particular to a kind of Multifunctional visual sense defect detecting system, including rack, it is set to the monitor station of rack, secondary light source above monitor station and the image collecting device above secondary light source, the rack is installed with horizontal cross bar and the lifting mould group for driving horizontal cross bar to move up and down, this programme can carry out vision-based detection to a variety of different workpiece, context of detection includes the whether complete detection of components, the scratch of workpiece surface, material is dirty, the bad detection of weld tabs, the concentricity of round piece detects, the detection of workpiece size, workpiece placement position detection etc., not only effectively reduce the equipment input cost of production firm, effectively improve the Detection accuracy and efficiency of vision system, practicability is stronger.

Description

Multifunctional visual sense defect detecting system
Technical field
The present invention relates to the technical field of vision detection of product, refer in particular to a kind of Multifunctional visual sense defect detecting system.
Background technique
In the process of product, it is often necessary to the detection of material or workpiece is carried out to product or semi-finished product, it is general to wrap Include the whether complete detection of components, the scratch of workpiece surface, material dirt, the bad detection of weld tabs, the concentricity detection of round piece, work The detection of part size, the detection of workpiece placement position etc., using artificial detection, not only efficiency is very low, that there is also omission factors is high, The at high cost and lower problem of accuracy rate, artificial detection are limited to the subjective factor of people, missing inspection during saw blade Surface testing Probability is very high;Omission factor is high, and production firm has economic loss, and cost of labor is also gradually increasing;It manually examines merely It surveys, manually carries out a large amount of repetitive operation, sense tired out can be generated, constrain the efficiency of detection, rely on artificial detection, inspection merely Surveying precision will certainly reduce, it is difficult to meet and produce demand under manufacturing environment in enormous quantities.
Summary of the invention
It is high that the technical problem to be solved in the present invention is to provide a kind of Detection accuracies, high-efficient, can be according to different workpieces Testing requirements use the Multifunctional visual sense defect detecting system without detection method, in the case where being changed without hardware detection Realize the comprehensive detection function of a variety of detection demands of various workpieces.
In order to solve the above-mentioned technical problem, the present invention adopts the following technical scheme: a kind of Multifunctional visual sense defects detection system System, including rack, the monitor station, the secondary light source above monitor station and the figure above secondary light source that are set to rack As acquisition device, the rack is installed with horizontal cross bar and the lifting mould group for driving horizontal cross bar to move up and down, vision inspection Examining system includes the following steps:
Standard testing workpiece is placed in monitor station 2 by step A;
Step B, image collecting device 4 carry out Image Acquisition to the standard testing workpiece on monitor station 2 and obtain template image, and will Template image is sent to image processor;
Step C, image processor carry out binary conversion treatment to collected template image;
Step D, image processor 7 carry out edge detection algorithm to the template image after binary conversion treatment and obtain standard testing workpiece Shape information.
Step E, image processor establish the Template Information of standard testing workpiece using outline algorithm, remove standard survey Trial work part;
Step F, is put into workpiece for measurement;Image collecting device 4 carries out Image Acquisition to the workpiece for measurement on monitor station 2 and is detected Image, and will test image and be sent to image processor;
Step G, image processor 7 carry out binary conversion treatment to collected detection image;
Step H, image processor 7 carry out the shape that edge detection algorithm obtains workpiece for measurement to the detection image after binary conversion treatment Shape information.
Shape information obtained in step F and Template Information are carried out shape matching algorithm by step I, image processor 7, if Regular inspection measuring angle is 0 ~ 360 °;
Step J, outline: if outline success, determines OK, otherwise determine NG;
Step F to step J is repeated when detecting again.
Preferably, in the step G, detection image is carried out to carry out image preprocessing before binary conversion treatment to eliminate Unrelated information in image enhances detectability for information about and simplifies image data.
It preferably, further include spot-analysis algorithm and spacing detection step in the step I, after shape matching algorithm Suddenly.
Preferably, the spot-analysis algorithm is analyzed the connected domain of same pixel in image, specific steps packet It includes: now will test image and carry out binaryzation, segmentation obtains prospect background, carries out connected domain (Blob) detection, then to acquire The process of Blob block.
Preferably, in the step G, Low threshold being adjusted to 46 in binary conversion treatment, high threshold 255.
Preferably, in the step I, edge pattern is quick, feature quantity 50%, profile length 20;And in profile When matching, search parameter adjustment are as follows: number of searches 1, minimum score 70, ratio 100, overlap distance 0, search speed It is set to LV5 with positioning accuracy, matching polarity is normal.
Preferably, in the step E, edge pattern is accurate, feature quantity 10%, profile length 20, the step In J: number of searches 1, minimum score 80, ratio are set as 100, overlap distance 0, search speed and registration LV5, It is normal with polarity.
Preferably, the secondary light source 3 is circular ring shape light source, the central axis of described image acquisition device 4 and secondary light source Coaxial arrangement.
Preferably, the secondary light source is rectangular shaped light source, dome-geometry light source or square frame-shaped light source.
The beneficial effects of the present invention are: the present invention provides a kind of Multifunctional visual sense defect detecting systems, and this programme can With to a variety of different workpiece carry out vision-based detection, context of detection include components it is whether complete detection, workpiece surface scratch, Expect dirt, the bad detection of weld tabs, the concentricity detection of round piece, the detection of workpiece size, the detection of workpiece placement position etc., it is raw Manufacturer is produced to no longer need to individually designed for different workpiece and manufacture the dedicated visual detection equipment for specific workpiece, it is only necessary to The various of finished product after up to 20 kinds of components, semi-finished product can be realized in the Multifunctional visual sense defect detecting system of one playscript with stage directions invention Defects detection not only effectively reduces the equipment input cost of production firm, effectively improve vision system Detection accuracy and Efficiency, practicability are stronger.
Detailed description of the invention
Fig. 1 is the device structure schematic diagram of strip-shaped work vision detection system of the present invention.
Structural schematic diagram when Fig. 2 is the equipment hidden parts rack of strip-shaped work vision detection system of the present invention.
Fig. 3 is the detecting step functional block diagram of strip-shaped work vision detection system of the present invention.
Specific embodiment
For the ease of the understanding of those skilled in the art, below with reference to embodiment, the present invention is further illustrated, real The content that the mode of applying refers to not is limitation of the invention.
As shown in Figure 1 to Figure 3, a kind of Multifunctional visual sense defect detecting system including rack, is set to the detection of rack Platform, the secondary light source above monitor station and the image collecting device above secondary light source, the rack are installed with water Flat cross bar and lifting mould group for driving horizontal cross bar to move up and down, vision detection system include the following steps:
Standard testing workpiece is placed in monitor station 2 by step A;
Step B, image collecting device 4 carry out Image Acquisition to the standard testing workpiece on monitor station 2 and obtain template image, and will Template image is sent to image processor;
Step C, image processor carry out binary conversion treatment to collected template image;
Step D, image processor 7 carry out edge detection algorithm to the template image after binary conversion treatment and obtain standard testing workpiece Shape information.
Step E, image processor establish the Template Information of standard testing workpiece using outline algorithm, remove standard survey Trial work part;
Step F, is put into workpiece for measurement;Image collecting device 4 carries out Image Acquisition to the workpiece for measurement on monitor station 2 and is detected Image, and will test image and be sent to image processor;
Step G, image processor 7 carry out binary conversion treatment to collected detection image;
Step H, image processor 7 carry out the shape that edge detection algorithm obtains workpiece for measurement to the detection image after binary conversion treatment Shape information.
Shape information obtained in step F and Template Information are carried out shape matching algorithm by step I, image processor 7, if Regular inspection measuring angle is 0 ~ 360 °;
Step J, outline: if outline success, determines OK, otherwise determine NG;
Step F to step J is repeated when detecting again.
Preferably, in the step G, detection image is carried out to carry out image preprocessing before binary conversion treatment to eliminate Unrelated information in image enhances detectability for information about and simplifies image data.Firstly, carrying out two to obtained image Value processing, the image information feature for filtering out and being not belonging to solder horn itself in image is reached with this.Pass through binaryzation obtaining After the image of processing, carry out contours extract is carried out to different solder horns, obtains feature object image outline, meanwhile, it is taken turns with these Exterior feature establishes matching primary template respectively.Then template matching and matching are carried out to late detection image with primary template, and The image that will match to passes through the coordinate system established out and provides its opposite position coordinates.To reach and identify different soldering irons Head and detect its whether corresponding position testing goal.
Image preprocessing is to come out each character image sorting to give identification module identification, this process is known as scheming As pretreatment.In image analysis, the processing carried out before feature extraction, segmentation and matching is carried out to input picture.Image is pre- The main purpose of processing is to eliminate unrelated information in image, restores useful real information, enhances for information about detectable Property and to the maximum extent simplify data, to improve the reliability of feature extraction, image segmentation, matching and identification.
Binaryzation is exactly to set 0 or 255 for the gray value of the pixel on image, that is, whole image is showed The process of apparent black and white effect.It is 0 or 255 that the binary conversion treatment of image, which is exactly by the gray value of the point on image, that is, Whole image is showed into apparent black and white effect.The gray level image of 256 brightness degrees is chosen by threshold value appropriate And it obtains and still can reflect the whole binary image with local feature of image.In Digital Image Processing, bianry image is accounted for There is very important status, especially in practical image procossing, the system constituted with binary Images Processing realization is very More, the processing and analysis of Yao Jinhang bianry image first have to a Binary Sketch of Grey Scale Image, obtain binary image, so Being conducive to when being further processed to image, the set property of image is only related with the position of point that pixel value is 0 or 255, The multilevel values for not further relating to pixel make processing become simple, and data processing and decrement it is small.In order to obtain ideal two It is worth image, the region that the general boundary definition using closing, connection does not overlap.All gray scales are greater than or equal to the pixel quilt of threshold value It is judged to belonging to certain objects, gray value is 255 expressions, and otherwise these pixels are excluded other than object area, gray scale Value is 0, indicates the object area of background or exception.
Outline algorithm, the identification matching based on profile, needs image to split channel, finds edge, be converted to wheel Wide (polygonal segments, characteristic summary etc.), then carries out outline (image and images match, image and template matching).Journey Sequence person selects to be suitble to image abstraction method and matching process according to different situations.
The matching of profile mainly solves size, and position rotates angle, the matching problem between precision different images.Method Including Contour moment, pairwise geometric histograms, convex closure and convex defect, ratings match etc..
It preferably, further include spot-analysis algorithm and spacing detection step in the step I, after shape matching algorithm Suddenly.
Preferably, the spot-analysis algorithm is analyzed the connected domain of same pixel in image, specific steps packet It includes: now will test image and carry out binaryzation, segmentation obtains prospect background, carries out connected domain (Blob) detection, then to acquire The process of Blob block.
By taking the Defect Detection of plastic bottle as an example:
Main use algorithm in the present embodiment has: image preprocessing-Binarization methods, outline algorithm and spot point Analyse algorithm.
Firstly, carrying out binary conversion treatment to obtained image, is reached with this and filter out periphery unwanted picture letter Breath.It is obtaining after the image of binary conversion treatment, contours extract is carried out to it, obtaining feature object image outline, meanwhile, with This profile establishes matching primary template.Then template matching and matching are carried out to late detection image with primary template, and The image that will match to passes through the coordinate system established out and provides its opposite position coordinates, and carries out position benefit to subsequent algorithm Region just to limit algorithm detection.Finally, being calculated to limit using spot-analysis algorithm the template position coordinate by obtaining Method detection zone avoids breakfast or characteristics of image interference detection results of the outer image of body profile on image.Finally, spot-analysis It obtains and detects and be not belonging to itself or feature situation against regulation on cylinder, to realize testing goal.
Outline: the identification matching based on profile needs image to split channel, finds edge, it is (more to be converted to profile Side shape is approached, and characteristic is summarized etc.), then carry out outline (image and images match, image and template matching).Programmer's root According to different situations, select to be suitble to image abstraction method and matching process.
The matching of profile mainly solves size, and position rotates angle, the matching problem between precision different images.Method Including Contour moment, pairwise geometric histograms, convex closure and convex defect, ratings match etc..
Image preprocessing: being to come out each character image sorting to give identification module identification, this process is known as scheming As pretreatment.In image analysis, the processing carried out before feature extraction, segmentation and matching is carried out to input picture.Image is pre- The main purpose of processing is to eliminate unrelated information in image, restores useful real information, enhances for information about detectable Property and to the maximum extent simplify data, to improve the reliability of feature extraction, image segmentation, matching and identification.
Binaryzation is exactly to set 0 or 255 for the gray value of the pixel on image, that is, whole image is showed The process of apparent black and white effect.It is 0 or 255 that the binary conversion treatment of image, which is exactly by the gray value of the point on image, that is, Whole image is showed into apparent black and white effect.The gray level image of 256 brightness degrees is chosen by threshold value appropriate And it obtains and still can reflect the whole binary image with local feature of image.In Digital Image Processing, bianry image is accounted for There is very important status, especially in practical image procossing, the system constituted with binary Images Processing realization is very More, the processing and analysis of Yao Jinhang bianry image first have to a Binary Sketch of Grey Scale Image, obtain binary image, so Being conducive to when being further processed to image, the set property of image is only related with the position of point that pixel value is 0 or 255, The multilevel values for not further relating to pixel make processing become simple, and data processing and decrement it is small.In order to obtain ideal two It is worth image, the region that the general boundary definition using closing, connection does not overlap.All gray scales are greater than or equal to the pixel quilt of threshold value It is judged to belonging to certain objects, gray value is 255 expressions, and otherwise these pixels are excluded other than object area, gray scale Value is 0, indicates the object area of background or exception.
Spot-analysis algorithm: refer to that the connected domain to same pixel in image is analyzed.Its process be exactly by image into Row binaryzation, segmentation obtain prospect background, then carry out connected domain (Blob) detection, thus the process to Blob block.Connection Domain, referring in image has one piece of connected region composed by Similar color, textural characteristics.
Preferably, in the step G, Low threshold being adjusted to 46 in binary conversion treatment, high threshold 255.Preferably, In the step I, edge pattern is quick, feature quantity 50%, profile length 20;And in outline, search parameter Adjustment are as follows: number of searches 1, minimum score 70, ratio 100, overlap distance 0, search speed and positioning accuracy are all set It is set to LV5, matching polarity is normal.Preferably, in the step E, edge pattern is accurate, feature quantity 10%, profile length Be 20, in the step J: number of searches 1, minimum score 80, ratio are set as 100, overlap distance 0, search speed with Registration LV5, matching polarity are normal.
In the present solution, include that overall profile identification and local configuration identify to the shape matching algorithm of workpiece, it is especially suitable Shape matching algorithm when containing multiple products in a packing box.By taking the detection of solder horn complete product as an example.
Overall profile identification: in whole outline identification software algorithm, it is special to be directed to the multiple and different solder horn of workpiece Sign extracts identification, and establishes matching template respectively, outline is carried out convenient for image of the later period to acquisition, therefore, it is determined that being It is no there are misplaced, leakage is put.When Image Acquisition, carry out adopting figure under 1.4 apertures, the time for exposure of 30 μ s, and carry out image soft Part processing.Binary conversion treatment is carried out to image first, Low threshold is adjusted to 46, high threshold 255.Under this group of parameter, figure As that will be presented as that background is pure white, workpiece is completely black, to obtain the fine definition of image.Each workpiece is carried out with image after processing Template matching, when establishing template, in contour detecting parameter, quickly, feature quantity selects 50%, profile length for edge pattern selection Selection 20, the contour feature of different solder horns can be obtained with this parameter.And in outline, search parameter adjustment are as follows: search Quantity is 1, minimum score 70, ratio 100, overlap distance 0, and search speed and positioning accuracy are set to LV5, is matched Polarity is normal.Thus parameter can stable matching recognize same light source irradiation under soldering iron contour feature, therefore, it is determined that whether depositing It is put in leakage, it is misplaced.
Local configuration identification: due to wherein there is 3 templates that can not identify from front, need to detect workpiece type from side, therefore Increase the local detail of 3 workpiece of side station inspection.In Image Acquisition, under 4.0 apertures, the time for exposure of 400 μ s into Row adopts figure, and carries out software processing.After acquiring the image, outline is carried out to 3 workpiece respectively, is obtaining template contours inspection Survey numerical parameter setting are as follows: edge pattern is accurate, feature quantity 10%, profile length 20, thus can get the feature wheel of template It is wide.And the search parameter in later period outline are as follows: number of searches 1, minimum score 80, ratio are set as 100, overlapping Distance 0, search speed and registration LV5, matching polarity are normal.Under same illumination condition, which can guarantee workpiece Stablize identification.
Preferably, the secondary light source 3 is circular ring shape light source, the central axis of described image acquisition device 3 and secondary light source 3 Coaxial arrangement, effectively improve image collecting device 4 institute collected workpiece image integrality, reduction distortion rate.Certainly, described Secondary light source 3 can also be rectangular shaped light source, dome-geometry light source or square frame-shaped light source, according to the shape of detected workpiece and detection side Formula angle reasonably selects, to obtain the workpiece image information of optimum detection.
In the description of the present invention, it should be noted that " laterally (X) ", " vertical if any term " center " for the noun of locality To (Y) ", " vertical (Z) " " length ", " width ", " thickness ", "upper", "lower", "front", "rear", "left", "right", "vertical", " water It is flat ", "top", "bottom", "inner", "outside", " clockwise ", the indicating positions such as " counterclockwise " and positional relationship be based on the figure Orientation or positional relationship, be merely for convenience of narration the present invention and simplify description, rather than the device of indication or suggestion meaning or Element must have a particular orientation, be constructed and be operated with particular orientation, should not be understood as limiting specific protection model of the invention It encloses.
In addition, being used for description purposes only if any term " first ", " second ", it is not understood to indicate or imply relatively heavy The property wanted or the quantity for implicitly indicating technical characteristic." first " is defined as a result, " second " feature can be expressed or implicit include One or more this feature, in the present description, " several " are meant that two or more, unless otherwise clearly having The restriction of body.
In the present invention, except as otherwise clear stipulaties and restriction, should make if any term " assembling ", " connected ", " connection " term Broad sense goes to understand, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It is also possible to mechanical connect It connects;It can be directly connected, be also possible to be connected by intermediary, can be and be connected inside two elements.For ability For the those of ordinary skill of domain, the concrete meaning of above-mentioned term in the present invention can be understood as the case may be.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.

Claims (9)

1. Multifunctional visual sense defect detecting system, including rack (1), image processor (7), the monitor station for being set to rack (1) (2), the image collecting device (4) for being located at the secondary light source (3) above monitor station (2) and being located above secondary light source (3), it is special Sign is: the rack (1) is installed with horizontal cross bar (5) and the lifting mould group for driving horizontal cross bar (5) to move up and down (6), vision detection system includes the following steps:
Standard testing workpiece is placed in monitor station (2) by step A;
Step B, image collecting device (4) carry out Image Acquisition to the standard testing workpiece on monitor station (2) and obtain template image, And template image is sent to image processor;
Step C, image processor carry out binary conversion treatment to collected template image;
Step D, image processor (7) carry out edge detection algorithm to the template image after binary conversion treatment and obtain standard testing work The shape information of part;
Step E, image processor establish the Template Information of standard testing workpiece using outline algorithm, remove standard testing work Part;
Step F, is put into workpiece for measurement;Image collecting device (4) carries out Image Acquisition to the workpiece for measurement on monitor station (2) and obtains Detection image, and will test image and be sent to image processor;
Step G, image processor (7) carry out binary conversion treatment to collected detection image;
Step H, image processor (7) carry out edge detection algorithm to the detection image after binary conversion treatment and obtain workpiece for measurement Shape information;
Shape information obtained in step F and Template Information are carried out shape matching algorithm, setting by step I, image processor (7) Detection angles are 0 ~ 360 °;
Step J, outline: if outline success, determines OK, otherwise determine NG;
Step F to step J is repeated when detecting again.
2. Multifunctional visual sense defect detecting system according to claim 1, it is characterised in that: in the step G, to inspection Altimetric image carry out binary conversion treatment before carry out image preprocessing to eliminate information unrelated in image, enhance for information about can Detection property and simplified image data.
3. Multifunctional visual sense defect detecting system according to claim 1, it is characterised in that: in the step I, shape It further include spot-analysis algorithm and spacing detection step after matching algorithm.
4. Multifunctional visual sense defect detecting system according to claim 3, it is characterised in that: the spot-analysis algorithm is The connected domain of same pixel in image is analyzed, specific steps include: that now will test image to carry out binaryzation, and segmentation obtains Then prospect background carries out connected domain (Blob) detection, to acquire the process of Blob block.
5. Multifunctional visual sense defect detecting system according to claim 1, it is characterised in that: in the step G, binaryzation Adjusting Low threshold to 46 in processing, high threshold 255.
6. Multifunctional visual sense defect detecting system according to claim 5, it is characterised in that: in the step I, edge mould Formula is quick, feature quantity 50%, profile length 20;And in outline, search parameter adjustment are as follows: number of searches is 1, minimum score 70, ratio 100, overlap distance 0, search speed and positioning accuracy are set to LV5, are matching polarity just Often.
7. Multifunctional visual sense defect detecting system according to claim 5, it is characterised in that: in the step E, edge mould Formula is accurate, feature quantity 10%, profile length 20, in the step J: number of searches 1, minimum score 80, ratio It is set as 100, overlap distance 0, search speed and registration LV5, matching polarity are normal.
8. Multifunctional visual sense defect detecting system according to claim 1, it is characterised in that: the secondary light source (3) is Circular ring shape light source, the central axis setting of described image acquisition device (4) and secondary light source (3).
9. Multifunctional visual sense defect detecting system according to claim 1, it is characterised in that: the secondary light source (3) is Rectangular shaped light source, dome-geometry light source or square frame-shaped light source.
CN201910320820.1A 2019-04-20 2019-04-20 Multifunctional visual sense defect detecting system Pending CN110108712A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910320820.1A CN110108712A (en) 2019-04-20 2019-04-20 Multifunctional visual sense defect detecting system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910320820.1A CN110108712A (en) 2019-04-20 2019-04-20 Multifunctional visual sense defect detecting system

Publications (1)

Publication Number Publication Date
CN110108712A true CN110108712A (en) 2019-08-09

Family

ID=67485948

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910320820.1A Pending CN110108712A (en) 2019-04-20 2019-04-20 Multifunctional visual sense defect detecting system

Country Status (1)

Country Link
CN (1) CN110108712A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110706277A (en) * 2019-09-12 2020-01-17 创新奇智(合肥)科技有限公司 Method for detecting object rotation angle based on chain code histogram
CN111272766A (en) * 2020-02-20 2020-06-12 上海普密德自动化科技有限公司 Surface defect detection system based on vision technology and detection method thereof
US20210172884A1 (en) * 2019-12-02 2021-06-10 Juki Corporation Inspection device and inspection method
CN113379726A (en) * 2021-06-30 2021-09-10 深圳中科飞测科技股份有限公司 Line detection method, device, equipment and computer readable storage medium
CN113959951A (en) * 2021-11-21 2022-01-21 天津宏华焊研机器人科技有限公司 Machine vision device for online detection of workpiece assembly and detection method
CN114184616A (en) * 2021-11-25 2022-03-15 安徽布拉特智能科技有限公司 Detection device for blue film for lithium battery and control method thereof
CN114354631A (en) * 2022-01-12 2022-04-15 绍兴职业技术学院 Valve blank surface defect detection method based on vision
CN115753791A (en) * 2022-11-10 2023-03-07 哈尔滨耐是智能科技有限公司 Defect detection method, device and system based on machine vision

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105301003A (en) * 2015-11-05 2016-02-03 天津大学 Method for detecting bottle cap surface production date based on machine vision
CN205049488U (en) * 2015-10-14 2016-02-24 中国计量学院 Many light sources of brake block appearance imperfections combination formula on -line measuring device
US20160300338A1 (en) * 2015-04-13 2016-10-13 Anchor Semiconductor Inc. Pattern weakness and strength detection and tracking during a semiconductor device fabrication process
CN107525808A (en) * 2017-07-27 2017-12-29 佛山市南海区广工大数控装备协同创新研究院 Blister medication classification and the online visible detection method of defect on a kind of production line
CN107561087A (en) * 2017-08-31 2018-01-09 广东工业大学 A kind of mouse logo positioning and defect inspection method based on machine vision
CN107886496A (en) * 2017-09-30 2018-04-06 北京得华机器人技术研究院有限公司 A kind of quality determining method of the auto-parts based on form fit

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160300338A1 (en) * 2015-04-13 2016-10-13 Anchor Semiconductor Inc. Pattern weakness and strength detection and tracking during a semiconductor device fabrication process
CN205049488U (en) * 2015-10-14 2016-02-24 中国计量学院 Many light sources of brake block appearance imperfections combination formula on -line measuring device
CN105301003A (en) * 2015-11-05 2016-02-03 天津大学 Method for detecting bottle cap surface production date based on machine vision
CN107525808A (en) * 2017-07-27 2017-12-29 佛山市南海区广工大数控装备协同创新研究院 Blister medication classification and the online visible detection method of defect on a kind of production line
CN107561087A (en) * 2017-08-31 2018-01-09 广东工业大学 A kind of mouse logo positioning and defect inspection method based on machine vision
CN107886496A (en) * 2017-09-30 2018-04-06 北京得华机器人技术研究院有限公司 A kind of quality determining method of the auto-parts based on form fit

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
崔吉 等: "《工业视觉实用教程》", 31 October 2018, 上海交通大学出版社 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110706277A (en) * 2019-09-12 2020-01-17 创新奇智(合肥)科技有限公司 Method for detecting object rotation angle based on chain code histogram
US20210172884A1 (en) * 2019-12-02 2021-06-10 Juki Corporation Inspection device and inspection method
US11971367B2 (en) * 2019-12-02 2024-04-30 Juki Corporation Inspection device and inspection method
CN111272766A (en) * 2020-02-20 2020-06-12 上海普密德自动化科技有限公司 Surface defect detection system based on vision technology and detection method thereof
CN113379726A (en) * 2021-06-30 2021-09-10 深圳中科飞测科技股份有限公司 Line detection method, device, equipment and computer readable storage medium
CN113959951A (en) * 2021-11-21 2022-01-21 天津宏华焊研机器人科技有限公司 Machine vision device for online detection of workpiece assembly and detection method
CN114184616A (en) * 2021-11-25 2022-03-15 安徽布拉特智能科技有限公司 Detection device for blue film for lithium battery and control method thereof
CN114354631A (en) * 2022-01-12 2022-04-15 绍兴职业技术学院 Valve blank surface defect detection method based on vision
CN115753791A (en) * 2022-11-10 2023-03-07 哈尔滨耐是智能科技有限公司 Defect detection method, device and system based on machine vision
CN115753791B (en) * 2022-11-10 2024-03-01 哈尔滨耐是智能科技有限公司 Defect detection method, device and system based on machine vision

Similar Documents

Publication Publication Date Title
CN110108712A (en) Multifunctional visual sense defect detecting system
WO2020248439A1 (en) Crown cap surface defect online inspection method employing image processing
CN108520274B (en) High-reflectivity surface defect detection method based on image processing and neural network classification
CN110163853B (en) Edge defect detection method
CN109724990A (en) The quick positioning and detection method in coding region in a kind of packing box label
CN109900711A (en) Workpiece, defect detection method based on machine vision
CN109490316A (en) A kind of surface defects detection algorithm based on machine vision
CN104680519B (en) Seven-piece puzzle recognition methods based on profile and color
CN108596880A (en) Weld defect feature extraction based on image procossing and welding quality analysis method
CN110108711A (en) The vision detection system of annulus side wall defect
CN105913093A (en) Template matching method for character recognizing and processing
CN110807355A (en) Pointer instrument detection and reading identification method based on mobile robot
CN109993154B (en) Intelligent identification method for single-pointer sulfur hexafluoride instrument of transformer substation
CN110473184A (en) A kind of pcb board defect inspection method
CN106780526A (en) A kind of ferrite wafer alligatoring recognition methods
CN105954301A (en) Bottleneck quality detection method based on machine vision
CN110096980A (en) Character machining identifying system
CN107891012B (en) Pearl size and circularity sorting device based on equivalent algorithm
CN110108724A (en) Strip-shaped work vision detection system
CN109358067A (en) Motor ring varistor defect detecting system based on computer vision and method
CN110189375A (en) A kind of images steganalysis method based on monocular vision measurement
CN112304957A (en) Machine vision-based intelligent detection method and system for appearance defects
CN109781737A (en) A kind of detection method and its detection system of hose surface defect
CN111626995B (en) Intelligent insert detection method and device for workpiece
CN111060518A (en) Stamping part defect identification method based on instance segmentation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190809

RJ01 Rejection of invention patent application after publication