CN102519967A - Board card material inspection method based on image identification detection - Google Patents
Board card material inspection method based on image identification detection Download PDFInfo
- Publication number
- CN102519967A CN102519967A CN2011103601707A CN201110360170A CN102519967A CN 102519967 A CN102519967 A CN 102519967A CN 2011103601707 A CN2011103601707 A CN 2011103601707A CN 201110360170 A CN201110360170 A CN 201110360170A CN 102519967 A CN102519967 A CN 102519967A
- Authority
- CN
- China
- Prior art keywords
- circuit board
- integrated circuit
- standard
- comparison
- board card
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a board card material inspection method based on image identification detection. The method comprises the following steps that: 1) adopting a standard board card according to the board card specification and feeding requirements, the consistency with the standard board card needs to be verified during the material feeding, the standard board adoption is obtained through multi-time artificial observation, and the standard board card is used as the subsequent comparison standard; 2) images of the standard board card are collected into a system, in addition, the pixel color information is extracted and is converted into a pixel information table represented by numbers, and the table is used as a standard reference table to be used as the comparison reference object; and 3) images of the inspected board cards in the same type are collected into the system, the pixel color information is extracted and is converted into a pixel information table represented by the numbers, the table is compared with the standard reference table, the result shows that the position of the board card to be compared is a doubtful point position when the number of unmatched pixel color information is greater than the image comparison sensitivity value sigma in the same position regions, and the unmatched position prompt of the corresponding board card is given.
Description
Technical field
The present invention relates to computer communication field; Specifically be to utilize a kind of integrated circuit board material method of inspection that detects based on image recognition; Solve big, the inefficient problem of part check labour intensity on the current integrated circuit board material, greatly improved accuracy, and promoted checkability part check on the material.
Background technology
Along with the client improves constantly what product quality required, the check of current server product is had higher requirement, especially pass through PCBA after, the check of integrated circuit board warehouse-in need drop into very big manpower and materials, strengthens the check of product; In the design of integrated circuit board; Have a lot of materials need be on integrated circuit board when PCBA part, these materials or be used for that the selection of function or the upgrading that is used for function are reserved or reservation of being used to reduce cost or the like must be strengthened the management and control that PCBA produces for this type of material; If the situation of part appears going up in the components and parts position of should not go up part of these reservations; Then immeasurable risk possibly occur, possibly cause the integrated circuit board dysfunction, can't work; Even cause the puncture of the part components and parts of integrated circuit board to be burnt, therefore in the ware-house-in inspection of carrying out the server system integrated circuit board, material correct goes up part and is one of extremely important factor that influences server security performance and reliability.
In integrated circuit board ware-house-in inspection before, mainly through the in fact part situation of checker's manual observation material, the last part with material requires to compare then; This mode needs one by one material, integrated circuit board is tested successively one by one, and when waiting to check integrated circuit board quantity big, the ware-house-in inspection time and the human cost of integrated circuit board become one of important indicator that influences launch; And the checker is in single material ratio for a long time to state; Labour intensity is big, and work efficiency also can descend to some extent, to above problem; Through analysing in depth, we have summed up a kind of integrated circuit board material method of inspection that detects based on image recognition.
Summary of the invention
The purpose of this invention is to provide a kind of integrated circuit board material method of inspection that detects based on image recognition.
The objective of the invention is to realize by following mode; The present invention is with image recognition processing theory support point; Utilize a kind of integrated circuit board material method of inspection that detects based on image recognition, solve big, the inefficient problem of part check labour intensity on the current integrated circuit board material, concrete steps are following: 1) according to integrated circuit board specification and upward part requirement; Select a standard integrated circuit board for use; Need confirm during part consistently with the standard integrated circuit board on its material, acquisition is repeatedly observed in choosing by manual work of this on-gauge plate, and this standard integrated circuit board is used as the standard of follow-up comparison;
2) IMAQ with the standard integrated circuit board enters system, and extracts pixel color information, converts the Pixel Information form that a numbered is represented into, with this form as the standard basis form, as the benchmark object of comparison;
The IMAQ of integrated circuit board of the same type that 3) will be to be checked enters system; And extraction pixel color information; Convert the Pixel Information form that a numbered is represented into; This form and standard basis form are compared, if in co-located region, the unmatched number of pixel color information is compared Sensitirity va1ue greater than image
σ, think that then this position of integrated circuit board to be compared is the doubtful point position, and provide the position indicating that do not match of corresponding integrated circuit board.
The IMAQ of standard integrated circuit board and integrated circuit board of the same type to be checked is entered system, need image capture device be comprised like the placement location of camera and integrated circuit board and fixing that IMAQ need adopt unified RP, to guarantee the validity of comparison;
, the integrated circuit board IMAQ is entered system, and extracts pixel color information, employing coloured image is converted into gray level image, and extract the gray-scale value of each position pixel, form the comparison form with this;
Image comparison Sensitirity va1ue
σ, set by checked operation person, when
σValue when less than normal, comparison is strictness partially, when
σValue when bigger than normal, comparison can wider pine, image comparison Sensitirity va1ue
σDensity of components decision by ambient light, integrated circuit board.
The invention has the beneficial effects as follows: we can carry out the check of part situation on system's integrated circuit board material very easily; Not only reached the requirement to the check accuracy, and saved the cost of check, the work that has reduced the reviewer is slight; Improve work efficiency, simplified inspection process.Thereby, have good value for applications.
Description of drawings
Fig. 1 is the inspection process figure of the inventive method.
Embodiment
Explanation at length below with reference to Figure of description method of the present invention being done.
The integrated circuit board material method of inspection that detects based on image recognition of the present invention, concrete steps are following:
A) checking engineering Shi Shouxian is according to integrated circuit board specification and upward part requirement; Select a standard integrated circuit board for use; Its material in fact part situation is confirmed consistently with last requirement, and acquisition is repeatedly observed in choosing by manual work of this on-gauge plate, with the standard form integrated circuit board of this integrated circuit board as follow-up comparison;
B) IMAQ with the standard integrated circuit board enters system, and extracts pixel color information, and dress is changed to the Pixel Information form that a numbered is represented, with this form as the standard basis form, as the benchmark object of comparison;
The IMAQ of integrated circuit board of the same type that c) will be to be checked enters system, and extracts pixel color information, and dress is changed to the Pixel Information form that a numbered is represented, this form and standard basis form are compared; If in two integrated circuit board co-located region, the unmatched number of pixel color information is greater than image comparison sensitivity setting value
σ, think that then this position of integrated circuit board to be compared is unmatched doubtful point position, and provide the position indicating that do not match of the corresponding integrated circuit board of checker;
Except that the described technical characterictic of instructions, be the known technology of those skilled in the art.
Claims (4)
1. integrated circuit board material method of inspection that detects based on image recognition, step is following:
1) according to the integrated circuit board specification and go up the part requirement, select a standard integrated circuit board for use, need confirm during part consistently on its material with the standard integrated circuit board, acquisition is repeatedly observed in choosing by manual work of this on-gauge plate, with the standard use of this standard integrated circuit board as follow-up comparison;
2) IMAQ with the standard integrated circuit board enters system, and extracts pixel color information, converts the Pixel Information form that a numbered is represented into, with this form as the standard basis form, as the benchmark object of comparison;
The IMAQ of integrated circuit board of the same type that 3) will be to be checked enters system; And extraction pixel color information; Convert the Pixel Information form that a numbered is represented into; This form and standard basis form are compared, if in co-located region, the unmatched number of pixel color information is compared Sensitirity va1ue greater than image
σ, think that then this position of integrated circuit board to be compared is the doubtful point position, and provide the position indicating that do not match of corresponding integrated circuit board.
2. method according to claim 1; It is characterized in that the IMAQ of standard integrated circuit board and integrated circuit board of the same type to be checked is entered system; Need image capture device be comprised like the placement location of camera and integrated circuit board and fixing; IMAQ need adopt unified RP, to guarantee the validity of comparison.
3. method according to claim 1 is characterized in that, the integrated circuit board IMAQ is entered system, and extracts pixel color information, employing coloured image is converted into gray level image, and extract the gray-scale value of each position pixel, form the comparison form with this.
4. method according to claim 1 is characterized in that, image comparison Sensitirity va1ue
σ, set by checked operation person, when
σValue when less than normal, comparison is strictness partially, when
σValue when bigger than normal, comparison can wider pine, image comparison Sensitirity va1ue
σDensity of components decision by ambient light, integrated circuit board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103601707A CN102519967A (en) | 2011-11-15 | 2011-11-15 | Board card material inspection method based on image identification detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103601707A CN102519967A (en) | 2011-11-15 | 2011-11-15 | Board card material inspection method based on image identification detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102519967A true CN102519967A (en) | 2012-06-27 |
Family
ID=46290957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103601707A Pending CN102519967A (en) | 2011-11-15 | 2011-11-15 | Board card material inspection method based on image identification detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102519967A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406984A (en) * | 2014-12-16 | 2015-03-11 | 浪潮电子信息产业股份有限公司 | Consistency image detection method of server mainboard material |
| CN105389587A (en) * | 2015-10-27 | 2016-03-09 | 深圳德诚信用咭制造有限公司 | Card face printing quality automatic detection device and method thereof |
| CN105550081A (en) * | 2015-12-07 | 2016-05-04 | 广州视源电子科技股份有限公司 | Board card error display method and system |
| CN106525876A (en) * | 2016-12-30 | 2017-03-22 | 杭州耕德电子有限公司 | Automatic missing die-cutting part detecting system and method |
| CN109858452A (en) * | 2019-02-15 | 2019-06-07 | 滨州建筑工程施工图审查中心 | Architectural drawing automatic comparison method and device |
| CN110132974A (en) * | 2018-02-08 | 2019-08-16 | 克朗斯股份公司 | The monitoring method and bottle washing machine of bottle unit |
| CN110632095A (en) * | 2019-09-27 | 2019-12-31 | 安徽广德威正光电科技有限公司 | PCB automatic check out system based on 5G uses |
| CN112633437A (en) * | 2020-07-23 | 2021-04-09 | 广元量知汇科技有限公司 | Supply chain management method based on industrial interconnection |
| CN113138191A (en) * | 2020-01-20 | 2021-07-20 | 邓涛 | System and method for analyzing name of detection object part |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58132649A (en) * | 1982-02-03 | 1983-08-08 | Nippon Abionikusu Kk | Automatic-inspecting device for printed plug board |
| CN1504742A (en) * | 2002-11-28 | 2004-06-16 | 威光机械工程股份有限公司 | Automatic optical detecting system for blemish assembly on printed circuit board |
| JP2005172584A (en) * | 2003-12-10 | 2005-06-30 | Shirai Denshi Kogyo Kk | Inspection method of printed matter, and its inspection apparatus |
| CN101825581A (en) * | 2010-04-16 | 2010-09-08 | 广东工业大学 | Model-based method for detecting PCB defects |
-
2011
- 2011-11-15 CN CN2011103601707A patent/CN102519967A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58132649A (en) * | 1982-02-03 | 1983-08-08 | Nippon Abionikusu Kk | Automatic-inspecting device for printed plug board |
| CN1504742A (en) * | 2002-11-28 | 2004-06-16 | 威光机械工程股份有限公司 | Automatic optical detecting system for blemish assembly on printed circuit board |
| JP2005172584A (en) * | 2003-12-10 | 2005-06-30 | Shirai Denshi Kogyo Kk | Inspection method of printed matter, and its inspection apparatus |
| CN101825581A (en) * | 2010-04-16 | 2010-09-08 | 广东工业大学 | Model-based method for detecting PCB defects |
Non-Patent Citations (1)
| Title |
|---|
| 高明阳: "电路板元件贴装缺陷视觉检测***", 《信息科技辑》, 15 May 2009 (2009-05-15) * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104406984A (en) * | 2014-12-16 | 2015-03-11 | 浪潮电子信息产业股份有限公司 | Consistency image detection method of server mainboard material |
| CN105389587A (en) * | 2015-10-27 | 2016-03-09 | 深圳德诚信用咭制造有限公司 | Card face printing quality automatic detection device and method thereof |
| CN105550081A (en) * | 2015-12-07 | 2016-05-04 | 广州视源电子科技股份有限公司 | Board card error display method and system |
| CN106525876A (en) * | 2016-12-30 | 2017-03-22 | 杭州耕德电子有限公司 | Automatic missing die-cutting part detecting system and method |
| CN110132974A (en) * | 2018-02-08 | 2019-08-16 | 克朗斯股份公司 | The monitoring method and bottle washing machine of bottle unit |
| CN109858452A (en) * | 2019-02-15 | 2019-06-07 | 滨州建筑工程施工图审查中心 | Architectural drawing automatic comparison method and device |
| CN110632095A (en) * | 2019-09-27 | 2019-12-31 | 安徽广德威正光电科技有限公司 | PCB automatic check out system based on 5G uses |
| CN113138191A (en) * | 2020-01-20 | 2021-07-20 | 邓涛 | System and method for analyzing name of detection object part |
| CN113138191B (en) * | 2020-01-20 | 2022-08-05 | 上海各瑟信息科技有限公司 | System and method for analyzing name of detection object part |
| CN112633437A (en) * | 2020-07-23 | 2021-04-09 | 广元量知汇科技有限公司 | Supply chain management method based on industrial interconnection |
| CN112633437B (en) * | 2020-07-23 | 2022-06-17 | 贵州酱酒智造供应链有限公司 | Supply chain management method based on industrial interconnection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102519967A (en) | Board card material inspection method based on image identification detection | |
| CN108365557B (en) | Method and system for fine routing inspection of power transmission line by unmanned aerial vehicle | |
| CN103294994B (en) | For the device of face is recognized based on environmental suitability | |
| CN111080598B (en) | Bolt and nut missing detection method for coupler yoke key safety crane | |
| CN103577817B (en) | Form recognition method and apparatus | |
| Ce | PCB defect detection USING OPENCV with image subtraction method | |
| CN103512762A (en) | Image processing method and device and train fault detection system | |
| JP4987826B2 (en) | Number plate recognition method and number plate recognition apparatus | |
| CN103365967B (en) | Automatic difference detection method and device based on crawler | |
| CN103955660A (en) | Method for recognizing batch two-dimension code images | |
| KR102384771B1 (en) | Method and apparatus for bubble detection in conformal coated PCB and computer readable recording medium thereof | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| US20130039563A1 (en) | Method of generating inspection program | |
| CN110346704A (en) | Determination method, apparatus, equipment and the storage medium of test file in board test | |
| CN104201130A (en) | Optical detection method for defect classification | |
| CN114943875A (en) | Visual analysis method for cable element identification | |
| CN108596115A (en) | A kind of vehicle checking method, apparatus and system based on convolutional neural networks | |
| CN201522724U (en) | Detonator safety tracking management device | |
| CN111259887B (en) | Intelligent quality inspection method, system and device for dumb resource equipment | |
| CN111460198B (en) | Picture timestamp auditing method and device | |
| CN116091503B (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
| JP7307918B2 (en) | Data processing device, data processing program and substrate group evaluation system | |
| CN116071335A (en) | Wall surface acceptance method, device, equipment and storage medium | |
| US11727673B1 (en) | Visual analysis method for cable element identification | |
| CN116580026A (en) | Automatic optical detection method, equipment and storage medium for appearance defects of precision parts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120627 |
|
| WD01 | Invention patent application deemed withdrawn after publication |