Movatterモバイル変換


[0]ホーム

URL:


CN109596625A - Workpiece, defect detection recognition method in charging tray - Google Patents

Workpiece, defect detection recognition method in charging tray
Download PDF

Info

Publication number
CN109596625A
CN109596625ACN201910101499.8ACN201910101499ACN109596625ACN 109596625 ACN109596625 ACN 109596625ACN 201910101499 ACN201910101499 ACN 201910101499ACN 109596625 ACN109596625 ACN 109596625A
Authority
CN
China
Prior art keywords
workpiece
charging tray
recognition method
defect detection
cabinet
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
CN201910101499.8A
Other languages
Chinese (zh)
Inventor
谭良
赵大庆
蔡毓
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.)
Zhongke Fenghai Foshan Intelligent 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 LtdfiledCriticalDongguan Zhongke Blue Sea Intelligent Vision Technology Co Ltd
Priority to CN201910101499.8ApriorityCriticalpatent/CN109596625A/en
Publication of CN109596625ApublicationCriticalpatent/CN109596625A/en
Pendinglegal-statusCriticalCurrent

Links

Classifications

Landscapes

Abstract

The present invention relates to technical field of vision detection, the workpiece, defect detection recognition method in a kind of charging tray is referred in particular to, is included the following steps, step 1: Image Acquisition is carried out to the workpiece on charging tray;Step 2: the image of acquisition is subjected to binary conversion treatment;Step 3: spot detection algorithm being carried out to the image after binary conversion treatment, identifies the defect of each workpiece in charging tray;Step 4: the result of identification judgement is converted into the output of readable data information, charging tray need to only be moved to camera site and can be automatically performed the block division of charging tray and carry out Image Acquisition to the block of each division, shooting station without being repeatedly moved to different is repeatedly shot, the arrangement for reducing hardware device reduces manufacturing cost, the algorithm steps of the technical program are also more simple, reduce operation time and improve production efficiency.

Description

Workpiece, defect detection recognition method in charging tray
Technical field
The present invention relates to technical field of vision detection, the workpiece, defect detection recognition method in a kind of charging tray is referred in particular to.
Background technique
The characteristics of Machine Vision Detection is the flexibility and the degree of automation for improving production.It is not suitable for manual work someDangerous work environment or artificial vision be difficult to the occasion met the requirements, machine in normal service vision substitutes artificial vision;Exist simultaneouslyIn high-volume industrial processes, manually visual inspection product quality low efficiency and precision is not high, with Machine Vision Detection sideMethod can greatly improve the degree of automation of production efficiency and production.And machine vision is easily achieved information integration, is to realizeThe basic technology of computer integrated manufacturing system.Vision-based detection is exactly to replace human eye with machine to measure and judge.Vision-based detection isRefer to that, by machine vision product, image-pickup device is divided to CMOS and two kinds of CCD, will be ingested target and be converted into picture signal,It sends dedicated image processing system to, according to the information such as pixel distribution and brightness, color, is transformed into digitized signal;ImageSystem carries out various operations to these signals to extract clarification of objective, and then the equipment at scene is controlled according to the result of differentiationMovement.It is the valuable mechanism for producing, assembling or pack.It is in detection defect and prevents from faulty goods to be dispensed into disappearingThere is immeasurable value in terms of the function of the person of expense.
As above situation, vision-based detection has huge market value, most crucial in vision-based detection system not to beHardware device but algorithm steps, and algorithm steps can be because of testing result requirement, product shape, operating environment situation and designThe appearance of the factors such as the technical capability of personnel or group is multifarious, if core algorithm step design shortcoming, affects a whole set of viewThe operational efficiency and running quality for feeling detection device, and in the algorithm steps to multiple workpiece in charging tray, big portion in the marketDivide the use cost of technical solution high, while algorithm steps also join by the complex conventional change for being unfavorable for those skilled in the artThe operations such as number setting.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of workpiece by entire charging tray to identify in batches, guarantees that identification is quasi-The requirement that hardware device is reduced while exactness reduces manufacture production cost, and algorithm steps are simply easy to the charging tray of operationIn workpiece, defect detection recognition method.
In order to solve the above-mentioned technical problem, the present invention adopts the following technical scheme: the workpiece, defect in a kind of charging tray detectsRecognition methods includes the following steps, step 1: carrying out Image Acquisition to the workpiece on charging tray;
Step 2: the image of acquisition is subjected to binary conversion treatment;
Step 3: spot detection algorithm being carried out to the image after binary conversion treatment, identifies the defect of each workpiece in charging tray;
Step 4: the result of identification judgement is converted into the output of readable data information.
Preferably, charging tray area is divided into 2 to 8 blocks in the step 1, an image is acquired to each block,Contain 10 to 40 workpiece in each block.
Preferably, charging tray area is divided into 8 blocks in the step 1, an image is acquired to each block, it is eachContain 25 workpiece in block.
Preferably, the fixed-focus mirror of 16 to 35 millimeters of the industrial camera collocation of 300 to 6,000,000 pixels is used in the step 1Head carries out Image Acquisition, and wherein the vertical spacing distance between tight shot and workpiece is 300 to 480 millimeters.
Preferably, the tight shot of 25 millimeters of industrial camera collocation in the step 1 using 5,000,000 pixels carries out imageAcquisition, wherein the vertical spacing distance between tight shot and workpiece is 369 millimeters.
Preferably, in the step 1 using coaxial light source auxiliary complete Image Acquisition, wherein coaxial light source include cabinet,The folding that shooting duct abuts upper wall in cabinet is extended up through through the shooting duct of cabinet setting, from the interior angle of cabinet sidePenetrate mirror and the luminous lamp group for being installed in cabinet wall.
Preferably, the industrial camera is connected with the second driving device for driving its side-to-side movement.
Preferably, the vertical spacing distance between the outside bottom surface and workpiece of the cabinet is 180 to 300 millimeters.
Preferably, the vertical spacing distance between the outside bottom surface and workpiece of the cabinet is 228 millimeters.
Preferably, the lateral wall of the cabinet, which is connected with, adjusts the first of firm arm and the firm arm horizontal movement of driving adjustingDriving device.
The beneficial effects of the present invention are: the present invention provides the workpiece, defect detection recognition method in a kind of charging tray,In practical application, multiple electronic workpieces are housed, then charging tray area is divided into 8 blocks, acquires one to each block in charging traySecondary image contains 25 workpiece in each block, then carries out at spot detection algorithm to the image of an independent block respectivelyReason, identification of the completion of high-accuracy to workpiece, defect in charging tray, charging tray, which need to only be moved to camera site, can be automatically performed materialThe block of disk divides and carries out Image Acquisition to the block of each division, and the shooting station progress without being repeatedly moved to different is moreSecondary shooting, the arrangement for reducing hardware device reduce manufacturing cost, and the algorithm steps of the technical program are also more simple, reduce operationTime improves production efficiency.
Detailed description of the invention
Fig. 1 is the Facad structure cut-away illustration of coaxial light source in the present invention.
Fig. 2 is coaxial light source in the present invention, the schematic perspective view for adjusting firm arm and first driving device.
Fig. 3 is the positive structure schematic of industrial camera, tight shot and the second driving device in the present invention.
Fig. 4 is the detection contrast schematic diagram of one of block after 8 block of charging tray in 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, realThe content that the mode of applying refers to not is limitation of the invention.
As shown in Figures 1 to 4, the workpiece, defect detection recognition method in a kind of charging tray, includes the following steps, step 1: rightWorkpiece 2 on charging tray 1 carries out Image Acquisition, and 1 area of charging tray is divided into 8 blocks, an image is acquired to each block, oftenContain 25 workpiece 2 in one block, carries out image using the tight shot 4 of 25 millimeters of the collocation of industrial camera 3 of 5,000,000 pixels and adoptCollection, wherein the vertical spacing distance between tight shot 4 and workpiece 2 is 369 millimeters, and industrial camera 3, which is connected with, drives its left and rightSecond driving device 6 of movement assists completing Image Acquisition using coaxial light source 5, and wherein coaxial light source 5 includes cabinet 51, passes throughIt wears the shooting duct 52 of the setting of cabinet 51, extended up through from the interior angle of 51 side of cabinet in the abutting cabinet 51 of shooting duct 52The refracting telescope 53 of upper wall and the luminous lamp group 54 for being installed in 51 inner wall of cabinet, it is perpendicular between the outside bottom surface and workpiece 2 of cabinet 51Straight spacing distance is 228 millimeters, and the lateral wall of cabinet 51 is connected with the firm arm 55 of adjusting and driving adjusts the horizontal fortune of firm arm 55Dynamic first driving device 56;
Step 2: the image of acquisition is subjected to binary conversion treatment;
Step 3: spot detection algorithm being carried out to the image after binary conversion treatment, identifies the defect of each workpiece 2 in charging tray 1;
Step 4: the result of identification judgement is converted into the output of readable data information.
Workpiece, defect detection recognition method in the charging tray of the present embodiment is equipped with multiple electricity in practical applications in charging tray 1Sub- workpiece 2, then 1 area of charging tray is divided into 8 blocks, and an image is acquired to each block, contains 25 in each blockThen workpiece 2 carries out spot detection algorithm process to the image of an independent block respectively, the completion of high-accuracy is to charging tray 1The identification of middle 2 defect of workpiece, 1 need of charging tray, which are moved to camera site, can be automatically performed the block division of charging tray 1 and to eachThe block of division carries out Image Acquisition, and the shooting station without being repeatedly moved to different is repeatedly shot, and reduces hardware deviceArrangement reduce manufacturing cost, the algorithm steps of the technical program are also more simple, reduce operation time and improve production efficiency.
In addition, being used for description purposes only if any term " first ", " second ", it is not understood to indicate or imply relatively heavyThe property wanted or the quantity for implicitly indicating technical characteristic." first " is defined as a result, " second " feature can be expressed or implicit includeOne or more this feature, in the present description, " several " are meant that two or more, unless otherwise clearly havingThe restriction of body.
In the present invention, except as otherwise clear stipulaties and restriction, should make if any term " assembling ", " connected ", " connection " termBroad 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 connectIt connects;It can be directly connected, be also possible to be connected by intermediary, can be and be connected inside two elements.For abilityFor 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 simultaneouslyLimitations 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 artFor, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the inventionProtect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.

Claims (10)

CN201910101499.8A2019-02-012019-02-01Workpiece, defect detection recognition method in charging trayPendingCN109596625A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201910101499.8ACN109596625A (en)2019-02-012019-02-01Workpiece, defect detection recognition method in charging tray

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201910101499.8ACN109596625A (en)2019-02-012019-02-01Workpiece, defect detection recognition method in charging tray

Publications (1)

Publication NumberPublication Date
CN109596625Atrue CN109596625A (en)2019-04-09

Family

ID=65967245

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201910101499.8APendingCN109596625A (en)2019-02-012019-02-01Workpiece, defect detection recognition method in charging tray

Country Status (1)

CountryLink
CN (1)CN109596625A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110108724A (en)*2019-04-202019-08-09东莞中科蓝海智能视觉科技有限公司Strip-shaped workpiece visual detection system
CN115018846A (en)*2022-08-092022-09-06东声(苏州)智能科技有限公司AI intelligent camera-based multi-target crack defect detection method and device
CN119887702A (en)*2024-12-302025-04-25四川深瑞视科技有限公司Method, device, equipment and medium for detecting inclination of tray lens

Citations (9)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN102654902A (en)*2012-01-162012-09-05江南大学Contour vector feature-based embedded real-time image matching method
CN104215639A (en)*2013-06-052014-12-17江南大学Pear surface defect detection method based on machine vision
CN104568986A (en)*2015-01-262015-04-29中国科学院半导体研究所Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm
CN104820986A (en)*2015-04-282015-08-05电子科技大学Machine vision-based cable on-line detection method
CN107220649A (en)*2017-05-272017-09-29江苏理工学院A kind of plain color cloth defects detection and sorting technique
CN107389701A (en)*2017-08-222017-11-24西北工业大学A kind of PCB visual defects automatic checkout system and method based on image
CN107664645A (en)*2016-07-292018-02-06欧姆龙株式会社Lighting unit, flaw detection apparatus and means of illumination
CN107966448A (en)*2017-11-172018-04-27福建工程学院A kind of 2 dimension detection methods for PCB paste solder printing quality
CN108273769A (en)*2018-04-132018-07-13四川巴斯德环境检测技术有限责任公司A kind of product surface quality detecting system based on machine vision technique

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN102654902A (en)*2012-01-162012-09-05江南大学Contour vector feature-based embedded real-time image matching method
CN104215639A (en)*2013-06-052014-12-17江南大学Pear surface defect detection method based on machine vision
CN104568986A (en)*2015-01-262015-04-29中国科学院半导体研究所Method for automatically detecting printing defects of remote controller panel based on SURF (Speed-Up Robust Feature) algorithm
CN104820986A (en)*2015-04-282015-08-05电子科技大学Machine vision-based cable on-line detection method
CN107664645A (en)*2016-07-292018-02-06欧姆龙株式会社Lighting unit, flaw detection apparatus and means of illumination
CN107220649A (en)*2017-05-272017-09-29江苏理工学院A kind of plain color cloth defects detection and sorting technique
CN107389701A (en)*2017-08-222017-11-24西北工业大学A kind of PCB visual defects automatic checkout system and method based on image
CN107966448A (en)*2017-11-172018-04-27福建工程学院A kind of 2 dimension detection methods for PCB paste solder printing quality
CN108273769A (en)*2018-04-132018-07-13四川巴斯德环境检测技术有限责任公司A kind of product surface quality detecting system based on machine vision technique

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
吴强等: "基于机器视觉的零件缺陷检测算法", 《科学技术创新》*
高宏伟: "《电子封装工艺与装备技术基础教程》", 31 December 2017*

Cited By (4)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN110108724A (en)*2019-04-202019-08-09东莞中科蓝海智能视觉科技有限公司Strip-shaped workpiece visual detection system
CN115018846A (en)*2022-08-092022-09-06东声(苏州)智能科技有限公司AI intelligent camera-based multi-target crack defect detection method and device
CN115018846B (en)*2022-08-092022-12-27东声(苏州)智能科技有限公司AI intelligent camera-based multi-target crack defect detection method and device
CN119887702A (en)*2024-12-302025-04-25四川深瑞视科技有限公司Method, device, equipment and medium for detecting inclination of tray lens

Similar Documents

PublicationPublication DateTitle
CN108288288B (en)Method, device and system for measuring precision shaft dimension based on visual identification
CN109859192A (en)The detection recognition method of round high reflective workpiece
CN102590218B (en)Device and method for detecting micro defects on bright and clean surface of metal part based on machine vision
CN106323600B (en)Cascade distributed AOI defect detection system and detection method thereof
CN105938243B (en)More multiplying power microscope quick focusing methods in a kind of TFT LCD detections
CN106210520B (en)A kind of automatic focusing electronic eyepiece and system
CN116879308A (en)Industrial machine vision system image processing method
CN109596625A (en)Workpiece, defect detection recognition method in charging tray
CN109596054A (en)The size detection recognition methods of strip workpiece
CN206981462U (en)Stamping parts surface defect detection apparatus based on 3D vision
CN105785561B (en)A kind of digital microscope and its focus method
CN112213320B (en)Biscuit detection device and biscuit detection method based on machine vision
CN104713527A (en)Single-time multi-angle shooting mechanism
CN109632814A (en)Part defect detection method
CN108805870A (en)A kind of detection method of the connector with needle stand
CN105890669A (en)Universal image visual inspection robot
CN109596058A (en)Size detection and identification method for plastic workpiece
CN102374997A (en)High-precision detection device of coin surface quality based on vision system
CN109916914A (en)A kind of product defects detection method and device
CN110082356A (en)The visible detection method and device of wire surface defect
CN117092113A (en)Camera mould welding quality detection device and system thereof
CN109631763A (en)Irregular part detection and positioning method
CN109632802A (en)Method for detecting and adjusting front and back surfaces of part
CN109631803A (en)Part angle detects adjusting method
CN115015119A (en)AOI (automated optical inspection) polishing imaging

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
TA01Transfer of patent application right
TA01Transfer of patent application right

Effective date of registration:20190920

Address after:528000 Room 409, 4-storey, Fengshou Street, Chao'an South Road, Zumiao Street, Chancheng District, Foshan City, Guangdong Province

Applicant after:Zhongke Fenghai (Foshan) Intelligent Technology Co., Ltd.

Address before:Room 301, Unit 2, Building No. 10, Science and Technology Second Road, Songshan Lake Park, Dongguan City, Guangdong Province

Applicant before:Dongguan Zhongke blue sea Intelligent Vision Technology Co., Ltd.

RJ01Rejection of invention patent application after publication
RJ01Rejection of invention patent application after publication

Application publication date:20190409


[8]ページ先頭

©2009-2025 Movatter.jp