CN108993929A - A kind of dual-machine linkage industrial machine vision automatic checkout system - Google Patents
A kind of dual-machine linkage industrial machine vision automatic checkout system Download PDFInfo
- Publication number
- CN108993929A CN108993929A CN201810863357.0A CN201810863357A CN108993929A CN 108993929 A CN108993929 A CN 108993929A CN 201810863357 A CN201810863357 A CN 201810863357A CN 108993929 A CN108993929 A CN 108993929A
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- machine
- measured
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D11/00—Component parts of measuring arrangements not specially adapted for a specific variable
Abstract
The invention discloses a kind of dual-machine linkage industrial machine vision automatic checkout systems, include image capture module, application software module, image analysis module and storage enquiry module.Image capture module is responsible for acquiring the image of testee;Image analysis module is responsible for executing the image received specific analysis identification mission by the calling of application software module;Application software module provides friendly interaction page, the interface between definition and storage Query Subsystem for user;Storage enquiry module is responsible for the data base administration and user management of stored product testing information.Image capture module includes positioning shooting machine and detection video camera, and positioning shooting machine is used to determine the region to be measured of the complicated product to be measured of large volume;Video camera is detected to the image in all regions to be measured acquisition testing one by one, the dual-machine linkage both realized.The present invention can greatly improve detection efficiency, and speed is fast, and producing line speed can be cooperated to carry out, do not delay the production time.
Description
Technical field
The invention belongs to Industrial Robot Technology fields, are related to a kind of two-shipper with machine positioning and a machine examination brake
Link industrial machine vision automatic checkout system.
Background technique
In modern industry automated production, it is related to various inspections, production monitoring and Parts Recognition application, example
Such as the dimensional gaughing of spare and accessory parts batch machining, the integrity checking of daily chemical products automatic assembling, the character recognition in product packaging
Deng.These examine work mostly by the way of artificial detection at present, but artificial detection has and is much difficult to gram in actual production
The difficulty of clothes is mainly shown as that accuracy is low, since human eye has the limitation of physical condition, even if human eye relies on magnifying glass or micro-
Mirror carrys out testing product, is not still able to satisfy requirement of many products to accuracy;Stability is poor, due in automated production to
It is huge to examine product quantity, the artificial testing product that repeats can be because the reasons such as fatigue generate subtle difference, and the result of detection can not
It leans on;Working efficiency is low, and manual detection efficiency is low, especially on detection production line when the product of high-speed motion, within the unit time
The quantity of detection is very limited;Environmental requirement is high, in various industries, the more generally existing danger for being not suitable for manual work
Dangerous working environment seriously threatens the personal safety of testing staff.Sum up, manual detection mode there are the problem of it is as follows:
1. the extremely low product testing success rate of manual detection efficiency can only achieve 70%, the product zero for being unable to ensure sending is lacked
It falls into.
2. artificial detection speed is slow, it can not can cooperate high-speed production lines, greatly delay the production time.
3. artificial detection not can avoid touching product, there is the possibility for damaging product to be measured.
4. artificial detection is costly, a large amount of cost of labor is consumed, brings biggish financial burden for enterprise.
5. can not work in some hazardous environments, such as radiate, toxic gas, high temperature, high pressure, fluid etc. are not suitable for manually
The hazardous environment of operation.
With the development of automation industry, NI Vision Builder for Automated Inspection can be widely used in assembly positioning, product quality inspection
Survey, product identification, product size measurement etc..Therefore NI Vision Builder for Automated Inspection can significantly improve the automation journey of production line
Degree, especially it is contemplated that being difficult to the occasion met the requirements in manual detection mode substitutes artificial inspection with NI Vision Builder for Automated Inspection
It surveys, in high-volume industrial processes, the degree of automation of production efficiency and production can also be greatly improved.
Summary of the invention
The present invention manual detection mode there are aiming at the problem that propose that a kind of dual-machine linkage industrial machine vision detects automatically
System can be widely used in manual detection mode and be difficult to the assembly positioning met the requirements, product quality detection, product knowledge
Not, the application fields such as product size measurement, can significantly improve the degree of automation of production line.
To achieve the above object, the technical solution adopted by the present invention is the automatic detection system of dual-machine linkage industrial machine vision
System, system include four modules, are image capture module, application software module, image analysis module and storage inquiry mould respectively
Block.Image capture module is responsible for acquiring the image of testee, which includes positioning shooting machine and detection video camera, and positioning is taken the photograph
Camera is used to determine the region to be measured of the complicated product to be measured of large volume, by all areas to be measured of product to be measured from the image of acquisition
Domain positioning, and image is uploaded to the detection and analysis server in image analysis module, which passes related position information
Pass detection video camera, image acquisition testing and is uploaded to detection point one by one to the image in all regions to be measured by detection video camera
Server is analysed, realizes positioning shooting machine and detection video camera dual-machine linkage;Image analysis module by application software module calling,
It is responsible for executing the image received specific analysis identification mission;Application software module provides friendly interaction page for user,
Interface between definition and storage Query Subsystem;Storage enquiry module is responsible for the data depositary management of stored product testing information
Reason and user management.
Further, above-mentioned image capture module includes positioning shooting machine and detection video camera, and positioning shooting machine is for determining
The region to be measured of the complicated product to be measured of large volume, by all zone locations to be measured of product to be measured from the image of acquisition, and will
Image is uploaded to the detection and analysis server in image analysis module, which passes to detection camera shooting for related position information
Machine, image acquisition testing and is uploaded to detection and analysis server one by one to the image in all regions to be measured by detection video camera, real
Existing positioning shooting machine and detection video camera dual-machine linkage.
Detection video camera can pre-process acquired image before being uploaded to detection and analysis server.
Preferably, above-mentioned pretreatment includes automatic exposure, automatic white balance, automatic noise reduction, automatic gain function.
Detection video camera uploading detection Analysis server after pretreatment to acquired image, passes through point of server
Analysis and comparison, detect the quality results of current measured object, and store the result into storage server.
Run a specific Machine Vision Detection in above-mentioned detection and analysis server and analyze software, and provide the software and
The data-interface of other equipment in system.
The picture number that software detection Analysis server receives the acquisition of positioning shooting machine is analyzed by the Machine Vision Detection
According to, all regional locations to be measured of current product to be measured are determined by analysis, and location information is passed into detection video camera, it is logical
The image information of analysis detection video camera return is crossed, and it is compared with standard qualified products template data, is judged automatically
Whether current production is qualified, and substandard product is rejected if unqualified.
If it is determined that the unqualified triggering times for then passing through optocoupler trigger of current production, calculate substandard product and are producing
The position of line, to issue action command when substandard product reaches and rejects plug-in strip to plug-in strip is rejected, reject unqualified production
Product.
Compared with prior art, system of the invention has the advantage that relative to artificial detection
1. detection efficiency can be greatly improved, product testing success rate is close to 100%, it is ensured that the product defects rate pole of sending
It is low.
2. speed is fast, producing line speed can be cooperated to carry out, do not delay the production time.
3. non-contact, non break down test does not have any damage to product.
4. low cost, automatic detection saves a large amount of cost of labor, brings considerable interests for enterprise.
5. the operation is stable, can long-term stable work.
6. each product passes through quickly and accurately dimensional measurement, guarantee that each product conforms to quality requirements.
7. can work in some hazardous environments for being not suitable for manual work, such as radiate, toxic gas, high temperature, high pressure, stream
In the hazardous environments such as body.
Detailed description of the invention
Fig. 1 is the overall system view of dual-machine linkage industrial machine vision automatic checkout system of the present invention.
Fig. 2 is positioning shooting machine visual angle schematic diagram.
Fig. 3 is detection camera angles schematic diagram.
Fig. 4 is dual-machine linkage data interaction schematic diagram.
Fig. 5 is the work flow diagram that dual-machine linkage industrial machine vision detects automatically.
Fig. 6 is the subsystem schematic diagram that system presses function division.
Specific embodiment
Explanation in detail is done further to the present invention now in conjunction with attached drawing.
As shown in Figure 1, the chief component of dual-machine linkage industrial machine vision automatic checkout system includes:
1. positioning shooting machine:, will be to from the image of acquisition for determining the region to be measured of the complicated product to be measured of large volume
All zone locations to be measured of product are surveyed, and image is uploaded to detection and analysis server, server passes related position information
Pass detection video camera, image acquisition testing and is uploaded to detection point one by one to the image in all regions to be measured by detection video camera
Server is analysed, realizes positioning shooting machine and detection video camera dual-machine linkage, positioning shooting machine visual angle is as shown in Figure 2.
2. detecting video camera: dual-machine linkage is formed with positioning shooting machine, for acquiring all areas to be measured of product to be measured one by one
The image information in domain, acquired image is pre- by technologies such as automatic exposure, automatic white balance, automatic noise reduction, automatic gains
Processing, and it is uploaded to detection and analysis server, detection camera angles are as shown in Figure 3.
3. testing and analyzing server: it tests and analyzes the specific Machine Vision Detection of operation one in server and analyzes software,
And provide the data-interface of other equipment in the software and system.Test and analyze the image that server receives the acquisition of positioning shooting machine
Data determine all regional locations to be measured of current product to be measured by the analysis of software, and location information is passed to detection
Video camera.The image information returned by analysis detection video camera, and it is compared with standard qualified products template data,
Whether qualified judge automatically current production.If unqualified, pass through the triggering times of optocoupler trigger 2#, calculate unqualified production
Product are in the position of production line, when substandard product, which reaches, rejects plug-in strip, issue action command to plug-in strip is rejected, reject unqualified
Product.It tests and analyzes server and positioning shooting machine, detection camera data interactive process is as shown in Figure 4.Test and analyze software
It is the control core for testing and analyzing server, major function has:
A. automated graphics enhance: image enhancement is the necessary preprocessing process of image, it is therefore an objective to acquire intelligent camera
Image certain features enhancing, in order to subsequent image procossing.Generally include: gray value transformation sharpens, noise reduction.
B. automated graphics geometric transformation: since there are errors for practical operation, it not can guarantee target object and be always at equally
Position and direction, the position and direction information of target object, the i.e. pose of target object, then carry out phase in first detection image
The geometric transformation answered.Transformation is divided into four kinds, respectively translates, scales, rotation, inclination.
C. image segmentation: being split the image of intelligent camera acquisition, obtains target object (or comprising target object
Region) process.
D. connected region is extracted: the region obtained by image segmentation is the son of one or more images in the algorithm
Collection, if to allow subsequent image recognition algorithm to recognize target object one by one, it is necessary to obtain these segmentations
The region that is connected to one by one of subset label city, each connected region means that a target.
E. feature extraction: software one or more obtained in the region or profile has the feature of apparent distinction
Amount, identifies target.
F. stencil matching: it will be compared, be judged automatically by the template of the target image and standard qualified products that handle
Whether current product to be measured is qualified.
G. location information is transmitted: being received the image information that positioning shooting machine uploads, is determined being needed for current product to be measured
Regional location is surveyed, location information is passed into detection video camera.
H. remote control command is sent: when optocoupler trigger 2# triggering times are consistent with substandard product position, to rejecting lock
Knife issues action command, rejects substandard product.
4. light compensating lamp: so that target and image background in image is obtained optimal separation by light filling appropriate, can reduce
The difficulty of subsequent image processing and recognizer, while improving the precision and stability of system.
5. optocoupler trigger:
(1) optocoupler trigger 1# is used to detection trigger video camera, starts to acquire current product image to be measured;
(2) optocoupler trigger 2# sends product counting to server is tested and analyzed, by the way that into the product quantity crossed, judgement is not
Whether qualified products reach rejecting plug-in strip;
6. storage server: for storing the data server of testing result.
7. rejecting plug-in strip: the executive device for eliminating substandard product from assembly line.
The workflow of this system is as shown in Figure 5: system composition is as shown in Figure 1, product to be measured (flowing water on a moving belt
Line) movement, the optocoupler trigger 1# generation outer triggering signal that system uses.Testee needs specific illumination in order to produce
The raw image for being suitble to detection and identification, therefore the light source light filling for meeting site requirement is added in systems.Positioning shooting machine is being received
When to optocoupler trigger 1# signal, acquires all area images to be measured of current test product and upload to detection and analysis server
(being flowed by MJPEG), tests and analyzes and runs a specific machine vision applications in server, which can analyze determining image
On all regions to be measured, and corresponding location information is passed into detection video camera, detection video camera according to location information, by
A pair of all regions to be measured are detected, and acquired image is by automatic exposure, automatic white balance, automatic noise reduction, automatic increasing
Uploading detection Analysis server detects current measured object by the analysis and comparison of server after the pretreatment of the technologies such as benefit
Quality results, and store the result into storage server.Storage server is a database server, can save and be up to
1 year even higher data content, simultaneity factor are furnished with query software, support the quality knot of different terminals inquiry specific time
Fruit and relevant statistical report form.On assembly line design have device for eliminating, when product is detected it is defective in quality when, detection point
Server is analysed by the triggering times of optocoupler trigger 2#, calculates real time position of the substandard product in producing line, when not conforming to
Lattice product reach reject plug-in strip when, test and analyze server to reject plug-in strip issue action command, in time by substandard product from
It is shunted away on assembly line.
Dual-machine linkage industrial machine vision automatic checkout system, Ke Yijian are formed by positioning shooting machine and detection video camera
Current all regions to be measured of product to be measured are surveyed, guarantee is completely covered test request, is accurately positioned the real time position of substandard product,
Production line is eliminated, detection success rate is improved.Solve the problems, such as the low precision of current manual's detection mode, poor efficiency.
The work of the alternative artificial vision of dual-machine linkage industrial machine vision automatic checkout system.It is widely used for operating condition prison
Depending on the fields such as, product inspection and quality control.Using this system carry out industrial defects detection have it is non-contact, efficient, inexpensive,
The advantages that high degree of automation, can replace traditional defect inspection method completely.This detection and measurement are non-manual operations,
Therefore a large amount of human resources can be saved, considerable interests is brought for company, so its application is also more and more extensive.
Fig. 6 is the specific embodiment of this system, and by function division, whole system can be divided into four big subsystems.Point
Not are as follows: image acquisition subsystem, application software, image analysis subsystem and storage Query Subsystem.
It is illustrated referring now to this four subsystems:
One, image acquisition subsystem
It is mainly responsible for the image of acquisition testee.Main function has:
Optocoupler trigger: it is docked including optocoupler hardware components, and with camera;
Lighting system: hardware components provide optimal illuminating effect for scene, have great shadow to the image quality of camera
It rings;
Video camera: camera should select high-resolution (1080P or more), and aperture time wants short (for high-speed flow line, shutter
Time will be lower than 1/1000s);
Video camera customizes software: aiming at the video camera firmware of industrial detection optimization;
MJPEG spreads defeated: video camera acquired image data are sent to application program by MJPEG stream.
Two, application software
Application software part calls image analysis subsystem to carry out the analysis identification of image, and friendly friendship is provided for user
The mutual page.It is mainly made of following several parts:
MJPEG stream decoding: the MJPEG stream received is decoded, rgb image data is obtained;
Image interface: the image interface being defined between application software and image analysis subsystem is responsible for image data
It is converted to the format of image analysis needs, and is transmitted to image analysis subsystem;
Customization UI: friendly human-computer interaction interface is provided;
Memory interface: being defined on application software and stores the interface between Query Subsystem.
Three, image analysis subsystem
Image analysis subsystem is responsible for executing the image received specific analysis identification mission.Its function is fixed as needed
System, typical function such as:
Image enhancement: specific enhancing processing is carried out to the image of input, convenient for analysis and identification;
Image filtering: carrying out noise reduction process to image, helps to reduce the difficulty and error in analysis and identification;
Character segmentation: the character that specific region in image occurs is detected and is divided, the result of each segmentation represents
One specific character;
Character recognition: the character represented to segmentation result identifies, generallys use multilayer neural network, SVM or super
The sorting algorithms such as box identify;
Spot detection: detection testee surface is stained situation;
Two dimensional code identification: whether the two-dimensional barcode information of identification product surface printing, detection two dimensional code are wrong;
Bar code recognition: whether the bar code information of identification product surface printing, detection bar code are wrong;
Text detection: whether the printing word for detecting specific region is wrong, such as specification misprint;
The video procession function of other demands.
Four, Query Subsystem is stored
It is mainly responsible for the detection information of storage product.Main function has:
Data base administration: including information in foundation, storage, modification and access database;
User management: it is related to Role Management, role organizes management, the imparting corresponding right of different role;
As a result it records: the information record of product testing quality results;
Statistical report form: the information about product testing quality results is depicted as report form;
Web browsing: user is allowed to access on Web browser;
Log: the information of hardware, software and system problem in record system, the event occurred in monitoring system.
It should be noted that the description of the above specific embodiment is not intended to limit the invention, it is all in essence of the invention
Any modification, equivalent replacement, improvement and so within mind and principle, should all be included in the protection scope of the present invention.
Claims (7)
1. a kind of dual-machine linkage industrial machine vision automatic checkout system, which is characterized in that the system includes four modules, point
Not are as follows: image capture module, application software module, image analysis module and storage enquiry module, wherein
Described image acquisition module is responsible for acquiring the image of testee, and image capture module includes that positioning shooting machine and detection are taken the photograph
Camera, positioning shooting machine is used to determine the region to be measured of the complicated product to be measured of large volume, by product to be measured from the image of acquisition
All zone locations to be measured, and image is uploaded to the detection and analysis server in image analysis module, the server is by phase
It closes location information and passes to detection video camera, detection video camera is to the image in all regions to be measured acquisition testing and by image one by one
It is uploaded to detection and analysis server, realizes positioning shooting machine and detection video camera dual-machine linkage;
Described image analysis module is executed specific analysis identification to the image received by the calling of the application software module and appointed
Business;
The application software module provides friendly interaction page for user, and defines connecing between storage Query Subsystem
Mouthful;
The storage enquiry module is managed the database of the product testing information stored and user.
2. dual-machine linkage industrial machine vision automatic checkout system according to claim 1, it is characterised in that the detection
Video camera can pre-process acquired image before being uploaded to detection and analysis server.
3. dual-machine linkage industrial machine vision automatic checkout system according to claim 2, it is characterised in that the pre- place
Reason includes automatic exposure, automatic white balance, automatic noise reduction and automatic gain function.
4. dual-machine linkage industrial machine vision automatic checkout system according to claim 2, it is characterised in that detection camera shooting
To acquired image, the uploading detection Analysis server after pretreatment is detected by the analysis and comparison of server machine
The quality results of current measured object, and store the result into storage server.
5. dual-machine linkage industrial machine vision automatic checkout system according to claim 1, it is characterised in that the detection
A specific Machine Vision Detection is run in Analysis server and analyzes software, and other equipment in the software and system are provided
Data-interface.
6. dual-machine linkage industrial machine vision automatic checkout system according to claim 5, it is characterised in that by described
Machine Vision Detection analyzes the image data that software detection Analysis server receives the acquisition of positioning shooting machine, is worked as by analyzing determination
All regional locations to be measured of preceding product to be measured, and location information is passed into detection video camera, pass through analysis detection video camera
Whether the image information of return, and it is compared with standard qualified products template data, it is qualified to judge automatically current production,
Substandard product is rejected if unqualified.
7. dual-machine linkage industrial machine vision automatic checkout system according to claim 6, it is characterised in that if it is determined that
The unqualified triggering times for then passing through optocoupler trigger of current production calculate substandard product in the position of production line, to work as
When substandard product reaches rejecting plug-in strip, action command is issued to plug-in strip is rejected, rejects substandard product.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810863357.0A CN108993929A (en) | 2018-08-01 | 2018-08-01 | A kind of dual-machine linkage industrial machine vision automatic checkout system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810863357.0A CN108993929A (en) | 2018-08-01 | 2018-08-01 | A kind of dual-machine linkage industrial machine vision automatic checkout system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108993929A true CN108993929A (en) | 2018-12-14 |
Family
ID=64594179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810863357.0A Pending CN108993929A (en) | 2018-08-01 | 2018-08-01 | A kind of dual-machine linkage industrial machine vision automatic checkout system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108993929A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110118777A (en) * | 2019-04-30 | 2019-08-13 | 北京航天自动控制研究所 | A kind of control system system integration Smart Verify platform |
CN110133006A (en) * | 2019-04-02 | 2019-08-16 | 无锡奥驰豪迈科技有限公司 | Take turns tyre defect X-ray automatic checkout system |
CN113129284A (en) * | 2021-02-26 | 2021-07-16 | 山东大学 | Appearance detection method based on 5G cloud edge cooperation and implementation system |
CN113552139A (en) * | 2021-06-23 | 2021-10-26 | 番禺得意精密电子工业有限公司 | Automatic vision detection system and detection method |
CN114280073A (en) * | 2021-12-27 | 2022-04-05 | 南京光衡科技有限公司 | Tile defect detection device adopting laser and camera composite detection mode and classification method |
CN114707904A (en) * | 2022-05-05 | 2022-07-05 | 江苏文友软件有限公司 | Quality detection method and system based on big data |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101403602A (en) * | 2008-11-17 | 2009-04-08 | 天津理工大学 | Embedded high-speed on-line machine vision detection method and device |
WO2013106469A1 (en) * | 2012-01-11 | 2013-07-18 | Quirky, Inc. | Apparatus and methods for removing material from a surface |
CN104792263A (en) * | 2015-04-20 | 2015-07-22 | 合肥京东方光电科技有限公司 | Method and device for determining to-be-detected area of display mother board |
CN105975762A (en) * | 2016-04-29 | 2016-09-28 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN106000912A (en) * | 2016-05-18 | 2016-10-12 | 湖北工业大学 | Citrus cyst foreign matter removing system based on machine vision guidance |
CN107150032A (en) * | 2016-03-04 | 2017-09-12 | 上海电气集团股份有限公司 | A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method |
CN107786811A (en) * | 2017-10-20 | 2018-03-09 | 维沃移动通信有限公司 | A kind of photographic method and mobile terminal |
CN112598651A (en) * | 2020-12-24 | 2021-04-02 | 武汉吉电科技有限公司 | Intelligent robot processing production detecting system |
-
2018
- 2018-08-01 CN CN201810863357.0A patent/CN108993929A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101403602A (en) * | 2008-11-17 | 2009-04-08 | 天津理工大学 | Embedded high-speed on-line machine vision detection method and device |
WO2013106469A1 (en) * | 2012-01-11 | 2013-07-18 | Quirky, Inc. | Apparatus and methods for removing material from a surface |
CN104792263A (en) * | 2015-04-20 | 2015-07-22 | 合肥京东方光电科技有限公司 | Method and device for determining to-be-detected area of display mother board |
CN107150032A (en) * | 2016-03-04 | 2017-09-12 | 上海电气集团股份有限公司 | A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method |
CN105975762A (en) * | 2016-04-29 | 2016-09-28 | 联想(北京)有限公司 | Information processing method and electronic equipment |
CN106000912A (en) * | 2016-05-18 | 2016-10-12 | 湖北工业大学 | Citrus cyst foreign matter removing system based on machine vision guidance |
CN107786811A (en) * | 2017-10-20 | 2018-03-09 | 维沃移动通信有限公司 | A kind of photographic method and mobile terminal |
CN112598651A (en) * | 2020-12-24 | 2021-04-02 | 武汉吉电科技有限公司 | Intelligent robot processing production detecting system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110133006A (en) * | 2019-04-02 | 2019-08-16 | 无锡奥驰豪迈科技有限公司 | Take turns tyre defect X-ray automatic checkout system |
CN110118777A (en) * | 2019-04-30 | 2019-08-13 | 北京航天自动控制研究所 | A kind of control system system integration Smart Verify platform |
CN113129284A (en) * | 2021-02-26 | 2021-07-16 | 山东大学 | Appearance detection method based on 5G cloud edge cooperation and implementation system |
CN113129284B (en) * | 2021-02-26 | 2023-04-07 | 山东大学 | Appearance detection method based on 5G cloud edge cooperation and implementation system |
CN113552139A (en) * | 2021-06-23 | 2021-10-26 | 番禺得意精密电子工业有限公司 | Automatic vision detection system and detection method |
CN114280073A (en) * | 2021-12-27 | 2022-04-05 | 南京光衡科技有限公司 | Tile defect detection device adopting laser and camera composite detection mode and classification method |
CN114707904A (en) * | 2022-05-05 | 2022-07-05 | 江苏文友软件有限公司 | Quality detection method and system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108993929A (en) | A kind of dual-machine linkage industrial machine vision automatic checkout system | |
Yun et al. | Automated defect inspection system for metal surfaces based on deep learning and data augmentation | |
KR102108956B1 (en) | Apparatus for Performing Inspection of Machine Vision and Driving Method Thereof, and Computer Readable Recording Medium | |
CN108982514A (en) | A kind of bionical vision detection system of casting surface defect | |
CN111507976B (en) | Defect detection method and system based on multi-angle imaging | |
CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
Medina et al. | Automated visual classification of frequent defects in flat steel coils | |
CN112884768A (en) | Neural network-based 3D printing online quality monitoring method, system and device | |
CN111179250A (en) | Industrial product defect detection system based on multitask learning | |
KR20220164124A (en) | System for inspecting product defects by type based on a deep learning model | |
Jung et al. | Anomaly Candidate Extraction and Detection for automatic quality inspection of metal casting products using high-resolution images | |
Kovalev et al. | Development of a module for analyzing milling defects using computer vision defects using computer vision | |
CN116071365A (en) | Part detection method, device, equipment and storage medium | |
Li et al. | Serial number inspection for ceramic membranes via an end-to-end photometric-induced convolutional neural network framework | |
Zhou et al. | Automated detection of surface defects on sphere parts using laser and CDD measurements | |
Zhang et al. | Research on brake pad surface defects detection based on deep learning | |
Evstafev et al. | Surface Defect Detection and Recognition Based on CNN | |
CN109632815A (en) | Surface defect on-line detecting system and method | |
Klarák et al. | Processing 3D data from laser sensor into visual content using pattern recognition | |
KR20230068445A (en) | Automatic quality inspection device and method of hole image based on artificial intelligence | |
Lin et al. | Applying discrete cosine transform and grey relational analysis to surface defect detection of LEDs | |
Qiao et al. | A Chip Defect Detection System Based on Machine Vision | |
CN112893178B (en) | Pen core quality detection system | |
KR102618194B1 (en) | Semiconductor package board processing hole 3d automatic process inspection method and system | |
CN114882597B (en) | Target behavior identification method and device and electronic equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181214 |