CN110838135A - PCB bare board image registration method - Google Patents

PCB bare board image registration method Download PDF

Info

Publication number
CN110838135A
CN110838135A CN201911056182.3A CN201911056182A CN110838135A CN 110838135 A CN110838135 A CN 110838135A CN 201911056182 A CN201911056182 A CN 201911056182A CN 110838135 A CN110838135 A CN 110838135A
Authority
CN
China
Prior art keywords
image
registered
bare board
processed
pcb
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
CN201911056182.3A
Other languages
Chinese (zh)
Inventor
周志峰
张怡
周坤
朱姿娜
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.)
Shanghai University of Engineering Science
Shanghai Institute of Space Power Sources
Original Assignee
Shanghai University of Engineering Science
Shanghai Institute of Space Power Sources
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 Shanghai University of Engineering Science, Shanghai Institute of Space Power Sources filed Critical Shanghai University of Engineering Science
Priority to CN201911056182.3A priority Critical patent/CN110838135A/en
Publication of CN110838135A publication Critical patent/CN110838135A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details
    • G06T2207/20192—Edge enhancement; Edge preservation
    • 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)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a PCB bare board image registration method, which comprises the following steps: step S1: obtaining a PCB bare board image and a template image to be registered; step S2: preprocessing and detecting an edge connected domain of a PCB bare board image to be registered, and preprocessing and detecting an edge connected domain of the template image to obtain a processed PCB bare board image to be registered and a processed template image; step S3: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain a homography matrix of the template image; step S4: and performing affine transformation on the PCB bare board image to be registered based on the homography matrix to obtain the registered PCB bare board image. Compared with the prior art, the calculation amount of Hough transformation is reduced, the registration precision is improved, and no requirement is made on the datum point of the PCB bare board to be registered.

Description

PCB bare board image registration method
Technical Field
The invention relates to the field of PCB bare board detection, in particular to a PCB bare board image registration method.
Background
A printed circuit board (also referred to as PCB) is a provider of electrical connection of electronic components, and is a key component of various electronic products, and the performance of the printed circuit board directly affects the service life of the electronic products. The development of bare PCB boards has been over 100 years old, and the main advantages of the bare PCB boards are that the errors of wiring and assembly are greatly reduced, and the automation level and the production efficiency are improved. The PCB bare board is developed from a single-layer board to a double-sided board, a multi-layer board and a flexible board, and is continuously developed towards high precision, high density and high reliability, the volume is continuously reduced, the cost is reduced, and the performance is improved.
At present, a PCB bare board image registration method with high accuracy and small calculation amount is lacked.
Disclosure of Invention
The present invention is directed to a method for aligning images of a bare PCB, which overcomes the above-mentioned drawbacks of the prior art.
The purpose of the invention can be realized by the following technical scheme:
a PCB bare board image registration method comprises the following steps:
step S1: obtaining a PCB bare board image and a template image to be registered;
step S2: preprocessing and detecting an edge connected domain of a PCB bare board image to be registered, and preprocessing and detecting an edge connected domain of the template image to obtain a processed PCB bare board image to be registered and a processed template image;
step S3: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain a homography matrix of the template image;
step S4: and performing affine transformation on the PCB bare board image to be registered based on the homography matrix to obtain the registered PCB bare board image.
The preprocessing comprises median filtering, binarization, edge extraction and closing operation.
And the edge connected domain detection eliminates a small-area region through an empirically set connected domain value.
The step S3 includes:
step S31: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain vertex coordinates (x ', y') of the processed PCB bare board image to be registered, corresponding vertex coordinates (x, y) of the processed template image and a rotation angle theta;
step S32: obtaining translation quantity through a conversion formula based on the vertex coordinates (x ', y') of the processed bare PCB image to be registered, the vertex coordinates (x, y) corresponding to the processed template image and the rotation angle theta;
step S33: and obtaining a homography matrix of the template image based on the translation amount and the rotation angle theta.
The step S31 includes:
step S311: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image;
step S312: fitting the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image respectively to obtain the longest fitting line segment of the processed PCB bare board image to be registered and the longest fitting line segment of the processed template image;
step S313: and obtaining the vertex coordinates (x ', y') of the processed bare PCB image to be registered, the corresponding vertex coordinates (x, y) of the processed template image and the rotation angle theta based on the longest fitting line segment of the processed bare PCB image to be registered and the longest fitting line segment of the processed template image.
The conversion formula is as follows:
x＝x'×cos(-θ)-y'×sin(-θ)+Tx
y＝x'×sin(-θ)+y'×cos(-θ)+Ty
wherein, Tx,TyAre respectively horizontal andthe amount of translation in the vertical direction.
The homography matrix A is as follows:
Figure BDA0002256611870000021
and the PCB bare board image to be registered is obtained through a CCD camera.
Compared with the prior art, the invention has the following advantages:
(1) edge connected domain detection is carried out on the PCB bare board image and the template image to be registered, a small area region is removed through connected domain values set by experience, the calculation amount of Hough transformation is reduced, and the calculation speed is improved.
(2) The PCB bare board image to be registered after processing and the template image after processing are subjected to integral Hough transformation, the complex process of the traditional local Hough transformation is avoided, the calculation amount of the Hough transformation is reduced, and the calculation speed is improved.
(3) The registration is carried out by utilizing the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image, more characteristic information can be obtained, the position transformation of the whole image can be represented sufficiently, the registration precision is improved, and no requirement is provided for the datum point of the PCB bare board to be registered.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of an image capturing device for a PCB bare board to be registered according to the present invention;
FIG. 3 is a graph comparing the results of the present invention;
reference numerals:
1 is a CCD camera; 2 is a lens; 3 is a ring light source; 4 is a strut; 6 is an operation table; 7 is a camera fixing bracket; 8 is a light source fixing bracket; and 9 is a pillar flange plate.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
The embodiment provides a method for registering images of a bare PCB, which, as shown in fig. 1, includes the following steps:
step S1: obtaining a PCB bare board image and a template image to be registered;
step S2: preprocessing and detecting an edge connected domain of a PCB bare board image to be registered, and preprocessing and detecting an edge connected domain of the template image to obtain a processed PCB bare board image to be registered and a processed template image;
step S3: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain a homography matrix of the template image;
step S4: and performing affine transformation on the PCB bare board image to be registered based on the homography matrix to obtain the registered PCB bare board image.
Specifically, the method comprises the following steps:
in step S1, the to-be-registered PCB bare board image can be obtained by photographing the to-be-registered PCB bare board with the CCD camera 1, the resolution of the to-be-registered PCB bare board image obtained by photographing with the CCD camera 1 is very high, and the picture pixels can reach tens of millions.
In steps S2 and S3, the main purpose of the preprocessing is to remove useless information from the image, reduce the complexity of the image, highlight the basic features of holes, lines, pads, etc. of the PCB board, and facilitate the analysis and processing by the computer. The pretreatment comprises the following steps: median filtering, binarization, edge extraction and closing operation.
The median filtering is a statistical sorting filtering, and the idea is that all pixels in a certain field are sorted from small to large, the pixel values are compared, the median value is taken out and used as the value of the central pixel in the field, and isolated noise points are eliminated. The acquired image usually contains noise, so-called image noise, which refers to random interference signals received by the image when the image is captured or transmitted. The median filtering is a classic noise smoothing method, has a good effect on eliminating salt and pepper noise, and can be used for protecting image edge information.
The binarization of the image is to set the gray value of a pixel point on the image to be 0 or 255, that is, the whole image has an obvious visual effect of only black and white.
The edge detection method comprises the steps of firstly, highlighting a local edge in an image by using an edge enhancement operator, defining the edge as a region boundary with the rapid change of the gray level in the image, and extracting an edge point set by a method of setting a threshold value. The monitored boundary may widen or break at some point due to the presence of noise and ambiguity. Thus, boundary detection includes two basic contents: 1) and extracting an edge point set reflecting the gray level change by using an edge operator. 2) And removing some boundary points or filling boundary discontinuous points in the edge point set, and connecting the edges into a complete line.
And performing morphological closed operation, namely expanding and corroding. Dilation expands components of an image and erosion shrinks components of an image. The effect of dilation is to expand the edges of the target image, so that neighboring pixels are engulfed by a larger set of boundary pixels. The closing operation smoothes a portion of the contour, closing narrow discontinuities and elongated ravines, eliminating small holes, and filling up breaks in the contour. The corrosion processing effect is to remove some pixels with low correlation degree at the object boundary, and in the image processing of the PCB bare board, the interference line edge spots can be properly eliminated, and the binary image contour of the PCB bare board after the closed operation is more vivid.
The good reliability and robustness of the Hough transformation are significant advantages in practical application, the effect of extracting straight lines in an image is good, but after the Hough transformation is mapped to a parameter space in an image space, each point in the parameter space is detected and accumulated by an accumulator, the calculation amount is huge, so that the Hough transformation needs a large amount of storage space during application, and the disadvantage of the Hough transformation is the maximum. Improving the efficiency of Hough transform requires reducing the number of points and the dimension of the accumulator array as much as possible on the basis of the traditional Hough transform. Therefore, on the basis of the traditional Hough transformation, a method for detecting an edge connected domain and setting a connected domain value according to experience is provided, the number of points participating in Hough transformation is reduced, a small-area region (which refers to a part with a smaller connected domain and can be restored) is eliminated by using the experience set connected domain value, the edge connected domain detection is carried out on the preprocessed PCB bare board image to be registered and the preprocessed template image to obtain the preprocessed PCB bare board image to be registered and the preprocessed template image, the Hough transformation is carried out on the preprocessed PCB bare board image to be registered and the preprocessed template image, the small-area region cannot participate in the extraction of straight line information, and the accuracy and the efficiency of the extraction of the straight line information of the PCB board image in a complex scene can be remarkably improved.
Step S3 includes:
step S31: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain vertex coordinates (x ', y') of the processed PCB bare board image to be registered, corresponding vertex coordinates (x, y) of the processed template image and a rotation angle theta, wherein the vertex is any one of four vertexes of the processed PCB bare board image to be registered;
step S32: obtaining translation quantity through a conversion formula based on the vertex coordinates (x ', y') of the processed bare PCB image to be registered, the vertex coordinates (x, y) corresponding to the processed template image and the rotation angle theta;
step S33: and obtaining a homography matrix of the template image based on the translation amount and the rotation angle theta.
In the embodiment, the Hough transformation is the integral Hough transformation, so that the complicated process of the traditional local Hough transformation is avoided, the calculation amount of the Hough transformation is reduced, and the calculation speed is improved; the conditions for integral Hough transformation are that the size of the PCB bare board image to be registered and the size of the template image are moderate, the PCB bare board image to be registered and the template image to be registered are obtained under good illumination conditions, and the PCB bare board image to be registered and the template image are not distorted.
In order to shorten the time consumed by Hough transformation, a straight line at the edge of a PCB is the longest line segment in an image, the Hough transformation is utilized to detect the longest line segment of a PCB bare board image to be registered after processing and the longest line segment of a template image after processing, the longest line segment of the PCB bare board image to be registered after processing and the longest line segment of the template image after processing are respectively fitted to obtain the longest fitting line segment of the PCB bare board image to be registered after processing and the longest fitting line segment of the template image after processing, and the rotation angle theta of the PCB bare board image to be registered is obtained according to the slopes of the longest fitting line segment of the PCB bare board image to be registered after processing and the longest fitting line segment of the template image after processing; obtaining vertex coordinates (x ', y') of the processed bare PCB image to be registered and vertex coordinates (x, y), (x ', y') and (x, y) corresponding to the processed template image based on the longest fitting line segment of the processed bare PCB image to be registered and the longest fitting line segment of the processed template image, directly obtaining the vertex coordinates (x ', y') and the vertex coordinates (x, y), (x ', y') and (x, y) through a computer graphic interface, and obtaining the vertex coordinates by calculating a fitting line segment perpendicular to the longest fitting line segment and then calculating an intersection point.
Obtaining the translation amount of the PCB in the image to be registered by a conversion formula of a preset formula, wherein the conversion formula is as follows:
x＝x'×cos(-θ)-y'×sin(-θ)+Tx
y＝x'×sin(-θ)+y'×cos(-θ)+Ty
wherein, Tx,TyThe amount of translation in the horizontal and vertical directions, respectively.
And recovering the small-area of the PCB bare board image to be registered and the template image deletion.
In step S4, the homography is the mapping from one plane to another plane, and the homography matrix can represent the affine transformation relationship between two pictures.
The homography matrix A is:
secondly, the embodiment further provides an image obtaining device for a bare PCB to be registered, as shown in fig. 2.
The device for acquiring the PCB bare board image to be registered comprises a CCD camera 1, a lens 2, an annular light source 3, a support column 4, a PCB to be detected, an operating platform 6, a camera fixing support 7, a light source fixing support 8 and a support column flange 9. The CCD camera 1 is connected to the camera fixing bracket 7 through a screw; the lens 2 is installed on the CCD camera 1 through threads; the annular light source 3 is connected to the light source fixing bracket 8 through a screw; the camera fixing bracket 7 and the light source fixing bracket 8 are connected to the support 4 through screws; the support 4 is connected to a support flange 9 through a set screw; placing the PCB bare board to be registered on the operation table 6; the operation table 6 is a support table of the entire apparatus.
Specifically, the method comprises the following steps:
a CCD is a semiconductor device capable of converting an optical image into a digital signal; the CCD acts like a film, but it converts image pixels into digital signals; the lens 2 mainly functions to focus an optical image of a target on a photosensitive area array of an image sensor, all image information is obtained through the lens 2 in a machine vision system, and the lens 2 generally consists of a plurality of lenses, a variable diaphragm and a focusing ring; the operation table 6 is placed on a stable horizontal table.
The annular light source 3 is an annular RGB light source, LEDs are arranged on the annular substrate in a high density mode, light rays of the LEDs are mainly concentrated on the central portion formed by the annular substrate, and therefore the collected pictures of the PCB bare board can have good illumination conditions.
The centers of the CCD camera 1, the lens 2 and the annular light source 3 are perpendicular to a PCB to be detected as much as possible, so that the acquired image is free of distortion.
And placing the PCB bare board to be registered on the operation table 6, adjusting the camera fixing support 7 and the light source fixing support 8, finding a proper position, fixing the camera fixing support 7 and the light source fixing support 8, and adjusting the lens 2 and the illumination brightness to obtain a clear PCB picture.
Fig. 3 is a comparison graph of the results of the method of the present embodiment, and it can be seen that the method of the present embodiment has a smaller amount of calculation, a faster calculation speed, and a higher accuracy compared to the conventional method.
According to the PCB bare board image registration method provided by the embodiment, the edge connected domain detection is carried out on the PCB bare board image to be registered and the template image, and a small area region is removed through the connected domain value set by experience, so that the calculation amount of Hough transformation is reduced, and the calculation speed is improved; the processed PCB bare board image to be registered and the processed template image are subjected to integral Hough transformation, so that the complicated process of the traditional local Hough transformation is avoided, the calculation amount of the Hough transformation is reduced, and the calculation speed is improved; the registration is carried out by utilizing the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image, more characteristic information can be obtained, the position transformation of the whole image can be represented sufficiently, the registration precision is improved, and no requirement is provided for the datum point of the PCB bare board to be registered.

Claims (8)

1. A PCB bare board image registration method is characterized by comprising the following steps:
step S1: obtaining a PCB bare board image and a template image to be registered;
step S2: preprocessing and detecting an edge connected domain of a PCB bare board image to be registered, and preprocessing and detecting an edge connected domain of the template image to obtain a processed PCB bare board image to be registered and a processed template image;
step S3: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain a homography matrix of the template image;
step S4: and performing affine transformation on the PCB bare board image to be registered based on the homography matrix to obtain the registered PCB bare board image.
2. The PCB bare board image registration method of claim 1, wherein the preprocessing comprises median filtering, binarization, edge extraction and closing operations.
3. The PCB bare board image registration method of claim 1, wherein in the edge connected domain detection, a small area region is eliminated through an empirically set connected domain value.
4. The PCB bare board image registration method according to claim 1, wherein the step S3 comprises:
step S31: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain vertex coordinates (x ', y') of the processed PCB bare board image to be registered, corresponding vertex coordinates (x, y) of the processed template image and a rotation angle theta;
step S32: obtaining translation quantity through a conversion formula based on the vertex coordinates (x ', y') of the processed bare PCB image to be registered, the vertex coordinates (x, y) corresponding to the processed template image and the rotation angle theta;
step S33: and obtaining a homography matrix of the template image based on the translation amount and the rotation angle theta.
5. The PCB bare board image registration method of claim 4, wherein the step S31 comprises:
step S311: carrying out integral Hough transformation on the processed PCB bare board image to be registered and the processed template image to obtain the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image;
step S312: fitting the longest line segment of the processed PCB bare board image to be registered and the longest line segment of the processed template image respectively to obtain the longest fitting line segment of the processed PCB bare board image to be registered and the longest fitting line segment of the processed template image;
step S313: and obtaining the vertex coordinates (x ', y') of the processed bare PCB image to be registered, the corresponding vertex coordinates (x, y) of the processed template image and the rotation angle theta based on the longest fitting line segment of the processed bare PCB image to be registered and the longest fitting line segment of the processed template image.
6. The PCB bare board image registration method of claim 4, wherein the conversion formula is:
x＝x'×cos(-θ)-y'×sin(-θ)+Tx
y＝x'×sin(-θ)+y'×cos(-θ)+Ty
wherein, Tx,TyThe amount of translation in the horizontal and vertical directions, respectively.
7. The PCB bare board image registration method of claim 6, wherein the homography matrix A is:
Figure FDA0002256611860000021
8. the PCB bare board image registration method according to claim 1, wherein the PCB bare board image to be registered is obtained by a CCD camera (1).
CN201911056182.3A 2019-10-31 2019-10-31 PCB bare board image registration method Pending CN110838135A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911056182.3A CN110838135A (en) 2019-10-31 2019-10-31 PCB bare board image registration method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911056182.3A CN110838135A (en) 2019-10-31 2019-10-31 PCB bare board image registration method

Publications (1)

Publication Number Publication Date
CN110838135A true CN110838135A (en) 2020-02-25

Family

ID=69575819

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911056182.3A Pending CN110838135A (en) 2019-10-31 2019-10-31 PCB bare board image registration method

Country Status (1)

Country Link
CN (1) CN110838135A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116630325A (en) * 2023-07-25 2023-08-22 苏州赫芯科技有限公司 Method, equipment and storage medium for detecting UV glue based on circuit board

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102096920A (en) * 2010-12-31 2011-06-15 清华大学 Target image-based sub-pixel registering method
CN103295232A (en) * 2013-05-15 2013-09-11 西安电子科技大学 SAR (specific absorption rate) image registration method based on straight lines and area
CN106897994A (en) * 2017-01-20 2017-06-27 北京京仪仪器仪表研究总院有限公司 A kind of pcb board defect detecting system and method based on layered image
CN108269274A (en) * 2016-12-31 2018-07-10 南京理工大学 Method for registering images based on Fourier transformation and Hough transform
CN110298799A (en) * 2019-06-25 2019-10-01 福建工程学院 A kind of PCB image positioning correction method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102096920A (en) * 2010-12-31 2011-06-15 清华大学 Target image-based sub-pixel registering method
CN103295232A (en) * 2013-05-15 2013-09-11 西安电子科技大学 SAR (specific absorption rate) image registration method based on straight lines and area
CN108269274A (en) * 2016-12-31 2018-07-10 南京理工大学 Method for registering images based on Fourier transformation and Hough transform
CN106897994A (en) * 2017-01-20 2017-06-27 北京京仪仪器仪表研究总院有限公司 A kind of pcb board defect detecting system and method based on layered image
CN110298799A (en) * 2019-06-25 2019-10-01 福建工程学院 A kind of PCB image positioning correction method

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
李孟等: "基于改进Hough变换的印刷电路板定位配准", 《电视技术》 *
陈姜嘉旭: "基于机器视觉的PCB裸板缺陷检测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 *
黄亚伟: "PCB裸板缺陷光学检测技术的研究与应用", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *
黄祚继等: "《多源遥感数据目标地物的分类与优化》", 31 May 2017 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116630325A (en) * 2023-07-25 2023-08-22 苏州赫芯科技有限公司 Method, equipment and storage medium for detecting UV glue based on circuit board
CN116630325B (en) * 2023-07-25 2023-10-13 苏州赫芯科技有限公司 Method, equipment and storage medium for detecting UV glue based on circuit board

Similar Documents

Publication Publication Date Title
CN111308448B (en) External parameter determining method and device for image acquisition equipment and radar
CN109100370A (en) A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis
CN110189322B (en) Flatness detection method, device, equipment, storage medium and system
JP2011238228A (en) Screen area detection method and system
CN107610085A (en) A kind of welding point defect detecting system based on computer vision
CN108918093B (en) Optical filter mirror surface defect detection method and device and terminal equipment
CN106643555B (en) Connector recognition methods based on structured light three-dimensional measurement system
CN110648330B (en) Defect detection method for camera glass
CN109738450A (en) The detection method and device of keyboard of notebook computer
CN110599404A (en) Circuit board microscopic image splicing method and device and information data processing terminal
CN117152165A (en) Photosensitive chip defect detection method and device, storage medium and electronic equipment
CN116777877A (en) Circuit board defect detection method, device, computer equipment and storage medium
CN113705564B (en) Pointer type instrument identification reading method
CN114820439A (en) PCB bare board defect detection system and method based on AOI
CN110838135A (en) PCB bare board image registration method
CN112833821B (en) Differential geometric three-dimensional micro-vision detection system and method for high-density IC welding spots
CN112669272A (en) AOI rapid detection method and rapid detection system
JP2014191685A (en) Image processing apparatus and image processing method
CN108898584B (en) Image analysis-based full-automatic veneered capacitor welding polarity discrimination method
CN116908185A (en) Method and device for detecting appearance defects of article, electronic equipment and storage medium
CN115082504B (en) Light spot identification method for solar photovoltaic panel
JP2009281759A (en) Color filter defect inspection method, inspection apparatus, and color filter manufacturing method using it
CN116993654A (en) Camera module defect detection method, device, equipment, storage medium and product
Wu et al. A visual inspection system for surface mounted components based on color features
CN114720473A (en) Defect detection method of vehicle-mounted screen backboard based on machine vision

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200225