CN105243663A - automatic PCB (Printed Circuit Board) scan image matching method and system - Google Patents

automatic PCB (Printed Circuit Board) scan image matching method and system Download PDF

Info

Publication number
CN105243663A
CN105243663A CN201510633320.5A CN201510633320A CN105243663A CN 105243663 A CN105243663 A CN 105243663A CN 201510633320 A CN201510633320 A CN 201510633320A CN 105243663 A CN105243663 A CN 105243663A
Authority
CN
China
Prior art keywords
scan image
prime
coordinate
standard picture
image
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
CN201510633320.5A
Other languages
Chinese (zh)
Inventor
程涛
冯平
孙高磊
徐刚
彭小波
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.)
Shenzhen University
Original Assignee
Shenzhen University
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 Shenzhen University filed Critical Shenzhen University
Priority to CN201510633320.5A priority Critical patent/CN105243663A/en
Publication of CN105243663A publication Critical patent/CN105243663A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30141—Printed circuit board [PCB]

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The present invention is applicable to the field of image scanning and provides an automatic PCB scan image matching method. The method comprises: step A, extracting marking points of a PCB scan image and a standard image, and acquiring coordinates of the marking points; step B, according to the coordinates of the marking points on the standard image and the coordinates of the marking points in the same positions of the PCB scan image, determining a transform matrix K for transforming the standard image into the PCB scan image; and step C, transforming the standard image according to the transform matrix K to obtain a standard template image. According to the automatic matching method and system provided by the present invention, a space transformation relationship between two images is found out by adopting a bilinear transform algorithm according to corresponding relationships among the coordinates of the similar feature points of the PCB scan image and the corresponding standard image, thereby acquiring a standard image with the same size as the scan image for subsequent defect comparison; and no manual interference is required, matching points can be automatically found out and calculated, the obtained scan image is substantially not distorted, and the matching is relatively precise, so that a foundation is laid for subsequent defect identification.

Description

A kind of automatic matching method of PCB scan image and system
Technical field
The invention belongs to image scanning field, particularly relate to a kind of automatic matching method and system of PCB scan image.
Background technology
When adopting reference relative method to carry out defects detection to PCB bare board, require that PCB scan image to be measured and standard picture spatially must be aimed at completely, not so easily produce the defect of many wrong reports.But, owing to there is the factors such as PCB bare board edge to be measured fabrication error, worktable and camera shake, to gather and the PCB scan image to be measured spliced and standard picture there are differences on locus, can not complete matching.
Summary of the invention
Technical matters to be solved by this invention is the automatic matching method and the system that provide a kind of PCB scan image, and being intended to solve PCB scan image to be measured and standard picture can not the problem of complete matching.
The present invention is achieved in that a kind of automatic matching method of PCB scan image, comprises the following steps:
Steps A, extracts the gauge point of pcb board scan image and standard picture, obtains the coordinate of each gauge point;
Step B, according to the coordinate of the gauge point at same position place on the coordinate of gauge point each on standard picture and pcb board scan image, determines and is converted into transformation matrix K needed for pcb board scan image by standard picture;
Step C, carries out conversion according to described transformation matrix K by described standard picture and obtains standard form image.
The present invention compared with prior art, beneficial effect is: the present invention is according to the corresponding relation of PCB scan image with corresponding standard picture similar features point coordinate, adopt bilinear transformation algorithm to find out the space transforming relation of two width images, thus obtain the standard drawing large with scan image etc. and be used in the middle of subsequent defective contrasts.The present invention does not need Human disturbance, can automatically find out match point and calculate, the scan image obtained substantially undistorted, and coupling is comparatively accurate, for subsequent defective identification lays the foundation.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the automatic matching method of a kind of PCB scan image that the embodiment of the present invention provides.
Fig. 2 is the matching image of the same position feature point extraction template that the embodiment of the present invention provides.
Fig. 3 is the Matching Model of the scan image that provides of the embodiment of the present invention and standard picture.
Fig. 4 is the structural representation of the automatic patching system of a kind of PCB scan image that the embodiment of the present invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Need to carry out registration and Accurate align to scan image and standard picture before defect recognition; the stage is manufactured and designed at circuit-board processes; deviser can arrange the localization criteria that specific witness marker cuts as follow-up components and parts welding and PCB usually on PCB; on four angles of PCB effective information, such as respectively do " L " type mark mark; as location Mark point; i.e. gauge point, every block PCB has identical effective information in the region of four corner " L " type institute frames.Based on this kind of feature, the present invention extracts the coordinate on the gauge point of PCB scan image to be measured and standard picture four same positions, then adopts the method for bilinear transformation to carry out two width image registrations.
The automatic matching method of a kind of PCB scan image that Fig. 1 provides for the embodiment of the present invention, concrete steps comprise:
S1. extract the gauge point of pcb board scan image and standard picture, obtain the coordinate of each gauge point.In this step, when extracting the coordinate position of described standard picture and scan image 4 gauge points separately, all adopt the method (as shown in Figure 2, a is intercepting region, the standard picture upper left corner, and b is template image) of template matches.Template image (namely possessing the area image of unique point) is carried out translation gliding by the essence of coupling exactly on large image (i.e. PCB scan image and standard picture), find in large image and exist and the same or analogous region of template image, if this region exists, then extract this region, determine its position, finally determine the position of template image in large image, and obtain the coordinate position of described standard picture four gauge points corresponding with on scan image.
S2. determine that standard picture is converted into the transformation matrix K needed for pcb board scan image according to described coordinate.Owing to can not aim at completely between described standard picture and scan image; certain anglec of rotation and side-play amount is there is between them; therefore; need with the volume coordinate of a certain width figure for benchmark; the coordinate of another piece image is transformed in benchmark by certain spatial transform relation and goes, usually can relate in this conversion process and image to be transformed be rotated and the operation such as stretching.
In step s 2, the PCB scan image carrying out registration as required sets up simplified model with corresponding standard picture, as shown in Figure 3, c is PCB standard picture model, and d is PCB scan image model, the interior angle point (little red circle) getting " L " shape (yellow right angle) in Mark region, four corners (red dotted line frame) corresponding in figure is respectively unique point, with A, B, C, D represents the described coordinate of described standard picture, and it is expressed as: A (X a, Y a), B (X b, Y b), C (X c, Y c), D (X d, Y d); Represent the described coordinate of the described same position unique point of described scan image with A', B', C', D', it is expressed as: A'(X' a, Y' a), B'(X' b, Y' b), C'(X' c, Y' c), D'(X' d, Y' d);
According to the coordinate of the four pairs of Feature point correspondence found, the method for bilinear transformation (the method includes rotation and stretching conversion) is adopted to find out the locus transformation relation of described scan image and standard picture, i.e. transformation matrix K:
X a Y a X a Y a 1 X b Y b X b Y b 1 X c Y c X c Y c 1 X d Y d X d Y d 1 K 11 K 12 K 21 K 22 K 31 K 32 K 41 K 42 = X a ′ Y a ′ X b ′ Y b ′ X c ′ Y c ′ X d ′ Y d ′ - - - ( 1 )
According to above formula (1), obtain conversion and put to the proof K, make:
[X'Y']＝[XYXY1]×K---(2)；
Step S3, carries out conversion according to described transformation matrix K by described standard picture and obtains standard form image.In this step, according to above-mentioned formula (2), the pixel space coordinate conversion of described standard picture, in the coordinate system of described scan image, obtains the standard form image of the same size with described scan image.Only registration need be carried out to first piece of PCB for a collection of PCB, guarantee that standard picture is consistent with scan image, realize accurately location, afterwards, this batch of pcb board is scanned, the scan image of each the block plate obtained passes to follow-up defect recognition module together with the described standard form figure after this registration, carries out defects detection.
The automatic patching system of a kind of PCB scan image that Fig. 4 provides for the embodiment of the present invention, comprising:
Coordinate extraction unit 1, for extracting the gauge point of pcb board scan image and standard picture, obtain the coordinate of a gauge point, what adopt in the process extracting gauge point is template matching method;
Transformation matrix determining unit 2, according to the coordinate of the gauge point at same position place on the coordinate of gauge point each on standard picture and pcb board scan image, determine and be converted into transformation matrix K needed for pcb board scan image by standard picture, concrete steps are:
Represent the described coordinate of described standard picture with A, B, C, D, it is expressed as: A (X a, Y a), B (X b, Y b), C (X c, Y c), D (X d, Y d); Represent the described coordinate of the described same position unique point of described scan image with A', B', C', D', it is expressed as: A'(X' a, Y' a), B'(X' b, Y' b), C'(X' c, Y' c), D'(X' d, Y' d);
According to described coordinate, bilinear transformation is adopted to find out the locus transformation relation of described simplification scan image and described simplification standard picture, i.e. transformation matrix K:
X a Y a X a Y a 1 X b Y b X b Y b 1 X c Y c X c Y c 1 X d Y d X d Y d 1 K 11 K 12 K 21 K 22 K 31 K 32 K 41 K 42 = X a ′ Y a ′ X b ′ Y b ′ X c ′ Y c ′ X d ′ Y d ′ - - - ( 3 )
According to above formula (3), obtain conversion and put to the proof K, make:
[X'Y']＝[XYXY1]×K---(4)；
Matching unit 3, obtains standard form image for described standard picture being carried out conversion according to described transformation matrix K.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.

Claims (6)

1. an automatic matching method for PCB scan image, is characterized in that, comprises the following steps:
Steps A, extracts the gauge point of pcb board scan image and standard picture, obtains the coordinate of each gauge point;
Step B, according to the coordinate of the gauge point at same position place on the coordinate of gauge point each on standard picture and pcb board scan image, determines and is converted into transformation matrix K needed for pcb board scan image by standard picture;
Step C, carries out conversion according to described transformation matrix K by described standard picture and obtains standard form image.
2. the automatic matching method of PCB scan image as claimed in claim 1, is characterized in that, adopts template matching method to extract the gauge point of pcb board scan image and standard picture in described steps A.
3. the automatic matching method of PCB scan image as claimed in claim 1, is characterized in that, in stepb:
Represent the described coordinate of described standard picture with A, B, C, D, it is expressed as: A (X a, Y a), B (X b, Y b), C (X c, Y c), D (X d, Y d); Represent the described coordinate of the described same position unique point of described scan image with A', B', C', D', it is expressed as: A'(X' a, Y' a), B'(X' b, Y' b), C'(X' c, Y' c), D'(X' d, Y' d);
According to described coordinate, bilinear transformation is adopted to find out the locus transformation relation of described simplification scan image and described simplification standard picture, i.e. transformation matrix K:
X a Y a X a Y a 1 X b Y b X b Y b 1 X c Y c X c Y c 1 X d Y d X d Y d 1 K 11 K 12 K 21 K 22 K 31 K 32 K 41 K 42 = X a ′ Y a ′ X b ′ Y b ′ X c ′ Y c ′ X d ′ Y d ′ - - - ( 1 )
According to above formula (1), obtain transformation matrix K, make:
[X'Y']＝[XYXY1]×K。
4. an automatic patching system for PCB scan image, is characterized in that, comprising:
Coordinate extraction unit, for extracting the gauge point of pcb board scan image and standard picture, obtains the coordinate of each gauge point;
Transformation matrix determining unit, according to the coordinate of the gauge point at same position place on the coordinate of gauge point each on standard picture and pcb board scan image, determines and is converted into transformation matrix K needed for pcb board scan image by standard picture;
Matching unit, obtains standard form image for described standard picture being carried out conversion according to described transformation matrix K.
5. automatic patching system as claimed in claim 4, is characterized in that, described coordinate extraction unit adopts template matching method to extract the same position unique point of pcb board scan image and standard picture.
6. automatic patching system as claimed in claim 4, is characterized in that, described transformation matrix determining unit specifically for:
Represent the described coordinate of described standard picture with A, B, C, D, it is expressed as: A (X a, Y a), B (X b, Y b), C (X c, Y c), D (X d, Y d); Represent the described coordinate of the described same position unique point of described scan image with A', B', C', D', it is expressed as: A'(X' a, Y' a), B'(X' b, Y' b), C'(X' c, Y' c), D'(X' d, Y' d);
According to described coordinate, bilinear transformation is adopted to find out the locus transformation relation of described simplification scan image and described simplification standard picture, i.e. transformation matrix K:
X a Y a X a Y a 1 X b Y b X b Y b 1 X c Y c X c Y c 1 X d Y d X d Y d 1 K 11 K 12 K 21 K 22 K 31 K 32 K 41 K 42 = X a ′ Y a ′ X b ′ Y b ′ X c ′ Y c ′ X d ′ Y d ′ - - - ( 2 )
According to above formula (2), obtain transformation matrix K, make:
[X'Y']＝[XYXY1]×K。
CN201510633320.5A 2015-09-29 2015-09-29 automatic PCB (Printed Circuit Board) scan image matching method and system Pending CN105243663A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510633320.5A CN105243663A (en) 2015-09-29 2015-09-29 automatic PCB (Printed Circuit Board) scan image matching method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510633320.5A CN105243663A (en) 2015-09-29 2015-09-29 automatic PCB (Printed Circuit Board) scan image matching method and system

Publications (1)

Publication Number Publication Date
CN105243663A true CN105243663A (en) 2016-01-13

Family

ID=55041295

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510633320.5A Pending CN105243663A (en) 2015-09-29 2015-09-29 automatic PCB (Printed Circuit Board) scan image matching method and system

Country Status (1)

Country Link
CN (1) CN105243663A (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106778730A (en) * 2016-12-29 2017-05-31 深圳爱拼信息科技有限公司 A kind of adaptive approach and system for quickly generating OCR training samples
WO2017193596A1 (en) * 2016-05-13 2017-11-16 广州视源电子科技股份有限公司 Image matching method and system for printed circuit board
CN107392903A (en) * 2017-07-25 2017-11-24 魏延福 PCB line acquisition methods, obtain system and the method for maintenance
CN107944494A (en) * 2017-11-30 2018-04-20 华中科技大学 A kind of Mark point visual identitys and localization method based on not bending moment
CN108387591A (en) * 2017-12-29 2018-08-10 苏州通富超威半导体有限公司 A kind of failure analysis method and its equipment of semiconductor devices
CN108416773A (en) * 2018-03-08 2018-08-17 凌云光技术集团有限责任公司 A kind of the PCB aperture method of inspection and system of the over-determined systems based on registration point
CN108648173A (en) * 2018-03-30 2018-10-12 湖北工程学院 It is merged facial mask method for correcting position and device
CN110443777A (en) * 2018-10-09 2019-11-12 广东仙童智能机器人科技有限公司 A kind of PCB image alignment method, device and computer storage medium
CN112085709A (en) * 2020-08-19 2020-12-15 浙江华睿科技有限公司 Image contrast method and equipment
CN113920117A (en) * 2021-12-14 2022-01-11 成都数联云算科技有限公司 Panel defect area detection method and device, electronic equipment and storage medium
CN117347367A (en) * 2023-08-24 2024-01-05 广州鹰视信息科技有限公司 Board card device positioning method, board card device detection method, device and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101339656A (en) * 2008-08-29 2009-01-07 中国电子科技集团公司第四十五研究所 Image processing process of full-automatic lead wire bonding machine image processing system
CN101833644A (en) * 2010-06-01 2010-09-15 福建新大陆电脑股份有限公司 Correction graph searching method based on dynamic template
CN102184560A (en) * 2011-03-25 2011-09-14 南昌航空大学 Template-based CCD-DR (charge coupled device-digital radiography) image splicing method
CN102567724A (en) * 2010-12-11 2012-07-11 鸿富锦精密工业（深圳）有限公司 Image correction system and method
CN103198035A (en) * 2013-02-28 2013-07-10 北京优纳科技有限公司 Position alignment method and position alignment system
CN103593663A (en) * 2013-09-27 2014-02-19 北京中钞钞券设计制版有限公司 Image positioning method of banknote printing plate

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101339656A (en) * 2008-08-29 2009-01-07 中国电子科技集团公司第四十五研究所 Image processing process of full-automatic lead wire bonding machine image processing system
CN101833644A (en) * 2010-06-01 2010-09-15 福建新大陆电脑股份有限公司 Correction graph searching method based on dynamic template
CN102567724A (en) * 2010-12-11 2012-07-11 鸿富锦精密工业（深圳）有限公司 Image correction system and method
CN102184560A (en) * 2011-03-25 2011-09-14 南昌航空大学 Template-based CCD-DR (charge coupled device-digital radiography) image splicing method
CN103198035A (en) * 2013-02-28 2013-07-10 北京优纳科技有限公司 Position alignment method and position alignment system
CN103593663A (en) * 2013-09-27 2014-02-19 北京中钞钞券设计制版有限公司 Image positioning method of banknote printing plate

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
A.D.VENTURA等: "Image registration by recognition of corresponding structures", 《IEEE TRANS.ON GEOSCIENCE AND REMOTE SENSING》 *
尚明姝等: "一种基于特征的全自动图像拼接算法", 《微计算机应用》 *
金士玲: "无人机可见光图像拼接算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017193596A1 (en) * 2016-05-13 2017-11-16 广州视源电子科技股份有限公司 Image matching method and system for printed circuit board
CN106778730A (en) * 2016-12-29 2017-05-31 深圳爱拼信息科技有限公司 A kind of adaptive approach and system for quickly generating OCR training samples
CN106778730B (en) * 2016-12-29 2020-07-07 深圳爱拼信息科技有限公司 Self-adaptive method and system for rapidly generating OCR training samples
CN107392903A (en) * 2017-07-25 2017-11-24 魏延福 PCB line acquisition methods, obtain system and the method for maintenance
WO2019019498A1 (en) * 2017-07-25 2019-01-31 深圳砾盈科技发展有限责任公司 Pcb line acquisition method, acquisition system and maintenance method
CN107944494B (en) * 2017-11-30 2020-09-18 华中科技大学 Mark point visual identification and positioning method based on invariant moment
CN107944494A (en) * 2017-11-30 2018-04-20 华中科技大学 A kind of Mark point visual identitys and localization method based on not bending moment
CN108387591A (en) * 2017-12-29 2018-08-10 苏州通富超威半导体有限公司 A kind of failure analysis method and its equipment of semiconductor devices
CN108416773A (en) * 2018-03-08 2018-08-17 凌云光技术集团有限责任公司 A kind of the PCB aperture method of inspection and system of the over-determined systems based on registration point
CN108648173A (en) * 2018-03-30 2018-10-12 湖北工程学院 It is merged facial mask method for correcting position and device
CN110443777A (en) * 2018-10-09 2019-11-12 广东仙童智能机器人科技有限公司 A kind of PCB image alignment method, device and computer storage medium
CN110443777B (en) * 2018-10-09 2023-03-10 广东仙童智能机器人科技有限公司 PCB image alignment method and device and computer storage medium
CN112085709A (en) * 2020-08-19 2020-12-15 浙江华睿科技有限公司 Image contrast method and equipment
CN112085709B (en) * 2020-08-19 2024-03-22 浙江华睿科技股份有限公司 Image comparison method and device
CN113920117A (en) * 2021-12-14 2022-01-11 成都数联云算科技有限公司 Panel defect area detection method and device, electronic equipment and storage medium
CN117347367A (en) * 2023-08-24 2024-01-05 广州鹰视信息科技有限公司 Board card device positioning method, board card device detection method, device and medium

Similar Documents

Publication Publication Date Title
CN105243663A (en) automatic PCB (Printed Circuit Board) scan image matching method and system
JP4681856B2 (en) Camera calibration method and camera calibration apparatus
WO2017092631A1 (en) Image distortion correction method for fisheye image, and calibration method for fisheye camera
US20200105012A1 (en) A non-contact visual detection method for mark positioning of mobile phone touch screen
JP2008014940A (en) Camera calibration method for camera measurement of planar subject and measuring device applying same
CN104766292A (en) Method and system for calibrating multiple stereo cameras
WO2014045508A1 (en) Inspection device, inspection method, and inspection program
JP2011238228A (en) Screen area detection method and system
CN102609941A (en) Three-dimensional registering method based on ToF (Time-of-Flight) depth camera
KR20190051463A (en) Apparatus and method for detecting checkerboard corner point for camera calibration
CN104552341A (en) Single-point multi-view meter-hanging posture error detecting method of mobile industrial robot
CN113744336A (en) Auxiliary positioning method and device and computer readable storage medium
CN113538583A (en) Method for accurately positioning position of workpiece on machine tool and vision system
CN107590495A (en) Answer sheet picture method for correcting error, device, readable storage medium storing program for executing and electronic equipment
CN106093055B (en) Quality detection method for plural films
CN102446355A (en) Method for detecting target protruding from plane based on double viewing fields without calibration
CN104423142B (en) Calibration data collection method and system for optical proximity correction model
CN103778607A (en) Image correction method
CN105856241B (en) A kind of difference scale electronic liquid crystal display positioning grasping means
CN106488204B (en) Have the depth camera of self-aligning and self-aligning method
CN116563391B (en) Automatic laser structure calibration method based on machine vision
CN103177416B (en) A kind of QR code image position method based on least square method
CN111784779A (en) Checkerboard image recognition and positioning system and method based on convolutional neural network and nested contour recognition
CN112648920A (en) Mask opening size measuring method, mask plate stretching device and screen expanding machine
TW202007956A (en) Projection type auxiliary system for assisting a printed circuit board to quickly locate a target and enable enlarged observation at a fixed point allowing the operator to move a printed circuit board to match the positioning image

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: 20160113