Nothing Special   »   [go: up one dir, main page]

CN109507192B - A method for detecting surface defects of magnetic cores based on machine vision - Google Patents

A method for detecting surface defects of magnetic cores based on machine vision Download PDF

Info

Publication number
CN109507192B
CN109507192B CN201811301846.3A CN201811301846A CN109507192B CN 109507192 B CN109507192 B CN 109507192B CN 201811301846 A CN201811301846 A CN 201811301846A CN 109507192 B CN109507192 B CN 109507192B
Authority
CN
China
Prior art keywords
image
defect
rectangle
grayscale
magnetic core
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.)
Expired - Fee Related
Application number
CN201811301846.3A
Other languages
Chinese (zh)
Other versions
CN109507192A (en
Inventor
范洪辉
李佳伟
朱洪锦
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.)
Sanluoxuan Big Data Technology Kunshan Co ltd
Original Assignee
Jiangsu University of Technology
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 Jiangsu University of Technology filed Critical Jiangsu University of Technology
Priority to CN201811301846.3A priority Critical patent/CN109507192B/en
Publication of CN109507192A publication Critical patent/CN109507192A/en
Application granted granted Critical
Publication of CN109507192B publication Critical patent/CN109507192B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/9501—Semiconductor wafers
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Image Analysis (AREA)

Abstract

本发明涉及缺陷检测技术领域，尤其是一种基于机器视觉的磁芯表面缺陷检测方法，其步骤为：通过彩色CCD工业相机采集待检测磁芯的十张图片；对采集到的图进进行灰度处理，转换为单通道的灰度图像；用图像质量评价函数对灰度处理之后的图片进行评价，选出最佳测试图片；用伽马变换对图像进行对比增强处理；用OSTU算法获得二值图；用4连通区域法提取出缺陷的轮廓；用最小外接矩形绘制出缺陷的轮廓，并计算其面积；将计算出的矩形面积与设定的阈值进行比较，大于阈值则将矩形的顶点坐标记录下来，否则忽略不计；在原图像中绘出缺陷的最小外接矩形；将缺陷信息和图片上传到数据库，本发明检测精度更高、灵活性更加好、更加具有智能性。

Figure 201811301846

The invention relates to the technical field of defect detection, in particular to a magnetic core surface defect detection method based on machine vision. It is converted into a single-channel grayscale image; the image after grayscale processing is evaluated by the image quality evaluation function, and the best test image is selected; the image is contrasted and enhanced by gamma transform; the OSTU algorithm is used to obtain two Value map; extract the contour of the defect with the 4-connected area method; draw the contour of the defect with the smallest circumscribed rectangle, and calculate its area; The coordinates are recorded, otherwise they are ignored; the minimum circumscribed rectangle of the defect is drawn in the original image; the defect information and pictures are uploaded to the database, and the invention has higher detection accuracy, better flexibility and more intelligence.

Figure 201811301846

Description

Magnetic core surface defect detection method based on machine vision
Technical Field
The invention relates to the technical field of defect detection, in particular to a magnetic core surface defect detection method based on machine vision.
Background
The magnetic core is produced in the production process due to the production process or the production environment, such as: surface defects such as scratches, and gaps. These core surface defects can cause the product to have poor strength, reduced electrical characteristics, and even serious safety hazards. Currently, quality inspection of magnetic cores generally relies on manual inspection of surface defects through glasses.
The traditional manual detection mainly has the following defects: 1. the human eye has limited spatial resolution and is difficult to resolve fine cracks. 2. The manual detection is easily affected by subjective consciousness, and the accuracy of the detection is difficult to guarantee. 3. The manual detection efficiency is low, and the product quality information management cannot be realized.
Disclosure of Invention
The invention aims to provide a magnetic core surface defect detection method based on machine vision, and aims to solve the problems of large manual operation error and low efficiency in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme: a magnetic core surface defect detection method based on machine vision comprises the following steps:
1) collecting ten pictures of the magnetic core to be detected by a color CCD industrial camera;
2) carrying out gray level processing on the acquired image, and converting the image into a single-channel gray level image;
3) evaluating the image after the gray processing by using an image quality evaluation function to select an optimal test image;
4) performing denoising processing on the selected best test picture by using median filtering of 3x 3;
5) carrying out contrast enhancement processing on the image by using gamma conversion;
6) obtaining a binary image by using an OSTU algorithm;
7) extracting the outline of the defect by using a 4-connected region method; (ii) a
8) Drawing the outline of the defect by using the minimum circumscribed rectangle and calculating the area of the defect;
9) comparing the calculated area of the rectangle with a set threshold, if the calculated area of the rectangle is larger than the set threshold, recording the vertex coordinates of the rectangle, otherwise, neglecting;
10) drawing a minimum bounding rectangle of the defect in the original image;
11) and uploading the defect information and the picture to a database.
Preferably, the CCD industrial camera is a color industrial camera.
Preferably, according to steps 1) to 3), 10 pictures (I) are taken each time0…I9) Performing gray level processing, and selecting the best test picture I by using the image quality evaluation functionbest。
Preferably, the image quality evaluation function is:
IGray＝0.30*R+0.59*G+0.11*B (1)
f＝∑x∑y(|f(x，y)-f(x-1，y)|+|f(x，y)-f(x+1，y)|+|f(t，y)-
f(x，y-1)|+|f(x，y)-f(x，y+1)|) (2)
equation 1: formula for single-channel graying IGrayThe image after graying, three channel values of R, G, B color image;
equation 2: and f (x, y) is a gray value of the image at the point (x, y), f (x, y-1), f (x, y +1), f (x-1, y) and f (x +1, y) are gray values of upper, lower, left and right points of the point (x, y), respectively, f is an image quality value, and the larger the f value, the better the image quality.
Preferably, the selected best test picture is subjected to median filtering of 3x3 to remove noise according to the steps 4) to 5), and then contrast enhancement processing is performed on the image by gamma conversion to obtain an image I'best。
Preferably, the image I 'after the image enhancement according to the steps 6) to 9)'bestObtaining a binary image I' by using an OTSU algorithmbestExtracting the outer contour of the defect by using a 4-connected domain method, determining the outer contour by using a minimum external rectangular frame, and calculating the area S of the outer contour1…nFinally, the coordinate of the vertex of the rectangle meeting the condition p is recorded by comparing the coordinate with a set threshold value delta1..m。
Preferably, the calculation formula is:
u＝w0*u0+w1*u1 (3)
g＝w0*(u0-u)*(u0-u)+w1*(u1-u)*(u1-u) (4)
Figure BDA0001852595260000031
S1...n＝L*W (6)
equation 3: w is a0，u0Average gray value of foreground under current threshold; w is a1，u1The average gray value of the background under the current threshold value; u is the total average gray scale of the image;
equation 4: g is the variance of the foreground and background images, and the gray value th is the optimal threshold when the variance g is maximum;
equation 5: i ″)bestThe method is a binary image, wherein A is an image pixel gray value, and th is an optimal threshold;
equation 6: s1…nIs of minimum rectangular area, L is rectangularLong, W is the width of the rectangle.
Preferably, the position of each defect is drawn by the minimum bounding rectangle in the original image according to the steps 10) to 11), and the number, the area and the picture information of the detected defects are uploaded to a database.
Compared with the prior art, the invention has the beneficial effects that: compared with traditional manual detection, mechanical detection and the like, the detection method is higher in detection precision, better in flexibility and more intelligent, comprises two parts of magnetic core surface defect detection and defect information and picture storage to a database, firstly, magnetic core pictures to be detected are collected (ten pictures are collected at each time), the collected pictures are converted into single-channel gray level images, then, image quality evaluation is carried out, and the best test pictures are selected. Carrying out 3X3 median filtering on the selected picture, carrying out image enhancement processing, obtaining a binary image through an OTSU algorithm (optimal inter-class variance), extracting the outline of the defect through a 4-connected region method, defining the outline by using a minimum circumscribed rectangle frame, calculating the area of the minimum circumscribed rectangle frame, recording the vertex coordinates of the external minimum rectangle if the area is larger than a threshold value (not fixed and can be flexibly changed), drawing the minimum circumscribed rectangle of the defect in the original image, and indicating the position of the defect. Finally, uploading the defect information and the picture to a database;
1. the position of the defect can be accurately and quickly positioned, and the detection precision and efficiency are improved;
2. the detection precision can be flexibly controlled, the production requirement is convenient, and the intelligent detection device is more intelligent;
3. the defect information and the pictures can be uploaded to a database, so that the product quality can be conveniently monitored and inquired;
4. the interference caused by human factors is avoided, and the production cost is reduced.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a selected best test gray scale picture of the present invention;
FIG. 3 is the result of the 3X3 median filtering of the present invention;
FIG. 4 is the result of the gamma conversion of the present invention;
FIG. 5 is the OSTU binarization result of the present invention;
FIG. 6 is a profile of the present invention obtained using the 4-connected domain method;
FIG. 7 is detected defect information of the present invention;
FIG. 8 shows the results of the surface defect inspection according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 8, the present invention provides a technical solution: a magnetic core surface defect detection method based on machine vision comprises the following steps:
1) collecting ten pictures of the magnetic core to be detected by a color CCD industrial camera;
2) carrying out gray level processing on the acquired image, and converting the image into a single-channel gray level image;
3) evaluating the image after the gray processing by using an image quality evaluation function to select an optimal test image;
4) performing denoising processing on the selected best test picture by using median filtering of 3x 3;
5) carrying out contrast enhancement processing on the image by using gamma conversion;
6) obtaining a binary image by using an OSTU algorithm;
7) extracting the outline of the defect by using a 4-connected region method; (ii) a
8) Drawing the outline of the defect by using the minimum circumscribed rectangle and calculating the area of the defect;
9) comparing the calculated area of the rectangle with a set threshold, if the calculated area of the rectangle is larger than the set threshold, recording the vertex coordinates of the rectangle, otherwise, neglecting;
10) drawing a minimum bounding rectangle of the defect in the original image;
11) and uploading the defect information and the picture to a database.
The CCD industrial camera is a color industrial camera.
According to steps 1) to 3), 10 pictures (I) are taken each time0…I9) Performing gray level processing, and selecting the best test picture I by using the image quality evaluation functionbest。
The image quality evaluation function is as follows:
IGray＝0.30*R+0.59*G+0.11*B (1)
＝∑x∑y)|f(x，y)-f(x-1，y)|+|f(x，y)-f(x+1，y)|+|f(x，y)-
f(x，y-1)|+|f(x，y)-f(x，y+1)|) (2)
equation 1: formula for single-channel graying IGrayThe image after graying, three channel values of R, G, B color image;
equation 2: and f (x, y) is a gray value of the image at the point (x, y), f (x, y-1), f (x, y +1), f (x-1, y) and f (x +1, y) are gray values of upper, lower, left and right points of the point (x, y), respectively, f is an image quality value, and the larger the f value, the better the image quality.
Filtering noise of the selected optimal test picture by using a median filter of 3x3 according to the steps 4) to 5), and performing contrast enhancement processing on the image by using gamma conversion to obtain an image I'best。
Enhancing the image I 'according to the steps 6) to 9)'bestObtaining a binary image I' by using an OTSU algorithmbestExtracting the outer contour of the defect by using a 4-connected domain method, determining the outer contour by using a minimum external rectangular frame, and calculating the area S of the outer contour1…nFinally, the coordinate of the vertex of the rectangle meeting the condition p is recorded by comparing the coordinate with a set threshold value delta1..m. The calculation formula is as follows:
u＝w0*u0+w1*u1 (3)
g＝w0*(u0-u)*(u0-u)+w1*(u1-u)*(u1-u) (4)
Figure BDA0001852595260000061
S1...n＝L*W (6)
equation 3: w is a0，u0Average gray value of foreground under current threshold; w is a1，u1The average gray value of the background under the current threshold value; u is the total average gray scale of the image;
equation 4: g is the variance of the foreground and background images, and the gray value th is the optimal threshold when the variance g is maximum;
equation 5: i ″)bestThe value graph is obtained, A is the gray value of the image pixel, and th is the optimal threshold;
equation 6: s1…nIs the smallest rectangular area, L is the length of the rectangle, and W is the width of the rectangle.
Drawing the position of each defect in the original image by using the minimum bounding rectangle according to the steps 10) to 11), and uploading the number, the area and the picture information of the detected defects to a database.
According to the technical scheme, 1) ten pictures of the magnetic core to be detected are collected through a color CCD industrial camera;
2) carrying out gray level processing on the acquired image, and converting the image into a single-channel gray level image;
3) evaluating the image after the gray processing by using an image quality evaluation function, and selecting an optimal test image shown in fig. 2;
4) denoising the selected best test picture by using median filtering of 3X3 to obtain a filtered image as shown in FIG. 3;
5) carrying out contrast enhancement processing on the image by using gamma conversion to obtain an enhanced image shown in FIG. 4;
6) obtaining a binary map as shown in fig. 5 using the OSTU algorithm, wherein white areas are defects;
7) extracting the outline of the defect by using a 4-connected region method, wherein the obtained result is shown in FIG. 6;
8) drawing the outline of the defect by using the minimum circumscribed rectangle and calculating the area of the defect;
9) comparing the calculated area of the rectangle with a set threshold, recording the vertex coordinates of the rectangle if the calculated area of the rectangle is larger than the threshold, otherwise, neglecting, and obtaining a result as shown in FIG. 7;
10) drawing a minimum bounding rectangle of the defect in the original image, indicating the position of the defect, and obtaining a result as shown in FIG. 8;
11) and uploading the defect information and the picture to a database.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (5)

1.一种基于机器视觉的磁芯表面缺陷检测方法，其特征在于：其步骤为：1. a magnetic core surface defect detection method based on machine vision, is characterized in that: its steps are: 1)通过彩色CCD工业相机采集待检测磁芯的十张图片；1) Collect ten pictures of the magnetic core to be tested through a color CCD industrial camera; 2)对采集到的图进进行灰度处理，转换为单通道的灰度图像；2) Perform grayscale processing on the collected image, and convert it into a single-channel grayscale image; 3)用图像质量评价函数对灰度处理之后的图片进行评价，选出最佳测试图片；3) Use the image quality evaluation function to evaluate the image after grayscale processing, and select the best test image; 4)用3x3的中值滤波对选出的最佳测试图片进行去噪声处理；4) Denoise the selected best test picture with a 3x3 median filter; 5)用伽马变换对图像进行对比增强处理；5) Perform contrast enhancement processing on the image with gamma transformation; 6)用OSTU算法获得二值图；6) Obtain the binary image by OSTU algorithm; 7)用4连通区域法提取出缺陷的轮廓；7) Extract the contour of the defect with the 4-connected region method; 8)用最小外接矩形绘制出缺陷的轮廓，并计算其面积；8) Draw the outline of the defect with the smallest circumscribed rectangle, and calculate its area; 9)将计算出的矩形面积与设定的阈值进行比较，大于阈值则将矩形的顶点坐标记录下来，否则忽略不计；9) Compare the calculated area of the rectangle with the set threshold, and if it is greater than the threshold, record the vertex coordinates of the rectangle, otherwise it will be ignored; 10)在原图像中绘出缺陷的最小外接矩形；10) Draw the minimum circumscribed rectangle of the defect in the original image; 11)将缺陷信息和图片上传到数据库；11) Upload defect information and pictures to the database; 所述的CCD工业相机为彩色工业相机；The CCD industrial camera is a color industrial camera; 根据步骤1)至3)，每次采集10张图片，进行灰度处理，再通过图像质量评价函数选出最佳测试图片Ibest；According to step 1) to 3), collect 10 pictures at a time, carry out grayscale processing, then select best test picture I best by image quality evaluation function; IGray＝0.30*R+0.59*G+0.11*B (1)I Gray = 0.30*R+0.59*G+0.11*B (1)
Figure FDA0003041045160000011
Figure FDA0003041045160000011
 公式(1)：单通道灰度化公式，IGray灰度化之后图像中每个像素点的灰度值，R、G、B为彩色图像的三通道值；Formula (1): single-channel grayscale formula, I Gray grayscale value of each pixel in the image after grayscale, R, G, B are the three-channel values of the color image; 公式(2)：图像质量评价函数，f(x,y)为图像在点(x,y)处的灰度值，f(x,y-1)、f(x,y+1)、f(x-1,y)、f(x+1,y)分别为点(x,y)上下左右点处的灰度值，f为图像质量值，f值越大图像质量越好。Formula (2): Image quality evaluation function, f(x,y) is the gray value of the image at point (x,y), f(x,y-1), f(x,y+1), f (x-1, y) and f(x+1, y) are the gray values at the upper, lower, left, and right points of the point (x, y), respectively, and f is the image quality value. The larger the f value, the better the image quality. 2.根据权利要求1所述的一种基于机器视觉的磁芯表面缺陷检测方法，其特征在于：根据步骤2. A machine vision-based magnetic core surface defect detection method according to claim 1, characterized in that: according to the step 4)至步骤5)对选出的最佳测试图片用3x3的中值滤波滤除噪声，再用伽马变换对图像进行对比增强处理，得到图像I′best。4) To step 5), the selected best test image is filtered with a 3×3 median filter to filter out noise, and then the image is subjected to contrast enhancement processing with gamma transformation to obtain an image I′ best . 3.根据权利要求2所述的一种基于机器视觉的磁芯表面缺陷检测方法，其特征在于：根据步骤6)至步骤9)对图像增强之后的图像I′best用OTSU算法，得到二值化图像I″best，并利用4连通域法提取出缺陷的外部轮廓，再用最小外接矩形框定出来，并计算其面积S1,S2....Sn，其中n为最小外接矩形的个数，最后与设定的阈值δ进行比较，记录下符合条件的矩形顶点坐标p1,p2....pm，其中m为最小外接矩形面积大于设定阈值δ的个数。3. a kind of magnetic core surface defect detection method based on machine vision according to claim 2, is characterized in that: according to step 6) to step 9) image I' best after image enhancement uses OTSU algorithm, obtains binary value Convert the image I″ best , and use the 4-connected domain method to extract the outer contour of the defect, then frame it with the smallest circumscribed rectangle, and calculate its area S 1 , S 2 ....S n , where n is the minimum circumscribed rectangle The number is finally compared with the set threshold δ, and the qualified rectangle vertex coordinates p 1 , p 2 ....p m are recorded, where m is the number of the minimum circumscribed rectangle area greater than the set threshold δ. 4.根据权利要求3所述的一种基于机器视觉的磁芯表面缺陷检测方法，其特征在于：计算公式为：4. a kind of magnetic core surface defect detection method based on machine vision according to claim 3, is characterized in that: calculation formula is: u＝w0*u0+w1*u1 (3)u=w 0 *u 0 +w 1 *u 1 (3) g＝w0*(u0-u)*(u0-u)+w1*(u1-u)*(u1-u) (4)g=w 0 *(u 0 -u)*(u 0 -u)+w 1 *(u 1 -u)*(u 1 -u) (4)
Figure FDA0003041045160000021
Figure FDA0003041045160000021
 Sn＝L*W (6) Sn = L*W (6) 公式(3)：w0和w1分别表示前景和背景对应的图像模板卷积运算的算子；u0和u1分别表示图像灰度化之后前景和背景的灰度值；w0*u0为当前阈值下前景的平均灰度值；w1*u1为当前阈值下背景的平均灰度值；u为图像的总平均灰度；Formula (3): w 0 and w 1 respectively represent the image template convolution operator corresponding to the foreground and background; u 0 and u 1 respectively represent the gray value of the foreground and background after grayscale; w 0 *u 0 is the average gray value of the foreground under the current threshold; w 1 *u 1 is the average gray value of the background under the current threshold; u is the total average gray value of the image; 公式(4)：g为前景与背景图像的方差，当方差g为最大时候的灰度值th为最佳阈值；Formula (4): g is the variance of the foreground and background images, and the gray value th when the variance g is the largest is the optimal threshold; 公式(5)：I″best为二值图，A为图像像素灰度值，th为最佳阈值；Formula (5): I″ best is a binary image, A is the gray value of the image pixel, and th is the best threshold; 公式(6)：Sn为最小外接矩形面积，L为矩形的长，W为矩形的宽。Formula (6): Sn is the minimum circumscribed rectangle area, L is the length of the rectangle, and W is the width of the rectangle. 5.根据权利要求1所述的一种基于机器视觉的磁芯表面缺陷检测方法，其特征在于：根据步骤10)至步骤11)在原图像中用最小外接矩形绘制出每个缺陷所在的位置，且把检测到缺陷的数量、面积和图片信息上传到数据库。5. a kind of magnetic core surface defect detection method based on machine vision according to claim 1, is characterized in that: according to step 10) to step 11) draw the position where each defect is located with minimum circumscribed rectangle in the original image, And upload the number, area and picture information of the detected defects to the database.
CN201811301846.3A 2018-11-02 2018-11-02 A method for detecting surface defects of magnetic cores based on machine vision Expired - Fee Related CN109507192B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811301846.3A CN109507192B (en) 2018-11-02 2018-11-02 A method for detecting surface defects of magnetic cores based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811301846.3A CN109507192B (en) 2018-11-02 2018-11-02 A method for detecting surface defects of magnetic cores based on machine vision

Publications (2)

Publication Number Publication Date
CN109507192A CN109507192A (en) 2019-03-22
CN109507192B true CN109507192B (en) 2021-07-02

Family

ID=65747479

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811301846.3A Expired - Fee Related CN109507192B (en) 2018-11-02 2018-11-02 A method for detecting surface defects of magnetic cores based on machine vision

Country Status (1)

Country Link
CN (1) CN109507192B (en)

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109870461B (en) * 2019-03-29 2020-04-24 泗阳恒润电子有限公司 Electronic components quality detection system
CN110186929A (en) * 2019-04-24 2019-08-30 南京邮电大学 A kind of real-time product defect localization method
CN110336931B (en) * 2019-06-14 2024-08-23 国网电力科学研究院武汉南瑞有限责任公司 Evaluation method of mold test result of low-voltage current transformer
CN110415195A (en) * 2019-08-08 2019-11-05 中国矿业大学(北京) A kind of high-temperature forging image preprocessing combined method
CN110514664B (en) * 2019-08-20 2022-08-12 北京信息科技大学 A robot and method for positioning and detecting the yarn rod of a cheese yarn
CN110470670A (en) * 2019-08-26 2019-11-19 浙江华是科技股份有限公司 A kind of magnetic core defect detecting system and method based on image procossing
CN110689520A (en) * 2019-08-26 2020-01-14 浙江华是科技股份有限公司 Magnetic core product defect detection system and method based on AI
CN111179243A (en) * 2019-12-25 2020-05-19 武汉昕竺科技服务有限公司 Small-size chip crack detection method and system based on computer vision
CN113706525B (en) * 2021-10-20 2022-02-15 武汉飞恩微电子有限公司 Intelligent printed circuit board patch defect identification method based on image processing
CN113935981A (en) * 2021-10-26 2022-01-14 深圳市玻尔智造科技有限公司 A Quantitative Evaluation Method of Defects Based on AOI Detection
CN114549493A (en) * 2022-02-28 2022-05-27 浙江工业大学 A deep learning-based magnetic core defect detection system and method
CN114581415A (en) * 2022-03-08 2022-06-03 成都数之联科技股份有限公司 Method and device for detecting defects of PCB, computer equipment and storage medium
CN115445953B (en) * 2022-06-28 2024-04-05 中国机械总院集团宁波智能机床研究院有限公司 Good product detection method and detection device for oil pipe
CN115358998B (en) * 2022-08-22 2023-06-16 法博思(宁波)半导体设备有限公司 Method and system for acquiring point coordinates in random array picture
CN116228590B (en) * 2023-03-22 2024-01-26 新创碳谷集团有限公司 Flame visual detection noise point elimination method, device and storage medium
CN116718607B (en) * 2023-06-13 2024-01-26 通用技术齐齐哈尔二机床有限责任公司 Fiber material belt online quality monitoring method based on visual monitoring

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204614A (en) * 2016-07-21 2016-12-07 湘潭大学 A kind of workpiece appearance defects detection method based on machine vision
CN106338520A (en) * 2016-09-18 2017-01-18 南京林业大学 Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board
CN107486415A (en) * 2017-08-09 2017-12-19 中国计量大学 Thin bamboo strip defect on-line detecting system and detection method based on machine vision
CN107870172A (en) * 2017-07-06 2018-04-03 黎明职业大学 A Method of Cloth Defect Detection Based on Image Processing

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106204614A (en) * 2016-07-21 2016-12-07 湘潭大学 A kind of workpiece appearance defects detection method based on machine vision
CN106338520A (en) * 2016-09-18 2017-01-18 南京林业大学 Recognition method of surface defects of multilayer solid wood composite floor with surface board being jointed board
CN107870172A (en) * 2017-07-06 2018-04-03 黎明职业大学 A Method of Cloth Defect Detection Based on Image Processing
CN107486415A (en) * 2017-08-09 2017-12-19 中国计量大学 Thin bamboo strip defect on-line detecting system and detection method based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机器视觉的密封件表面缺陷检测研究;赵磊等;《电子设计工程》;20111231;第19卷(第24期);第72-74、77页 *

Also Published As

Publication number Publication date
CN109507192A (en) 2019-03-22

Similar Documents

Publication Publication Date Title
CN109507192B (en) A method for detecting surface defects of magnetic cores based on machine vision
CN109934802B (en) A Cloth Defect Detection Method Based on Fourier Transform and Image Morphology
CN110349126B (en) A Marked Steel Plate Surface Defect Detection Method Based on Convolutional Neural Network
CN106780486B (en) A method for image extraction of steel plate surface defects
CN112308832B (en) Bearing quality detection method based on machine vision
CN108629775A (en) A kind of hot high-speed rod surface image processing method
CN109872303B (en) Surface defect visual inspection method, device and electronic equipment
CN115018844B (en) Plastic film quality evaluation method based on artificial intelligence
CN103914827B (en) The visible detection method of weather strip for automobile profile defects
WO2021109697A1 (en) Character segmentation method and apparatus, and computer-readable storage medium
CN105160652A (en) Handset casing testing apparatus and method based on computer vision
CN114494210A (en) Plastic film production defect detection method and system based on image processing
CN104792794A (en) Machine vision based optical film surface defect detecting method
CN106767564A (en) A kind of detection method for being applied to phone housing surface roughness
CN109781737B (en) Detection method and detection system for surface defects of hose
CN107644417B (en) Appearance defect detection method of strain gauge
CN107240086B (en) A kind of fabric defects detection method based on integral nomography
CN111047556A (en) Strip steel surface defect detection method and device
CN112258444A (en) Elevator steel wire rope detection method
CN110263778A (en) A kind of meter register method and device based on image recognition
CN117522778A (en) Hollow brick flaw detection system
CN112017109B (en) Online ferrographic video image bubble elimination method
CN111256596B (en) Size measuring method and device based on CV technology, computer equipment and medium
CN116071692A (en) Morphological image processing-based water gauge water level identification method and system
CN114332081A (en) Textile surface abnormity determination method based on image processing

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
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20221227

Address after: 215300 Station D-21, Room B103, Zone C, No. 55, Xiaxi Street, Kunshan Development Zone, Suzhou, Jiangsu Province

Patentee after: SANLUOXUAN BIG DATA TECHNOLOGY (KUNSHAN) Co.,Ltd.

Address before: 213001 No. 1801 Wu Cheng Road, Changzhou, Jiangsu

Patentee before: JIANGSU University OF TECHNOLOGY

CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210702