CN105572137A - Appearance defect test method - Google Patents
Appearance defect test method Download PDFInfo
- Publication number
- CN105572137A CN105572137A CN201510931910.6A CN201510931910A CN105572137A CN 105572137 A CN105572137 A CN 105572137A CN 201510931910 A CN201510931910 A CN 201510931910A CN 105572137 A CN105572137 A CN 105572137A
- Authority
- CN
- China
- Prior art keywords
- product
- image
- appearance
- product appearance
- standard picture
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan 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
- G01N2021/8887—Scan 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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an appearance defect test method, comprising the following steps of acquiring an image test interface of a product appearance by means of invoking an industrial camera to perform image acquisition on the product appearance, wherein the image test interface of the product appearance comprises an image of the product appearance; receiving a test command, and executing the test command in the image test interface of the product appearance; comparing the image of the product appearance in the image test interface with a pre-stored standard image by utilization of a test algorithm, and determining that the product appearance is defective if a difference between the image of the product appearance and the pre-stored standard image is beyond a preset range. The method disclosed by the invention has the advantages that the defect test of the product appearance is quickly and accurately performed, and the labor cost is saved.
Description
Technical field
The present invention relates to outward appearance technical field of measurement and test, particularly relate to a kind of open defect method of testing.
Background technology
At present, for the test of these products such as the test of auto parts and components outward appearance, gear defects test, cloth defect test and ceramic defect, the method of general employing manual testing detects outward appearance, need technician to use testing tool comprehensively check product and get rid of defect, find out open defect.
Owing to needing a large amount of technician and testing tool and testing the outward appearance of product, test process is also very loaded down with trivial details, and overlong time not only wastes a large amount of human resources, and causes the efficiency of test lower, finds out defect also not accurate enoughly.
Summary of the invention
The object of this invention is to provide a kind of open defect method of testing, to realize the defect test fast and accurately to product appearance, save human cost.
For solving the problems of the technologies described above, the invention provides a kind of open defect method of testing, the method comprises:
Call industrial camera and image acquisition is carried out to the outward appearance of product, obtain the image measurement interface of product appearance; The image measurement interface of described product appearance comprises the image of product appearance;
Receive test command, in the image measurement interface of described product appearance, perform test command;
Utilize testing algorithm the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance.
Preferably, before described reception test command, also comprise:
Obtain the appearance images of standardized product;
Picture frame is carried out to the appearance images of standardized product, utilizes degree of deep learning algorithm to carry out automatic learning to the local parameter of the appearance images of standardized product;
The learning parameter generated in automatic learning process is preserved.
Preferably, described product comprises auto parts and components, gear, cloth, pottery or paper.
Preferably, after the appearance images of described acquisition standardized product, also comprise:
The appearance images of standardized product is loaded in internal memory as standard picture, and described standard picture is divided into some.
Preferably, the image of product appearance in image measurement interface and the standard picture prestored are compared by the described testing algorithm that utilizes, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance, comprising:
The image of product appearance is divided into some;
According to testing algorithm, compare being divided into the image of the product appearance of some with the default standard picture of some that is divided into stored;
Comparative result and learning parameter are contrasted, if comparing result is not in tolerance, determines product appearance existing defects; Described learning parameter is the learning parameter that standard picture generates in automatic learning process.
Preferably, described in call industrial camera image acquisition carried out to the outward appearance of product, obtain the image measurement interface of product appearance, comprising:
Call industrial camera, send signal light control order by serial ports, polishing is carried out to tested product, obtain the image measurement interface of product appearance.
A kind of open defect method of testing provided by the present invention, calls industrial camera and carries out image acquisition to the outward appearance of product, obtains the image measurement interface of product appearance; The image measurement interface of described product appearance comprises the image of product appearance; Receive test command, in the image measurement interface of described product appearance, perform test command; Utilize testing algorithm the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance.Visible, the method realizes the defect test fast and accurately to product appearance, the right mode of image ratio is adopted only to require a very short time just to complete the open defect of a new product to test, manual testing is carried out without the need to technician, save human cost, and participate in without the need to too much artificial, testing process is simple, efficient and objective.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only embodiments of the invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to the accompanying drawing provided.
Fig. 1 is the process flow diagram of a kind of open defect method of testing provided by the present invention.
Embodiment
Core of the present invention is to provide a kind of open defect method of testing, to realize the defect test fast and accurately to product appearance, saves human cost.
The present invention program is understood better in order to make those skilled in the art person, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Please refer to Fig. 1, Fig. 1 is the process flow diagram of a kind of open defect method of testing provided by the present invention, and the method comprises:
S11: call industrial camera and carry out image acquisition to the outward appearance of product, obtains the image measurement interface of product appearance; The image measurement interface of product appearance comprises the image of product appearance;
Wherein, call industrial camera and carry out image acquisition to the outward appearance of product, the detailed process obtaining the image measurement interface of product appearance is: call industrial camera, sends signal light control order by serial ports, polishing is carried out to tested product, obtains the image measurement interface of product appearance.
Wherein, described product comprises auto parts and components, gear, cloth, pottery or paper.
S12: receive test command, perform test command in the image measurement interface of product appearance;
Wherein, before receiving test command, obtain the appearance images of standardized product; Picture frame is carried out to the appearance images of standardized product, utilizes degree of deep learning algorithm to carry out automatic learning to the local parameter of the appearance images of standardized product; The learning parameter generated in automatic learning process is preserved.
Wherein, after obtaining the appearance images of standardized product, the appearance images of standardized product is loaded in internal memory as standard picture, and standard picture is divided into some.
S13: utilize testing algorithm the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance.
Wherein, testing algorithm is utilized the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that product appearance occurs that the process of defect is specially: the image of product appearance is divided into some; According to testing algorithm, compare being divided into the image of the product appearance of some with the default standard picture of some that is divided into stored; Comparative result and learning parameter are contrasted, if comparing result is not in tolerance, determines product appearance existing defects; Described learning parameter is the learning parameter that standard picture generates in automatic learning process.
The method can be used in the test of auto parts and components outward appearance, and gear defects is tested, cloth defect test, ceramic defect test, the fields such as paper stain test.Only need a few minutes just can complete the open defect test of a new product.
Concrete, in the specific implementation process of the method, call industrial camera, send signal light control order by serial ports simultaneously and polishing is carried out to tested article.At study interface, tester can edit testing process and select testing algorithm.At test interface, can test be started by enter key or start test by serial ports transmission order.Tester presses left mouse button and carries out picture frame to tested object, mouse clicks " interpolation " button, corresponding algorithm is selected after ejection algorithm dialog box, the automatic learning to tested object local parameter can be completed, study to whole tested object is completed by continuing to click " interpolation " button to the local picture frame of tested object and mouse, all parameters of study will be preserved in xml format, prevent illegal modifications.The name of parts of study and the algorithm of selection, by being presented at the right at study interface with forms mode, can use the mode of click " deletion " or " amendment " button to modify to the parts learnt.
And, can test be started by enter key or start test by serial ports transmission order, performing flow process is afterwards:
The canonical parameter learnt in a flash and the normal pictures that start test will be loaded into internal memory; Camera is taken pictures, and reads the picture product of current tested article from camera; Some slice are become to be saved in internal memory according to flow process during study with non-parametric segmentation to photo current; Some little pictures of photo current and normal pictures compare according to the algorithm of specifying when learning; Automatically the parameter generated when comparative result and study contrasts, if in tolerance, corresponding little picture is qualified, and comparative result saves as mark T, otherwise defective, and comparative result saves as mark F; Form simultaneously on the right of refresh test interface, it is defective that result is that the test item of F is shown as, and it is qualified that result is that the test item of T is shown as, and compared result is that it is drawn red frame in the corresponding region of product picture by the little picture of correspondence of F.
A kind of open defect method of testing provided by the present invention, calls industrial camera and carries out image acquisition to the outward appearance of product, obtains the image measurement interface of product appearance; The image measurement interface of product appearance comprises the image of product appearance; Receive test command, in the image measurement interface of product appearance, perform test command; Utilize testing algorithm the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance.Visible, the method realizes the defect test fast and accurately to product appearance, the right mode of image ratio is adopted only to require a very short time just to complete the open defect of a new product to test, manual testing is carried out without the need to technician, save human cost, and participate in without the need to too much artificial, testing process is simple, efficient and objective.
Above a kind of open defect method of testing provided by the present invention is described in detail.Apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping.It should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention, can also carry out some improvement and modification to the present invention, these improve and modify and also fall in the protection domain of the claims in the present invention.
Claims (6)
1. an open defect method of testing, is characterized in that, comprising:
Call industrial camera and image acquisition is carried out to the outward appearance of product, obtain the image measurement interface of product appearance; The image measurement interface of described product appearance comprises the image of product appearance;
Receive test command, in the image measurement interface of described product appearance, perform test command;
Utilize testing algorithm the image of product appearance in image measurement interface and the standard picture prestored to be compared, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance.
2. the method for claim 1, is characterized in that, before described reception test command, also comprises:
Obtain the appearance images of standardized product;
Picture frame is carried out to the appearance images of standardized product, utilizes degree of deep learning algorithm to carry out automatic learning to the local parameter of the appearance images of standardized product;
The learning parameter generated in automatic learning process is preserved.
3. the method for claim 1, is characterized in that, described product comprises auto parts and components, gear, cloth, pottery or paper.
4. method as claimed in claim 2, is characterized in that, after the appearance images of described acquisition standardized product, also comprise:
The appearance images of standardized product is loaded in internal memory as standard picture, and described standard picture is divided into some.
5. method as claimed in claim 4, it is characterized in that, the image of product appearance in image measurement interface and the standard picture prestored are compared by the described testing algorithm that utilizes, if the difference results between the image of product appearance and the standard picture prestored exceedes preset range, determine that defect appears in product appearance, comprising:
The image of product appearance is divided into some;
According to testing algorithm, compare being divided into the image of the product appearance of some with the default standard picture of some that is divided into stored;
Comparative result and learning parameter are contrasted, if comparing result is not in tolerance, determines product appearance existing defects; Described learning parameter is the learning parameter that standard picture generates in automatic learning process.
6., as the method in claim 1 to 5 as described in any one, it is characterized in that, described in call industrial camera image acquisition carried out to the outward appearance of product, obtain the image measurement interface of product appearance, comprising:
Call industrial camera, send signal light control order by serial ports, polishing is carried out to tested product, obtain the image measurement interface of product appearance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510931910.6A CN105572137A (en) | 2015-12-15 | 2015-12-15 | Appearance defect test method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510931910.6A CN105572137A (en) | 2015-12-15 | 2015-12-15 | Appearance defect test method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105572137A true CN105572137A (en) | 2016-05-11 |
Family
ID=55882513
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510931910.6A Pending CN105572137A (en) | 2015-12-15 | 2015-12-15 | Appearance defect test method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105572137A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106442540A (en) * | 2016-09-07 | 2017-02-22 | 京东方科技集团股份有限公司 | Optical detection method and system |
CN107421955A (en) * | 2017-08-25 | 2017-12-01 | 西京学院 | A kind of ceramic defective vision detection method |
CN108229561A (en) * | 2018-01-03 | 2018-06-29 | 北京先见科技有限公司 | Particle product defect detection method based on deep learning |
CN108615232A (en) * | 2018-04-02 | 2018-10-02 | 珠海格力电器股份有限公司 | Detection method, device and the detection platform of enamel coating defect |
CN108663373A (en) * | 2018-05-15 | 2018-10-16 | 国网重庆市电力公司电力科学研究院 | A kind of electric energy meter surface structure and component information acquisition comparison method and system |
CN109919940A (en) * | 2019-03-28 | 2019-06-21 | 北京三快在线科技有限公司 | A kind of item detection systems and method |
CN111766255A (en) * | 2020-06-02 | 2020-10-13 | 珠海诚锋电子科技有限公司 | Flexible circuit board flaw detection method and device |
CN111815552A (en) * | 2019-04-09 | 2020-10-23 | Tcl集团股份有限公司 | Workpiece detection method and device, readable storage medium and terminal equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006071284A (en) * | 2004-08-31 | 2006-03-16 | Central Glass Co Ltd | Inside and outside discrimination method of flaw of glass substrate |
JP2006234656A (en) * | 2005-02-25 | 2006-09-07 | Ricoh Co Ltd | Defect detection device and defect detection method |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN103207183A (en) * | 2011-12-28 | 2013-07-17 | 株式会社其恩斯 | Visual Inspection Device And Visual Inspection Method |
CN103592310A (en) * | 2013-11-22 | 2014-02-19 | 昆山视杰维光电科技有限公司 | System for detecting keyboard |
CN104111029A (en) * | 2013-04-19 | 2014-10-22 | 延锋伟世通汽车电子有限公司 | Machine vision detection system used for electronic product processing inspection |
CN104142349A (en) * | 2014-07-28 | 2014-11-12 | 云南省机械研究设计院 | Method for detecting heat sealing defects of external packaging transparent film |
-
2015
- 2015-12-15 CN CN201510931910.6A patent/CN105572137A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006071284A (en) * | 2004-08-31 | 2006-03-16 | Central Glass Co Ltd | Inside and outside discrimination method of flaw of glass substrate |
JP2006234656A (en) * | 2005-02-25 | 2006-09-07 | Ricoh Co Ltd | Defect detection device and defect detection method |
CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
CN103207183A (en) * | 2011-12-28 | 2013-07-17 | 株式会社其恩斯 | Visual Inspection Device And Visual Inspection Method |
CN104111029A (en) * | 2013-04-19 | 2014-10-22 | 延锋伟世通汽车电子有限公司 | Machine vision detection system used for electronic product processing inspection |
CN103592310A (en) * | 2013-11-22 | 2014-02-19 | 昆山视杰维光电科技有限公司 | System for detecting keyboard |
CN104142349A (en) * | 2014-07-28 | 2014-11-12 | 云南省机械研究设计院 | Method for detecting heat sealing defects of external packaging transparent film |
Non-Patent Citations (2)
Title |
---|
YANN LECUN ET AL: "Deep learning", 《NATURE》 * |
王宪保 等: "基于深度学习的太阳能电池片表面缺陷检测方法", 《模式识别与人工智能》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106442540A (en) * | 2016-09-07 | 2017-02-22 | 京东方科技集团股份有限公司 | Optical detection method and system |
CN107421955A (en) * | 2017-08-25 | 2017-12-01 | 西京学院 | A kind of ceramic defective vision detection method |
CN108229561A (en) * | 2018-01-03 | 2018-06-29 | 北京先见科技有限公司 | Particle product defect detection method based on deep learning |
CN108615232A (en) * | 2018-04-02 | 2018-10-02 | 珠海格力电器股份有限公司 | Detection method, device and the detection platform of enamel coating defect |
CN108663373A (en) * | 2018-05-15 | 2018-10-16 | 国网重庆市电力公司电力科学研究院 | A kind of electric energy meter surface structure and component information acquisition comparison method and system |
CN109919940A (en) * | 2019-03-28 | 2019-06-21 | 北京三快在线科技有限公司 | A kind of item detection systems and method |
CN109919940B (en) * | 2019-03-28 | 2020-08-07 | 北京三快在线科技有限公司 | Article detection system and method |
CN111815552A (en) * | 2019-04-09 | 2020-10-23 | Tcl集团股份有限公司 | Workpiece detection method and device, readable storage medium and terminal equipment |
CN111766255A (en) * | 2020-06-02 | 2020-10-13 | 珠海诚锋电子科技有限公司 | Flexible circuit board flaw detection method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105572137A (en) | Appearance defect test method | |
CN106097361B (en) | Defect area detection method and device | |
WO2019096178A1 (en) | Fiber detection method and apparatus, and electronic device | |
US20190007589A1 (en) | Camera initialization for multiple camera devices | |
WO2018071958A1 (en) | System and method for performing automated analysis of air samples | |
CN110838149B (en) | Camera light source automatic configuration method and system | |
DE102016212984A1 (en) | Check for potentially unwanted items of laundry | |
CN111896232B (en) | Optical machine module testing method, equipment, system and computer readable storage medium | |
CN112730251B (en) | Device and method for detecting screen color defects | |
CN103945201A (en) | IR-Cut optical filter switching method, device and camera | |
WO2019011342A1 (en) | Cloth identification method and device, electronic device and storage medium | |
CN111145138A (en) | Detection method, device and equipment of LED lamp panel and storage medium | |
CN108280865B (en) | Color matching method, system, storage medium and computer equipment | |
JP2020077165A5 (en) | ||
CN106780488B (en) | System and method for detecting definition of digital pathological section | |
JP2015197929A (en) | Method for automatically setting image inspection system error identification parameter by computer | |
CN110824338A (en) | Method and system for automatically testing chip | |
CN111263141B (en) | Camera detection method and device and production line system | |
CN110441714B (en) | Method and device for detecting indicator light and computer readable storage medium | |
CN105572136A (en) | Test parameter generation method in appearance defect test | |
CN106383305A (en) | Printed circuit board testing method, printed circuit board testing device and testing tool | |
CN105548210A (en) | Detection method for American-standard power source extension wire based on machine vision | |
KR102462591B1 (en) | Sewing line automatic inspection method using vision system | |
KR20190101107A (en) | Method for detecting a defect in molding products using by analysis of conversion brightness | |
CN113850795A (en) | Test triggering method, device to be tested and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20160511 |