技术领域technical field
本发明涉及钢铁制造的技术领域，尤其涉及到基于机器视觉的不锈钢表面缺陷检测方法。The invention relates to the technical field of iron and steel manufacturing, in particular to a machine vision-based detection method for stainless steel surface defects.
背景技术Background technique
钢铁的生产和制造是一个影响国家国民经济和工业现代化的十分重要的因素。例如，在日常生活中，不锈钢产品应用于各个方面。所以对不锈钢的质量检测显得尤为重要。The production and manufacture of steel is a very important factor affecting the national economy and industrial modernization of a country. For example, in daily life, stainless steel products are used in various aspects. Therefore, the quality inspection of stainless steel is particularly important.
不锈钢表面缺陷通常分为二维缺陷和三维缺陷。传统不锈钢的表面缺陷检测由检测人员通过人眼目测来完成。但是,这种方法存在着很多不足，譬如：1、检测结果容易受检测人员主观因素影响；2、只能用于检测运行速度很慢的不锈钢表面；3、很难检测到小的缺陷。Stainless steel surface defects are usually divided into two-dimensional defects and three-dimensional defects. The surface defect detection of traditional stainless steel is completed by inspectors through human eyes. However, this method has many shortcomings, such as: 1. The test results are easily affected by the subjective factors of the testers; 2. It can only be used to detect the stainless steel surface with a slow running speed; 3. It is difficult to detect small defects.
发明内容Contents of the invention
本发明的目的在于克服现有技术的不足，提供一种检测结果精确、检测效率高、能检测到不锈钢表面二维及三维细小缺陷的基于机器视觉的不锈钢表面缺陷检测方法。The purpose of the present invention is to overcome the deficiencies of the prior art and provide a machine vision-based stainless steel surface defect detection method with accurate detection results, high detection efficiency, and the ability to detect two-dimensional and three-dimensional small defects on the stainless steel surface.
为实现上述目的，本发明所提供的技术方案为：方法包括以下步骤：In order to achieve the above object, the technical solution provided by the present invention is: the method comprises the following steps:
S1.采用CCD工业相机采集待检测不锈钢的表面图像；S1. Use a CCD industrial camera to collect the surface image of the stainless steel to be detected;
S2.对采集到的待检测不锈钢表面图像进行基于Blob分析的二维缺陷检测；S2. Perform two-dimensional defect detection based on Blob analysis on the collected stainless steel surface image to be detected;
S3.对采集到的待检测不锈钢表面图像进行基于频域的傅立叶变换的三维缺陷检测；S3. Perform three-dimensional defect detection based on frequency domain Fourier transform on the collected stainless steel surface image to be detected;
S4.根据二维和三维缺陷检测结果将存在缺陷的不锈钢分离开来。S4. Separate the defective stainless steel according to the two-dimensional and three-dimensional defect detection results.
进一步地，步骤S2不锈钢表面二维缺陷检测步骤如下：Further, the steps of step S2 for detecting two-dimensional defects on the stainless steel surface are as follows:
S21.选定ROI区域：S21. Select ROI area:
采用全局阈值法将ROI区域，即不锈钢板区域分割出来，然后提取不锈钢板连通域。设待分割图像为f(x，y),阈值分割后的图像为S(x，y),公式为The global threshold method is used to segment the ROI area, that is, the stainless steel plate area, and then the connected domain of the stainless steel plate is extracted. Suppose the image to be segmented is f(x, y), and the image after threshold segmentation is S(x, y), the formula is
其中，T为分割阈值；Among them, T is the segmentation threshold;
S22.图像预处理；S22. Image preprocessing;
S23.分割图像：S23. Segment image:
采用改进的双阈值法将预处理后的灰度图进行分割，将图像分割为前景图像(即缺陷区域)和背景图像的像素集合；The preprocessed grayscale image is segmented by an improved double-threshold method, and the image is divided into pixel sets of the foreground image (that is, the defect area) and the background image;
设前景图像为p(x,y),阈值分割后的图像为q(x,y),按如下公式进行图像分割：Let the foreground image be p(x, y), and the image after threshold segmentation be q(x, y), perform image segmentation according to the following formula:
其中T1和T2为针对不锈钢板成像效果所设置的改进阈值；Where T1 and T2 are the improved thresholds set for the stainless steel plate imaging effect;
S24.提取特征：S24. Extract features:
对目标区域进行连通区域提取，得出缺陷部分的面积、圆形度、灰度均值参数。The connected area is extracted from the target area, and the area, circularity, and gray value parameters of the defect part are obtained.
面积计算公式为：The area calculation formula is:
其中，R表示图像区域，m、n表示图像区域有m行n列，f(i，j)表示区域内点(i，j)处的像素值；Wherein, R represents the image area, m and n represent that the image area has m rows and n columns, and f(i, j) represents the pixel value at the point (i, j) in the region;
圆形度计算公式为：The formula for calculating circularity is:
其中，P表示区域的周长，A表示区域的面积；Among them, P represents the perimeter of the region, and A represents the area of the region;
灰度均值计算公式为：The formula for calculating the gray mean value is:
其中，L为灰度级总数，zi表示第i个灰度级，h(zi)表示直方图中统计的灰度为zi的像素个数；Wherein, L is the total number of gray levels, zi represents the i-th gray level, and h(zi ) represents the number of pixels whose gray level is zi in the histogram;
进一步地，步骤S3不锈钢表面三维缺陷检测步骤如下：Further, the step S3 three-dimensional defect detection steps on the stainless steel surface are as follows:
S31.创建高斯滤波器：S31. Create a Gaussian filter:
创建两个高斯滤波器,并对高斯滤波后的图像做减法处理；Create two Gaussian filters and perform subtraction on the Gaussian filtered images;
公式描述为：The formula is described as:
O(i，j)＝|I1(i，j)-I2(i，j)|，O(i,j)=|I1 (i,j)-I2 (i,j)|,
其中，O(i，j)为相减后的图像，I1(i，j)，I2(i，j)分别为经高斯滤波后的两图像；Among them, O(i, j) is the image after subtraction, I1 (i, j), I2 (i, j) are the two images after Gaussian filtering;
S32.图像预处理：S32. Image preprocessing:
将RGB三通道图像图转化为灰度图；Convert the RGB three-channel image to a grayscale image;
设转换后的灰度图为Gray(i，j)，计算公式为：Let the converted grayscale image be Gray(i, j), and the calculation formula is:
Gray(i，j)＝0.11*R(i，j)+0.59*G(i，j)+0.3*B(i，j)，Gray(i,j)=0.11*R(i,j)+0.59*G(i,j)+0.3*B(i,j),
其中，Gray(i，j)为转换后的图像在(i，j)点处的灰度值；Wherein, Gray(i, j) is the gray value of the converted image at (i, j) point;
S33.预处理后的图像从空间域转换到频域处理：S33. The preprocessed image is converted from the spatial domain to the frequency domain processing:
将灰度图进行傅立叶变换，从空间域转换到频域处理；Perform Fourier transform on the grayscale image and convert it from the spatial domain to the frequency domain;
二维傅立叶变换计算公式为：The two-dimensional Fourier transform calculation formula is:
其中，f(x，y)为空间域图像，F(u，v)为二维傅里叶变换后图像；Wherein, f(x, y) is a spatial domain image, and F(u, v) is a two-dimensional Fourier transformed image;
S34.对频域图像进行卷积运算：S34. Perform convolution operation on the frequency domain image:
对图像用一个滤波器在频域进行卷积运算，计算公式为：The image is convolved in the frequency domain with a filter, and the calculation formula is:
其中，g(i，j)为输入图像，h称为相关核，f(i，j)为输出图像；Among them, g(i, j) is the input image, h is called the correlation kernel, and f(i, j) is the output image;
S35.将频域图像重新转换到空间域处理：S35. Reconvert the frequency domain image to the spatial domain for processing:
对卷积运算后的图像进行傅立叶反变换，重新转换到空间域处理；Inverse Fourier transform is performed on the image after the convolution operation, and then converted to the spatial domain for processing;
计算公式为：The calculation formula is:
二维傅立叶反变换计算公式为:The calculation formula of two-dimensional inverse Fourier transform is:
其中，为二维傅里叶反变换后图像，F(u，v)为二维傅里叶图像；in, is the image after the two-dimensional inverse Fourier transform, F (u, v) is the two-dimensional Fourier image;
S36.空间域图像分割：S36. Spatial domain image segmentation:
利用改进的双阈值法对步骤S35的反傅里叶变换图像进行分割,提取缺陷区域。The improved double threshold method is used to segment the inverse Fourier transform image in step S35 to extract defect areas.
设前景图像为p(x,y),阈值分割后的图像为q(x,y),按如下公式进行图像分割：Let the foreground image be p(x, y), and the image after threshold segmentation be q(x, y), perform image segmentation according to the following formula:
其中T1和T2为针对不锈钢板成像效果所设置的改进阈值；Where T1 and T2 are the improved thresholds set for the stainless steel plate imaging effect;
S37.连通域选取。S37. Connected domain selection.
进一步地，步骤S22图像预处理的具体步骤如下：用灰度变换对选定的ROI区域进行图像预处理,采用掩膜对灰度图进行均值滤波去噪。Further, the specific steps of image preprocessing in step S22 are as follows: image preprocessing is performed on the selected ROI region by grayscale transformation, and mean filtering is performed on the grayscale image to denoise by using a mask.
本方案原理以及优点如下：The principles and advantages of this scheme are as follows:
本方案针对二维缺陷，提出一种基于Blob分析的表面缺陷检测算法，针对三维缺陷，提出一种基于频域的傅立叶变换算法，可以有效检出不锈钢产品表面常见缺陷，如划痕、油污、锈痕、凹点、裂纹、杂质、轧痕、辊痕等，而且，本方案检测结果精确、检测效率高。This program proposes a surface defect detection algorithm based on Blob analysis for two-dimensional defects, and a frequency domain-based Fourier transform algorithm for three-dimensional defects, which can effectively detect common defects on the surface of stainless steel products, such as scratches, oil stains, Rust marks, pits, cracks, impurities, rolling marks, roll marks, etc., and the detection results of this scheme are accurate and the detection efficiency is high.
附图说明Description of drawings
图1为本发明中二维缺陷检测的算法流程图；Fig. 1 is the algorithm flowchart of two-dimensional defect detection among the present invention;
图2为本发明中三维缺陷检测的算法流程图；Fig. 2 is the algorithm flowchart of three-dimensional defect detection among the present invention;
图3为不锈钢二维缺陷检测效果图；Figure 3 is the effect diagram of stainless steel two-dimensional defect detection;
图4为不锈钢三维缺陷检测效果图。Figure 4 is a three-dimensional defect detection effect diagram of stainless steel.
具体实施方式detailed description
下面结合具体实施例对本发明作进一步说明：The present invention will be further described below in conjunction with specific embodiment:
参见附图1-2所示，本实施例所述的基于机器视觉的不锈钢表面缺陷检测方法，包括以下步骤：Referring to shown in accompanying drawing 1-2, the stainless steel surface defect detection method based on machine vision described in the present embodiment, comprises the following steps:
S1.采用CCD工业相机采集待检测不锈钢的表面图像；S1. Use a CCD industrial camera to collect the surface image of the stainless steel to be detected;
S2.对采集到的待检测不锈钢表面图像进行基于Blob分析的二维缺陷检测，步骤如下：S2. Perform two-dimensional defect detection based on Blob analysis on the collected stainless steel surface image to be detected, the steps are as follows:
S21.选定ROI区域：S21. Select ROI area:
采用全局阈值法将ROI区域，即不锈钢板区域分割出来，然后提取不锈钢板连通域。设待分割图像为f(x，y),阈值分割后的图像为S(x，y),则The global threshold method is used to segment the ROI area, that is, the stainless steel plate area, and then the connected domain of the stainless steel plate is extracted. Suppose the image to be segmented is f(x, y), and the image after threshold segmentation is S(x, y), then
其中，T为分割阈值；Among them, T is the segmentation threshold;
S22.图像预处理：S22. Image preprocessing:
用灰度变换对选定的ROI区域进行图像预处理,采用21*21的掩膜对灰度图进行均值滤波去噪；Perform image preprocessing on the selected ROI area with grayscale transformation, and use 21*21 mask to denoise the grayscale image by mean filtering;
S23.分割图像：S23. Segment image:
采用改进的双阈值法将预处理后的灰度图进行分割，将图像分割为前景图像(即缺陷区域)和背景图像的像素集合；The preprocessed grayscale image is segmented by an improved double-threshold method, and the image is divided into pixel sets of the foreground image (that is, the defect area) and the background image;
设前景图像为p(x,y),阈值分割后的图像为q(x,y),按如下公式进行图像分割：Let the foreground image be p(x, y), and the image after threshold segmentation be q(x, y), perform image segmentation according to the following formula:
其中T1和T2为针对不锈钢板成像效果所设置的改进阈值；Where T1 and T2 are the improved thresholds set for the stainless steel plate imaging effect;
S24.提取特征：S24. Extract features:
对目标区域进行连通区域提取，得出缺陷部分的面积、圆形度、灰度均值参数；Extract the connected area of the target area, and obtain the area, circularity, and gray mean value parameters of the defect part;
面积计算公式为：The area calculation formula is:
其中，R表示图像区域，m、n表示图像区域有m行n列，f(i，j)表示区域内点(i，j)处的像素值；Wherein, R represents the image area, m and n represent that the image area has m rows and n columns, and f(i, j) represents the pixel value at the point (i, j) in the region;
圆形度计算公式为：The formula for calculating circularity is:
其中，P表示区域的周长，A表示区域的面积；Among them, P represents the perimeter of the region, and A represents the area of the region;
灰度均值计算公式为：The formula for calculating the gray mean value is:
其中，L为灰度级总数，zi表示第i个灰度级，h(zi)表示直方图中统计的灰度为zi的像素个数；Wherein, L is the total number of gray levels, zi represents the i-th gray level, and h(zi ) represents the number of pixels whose gray level is zi in the histogram;
S3.对采集到的待检测不锈钢表面图像进行基于频域的傅立叶变换的三维缺陷检测，步骤如下：S3. Perform three-dimensional defect detection based on frequency domain Fourier transform on the collected stainless steel surface image to be detected, the steps are as follows:
S31.建高斯滤波器：S31. Build a Gaussian filter:
创建两个高斯滤波器,并对高斯滤波后的图像做减法处理；Create two Gaussian filters and perform subtraction on the Gaussian filtered images;
公式描述为：The formula is described as:
O(i，j)＝|I1(i，j)-I2(i，j)|，O(i,j)=|I1 (i,j)-I2 (i,j)|,
其中，O(i，j)为相减后的图像，I1(i，j)，I2(i，j)分别为经高斯滤波后的两图像；Among them, O(i, j) is the image after subtraction, I1 (i, j), I2 (i, j) are the two images after Gaussian filtering;
S32.图像预处理：S32. Image preprocessing:
将RGB三通道图像图转化为灰度图；Convert the RGB three-channel image to a grayscale image;
设转换后的灰度图为Gray(i，j)，则计算公式为：Assuming the converted grayscale image is Gray(i, j), the calculation formula is:
Gray(i，j)＝0.11*R(i，j)+0.59*G(i，j)+0.3*B(i，j)，Gray(i,j)=0.11*R(i,j)+0.59*G(i,j)+0.3*B(i,j),
其中，Gray(i，j)为转换后的图像在(i，j)点处的灰度值；Wherein, Gray(i, j) is the gray value of the converted image at (i, j) point;
S33.预处理后的图像从空间域转换到频域处理：S33. The preprocessed image is converted from the spatial domain to the frequency domain processing:
将灰度图进行傅立叶变换，从空间域转换到频域处理；Perform Fourier transform on the grayscale image and convert it from the spatial domain to the frequency domain;
二维傅立叶变换计算公式为：The two-dimensional Fourier transform calculation formula is:
其中，f(x，y)为空间域图像，F(u，v)为二维傅里叶变换后图像；Wherein, f(x, y) is a spatial domain image, and F(u, v) is a two-dimensional Fourier transformed image;
S34.对频域图像进行卷积运算：S34. Perform convolution operation on the frequency domain image:
对图像用一个滤波器在频域进行卷积运算，计算公式为：The image is convolved in the frequency domain with a filter, and the calculation formula is:
其中，g(i，j)为输入图像，h称为相关核，f(i，j)为输出图像；Among them, g(i, j) is the input image, h is called the correlation kernel, and f(i, j) is the output image;
S35.将频域图像重新转换到空间域处理：S35. Reconvert the frequency domain image to the spatial domain for processing:
对卷积运算后的图像进行傅立叶反变换，重新转换到空间域处理；Inverse Fourier transform is performed on the image after the convolution operation, and then converted to the spatial domain for processing;
计算公式为：The calculation formula is:
二维傅立叶反变换计算公式为:The calculation formula of two-dimensional inverse Fourier transform is:
其中，为二维傅里叶反变换后图像，F(u，v)为二维傅里叶图像；in, is the image after the two-dimensional inverse Fourier transform, F (u, v) is the two-dimensional Fourier image;
S36.空间域图像分割：S36. Spatial domain image segmentation:
利用改进的双阈值法对步骤S35的反傅里叶变换图像进行分割,提取缺陷区域。The improved double threshold method is used to segment the inverse Fourier transform image in step S35 to extract defect areas.
设前景图像为p(x,y),阈值分割后的图像为q(x,y),按如下公式进行图像分割：Let the foreground image be p(x, y), and the image after threshold segmentation be q(x, y), perform image segmentation according to the following formula:
其中T1和T2为针对不锈钢板成像效果所设置的改进阈值；Where T1 and T2 are the improved thresholds set for the stainless steel plate imaging effect;
S37.连通域选取；S37. Connected domain selection;
S4.根据二维和三维缺陷检测结果将存在缺陷的不锈钢分离开来。S4. Separate the defective stainless steel according to the two-dimensional and three-dimensional defect detection results.
本实施例检测结果精确，检测效率高，能检测到不锈钢表面二维及三维细小缺陷，如划痕、油污、锈痕、凹点、裂纹、杂质、轧痕、辊痕等。This embodiment has accurate detection results and high detection efficiency, and can detect two-dimensional and three-dimensional small defects on the surface of stainless steel, such as scratches, oil stains, rust marks, pits, cracks, impurities, rolling marks, roll marks, etc.
以上所述之实施例子只为本发明之较佳实施例，并非以此限制本发明的实施范围，故凡依本发明之形状、原理所作的变化，均应涵盖在本发明的保护范围内。The implementation examples described above are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Therefore, all changes made according to the shape and principle of the present invention should be covered within the scope of protection of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469603.XACN107478657A (en) | 2017-06-20 | 2017-06-20 | Stainless steel surfaces defect inspection method based on machine vision |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469603.XACN107478657A (en) | 2017-06-20 | 2017-06-20 | Stainless steel surfaces defect inspection method based on machine vision |
| Publication Number | Publication Date |
|---|---|
| CN107478657Atrue CN107478657A (en) | 2017-12-15 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710469603.XAPendingCN107478657A (en) | 2017-06-20 | 2017-06-20 | Stainless steel surfaces defect inspection method based on machine vision |
| Country | Link |
|---|---|
| CN (1) | CN107478657A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037135A (en)* | 2018-01-15 | 2018-05-15 | 佛山职业技术学院 | A kind of magnet ring surface defect detection apparatus and method |
| CN108181324A (en)* | 2018-01-05 | 2018-06-19 | 佛山职业技术学院 | A kind of board surface detection method based on machine vision |
| CN108921861A (en)* | 2018-05-15 | 2018-11-30 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of portable computer touch tablet edge detection method based on machine vision |
| CN109211919A (en)* | 2018-09-03 | 2019-01-15 | 珠海格力智能装备有限公司 | Method and device for identifying magnetic tile defect area |
| CN109636785A (en)* | 2018-12-07 | 2019-04-16 | 南京埃斯顿机器人工程有限公司 | A kind of visual processing method identifying particles of silicon carbide |
| CN109682820A (en)* | 2018-11-05 | 2019-04-26 | 苏州佳智彩光电科技有限公司 | A kind of defect automatic optical detection method of display screen |
| CN110038859A (en)* | 2019-05-24 | 2019-07-23 | 苏州贝亚敏光电科技有限公司 | A kind of cleaning path automatic monitoring method of laser cleaning equipment |
| CN110111301A (en)* | 2019-03-21 | 2019-08-09 | 广东工业大学 | Metal based on frequency-domain transform aoxidizes surface defect visible detection method |
| CN110189290A (en)* | 2019-04-08 | 2019-08-30 | 广东工业大学 | Method and device for detecting fine defects on metal surface based on deep learning |
| CN110211120A (en)* | 2019-06-04 | 2019-09-06 | 北京航天宏图信息技术股份有限公司 | The corrosion degree of historical relic determines method, apparatus and electronic equipment |
| CN110223296A (en)* | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
| CN110361395A (en)* | 2019-08-06 | 2019-10-22 | 天津日博工业技术有限公司 | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision |
| CN110672635A (en)* | 2019-12-04 | 2020-01-10 | 杭州利珀科技有限公司 | A kind of cloth defect detection device and real-time detection method |
| CN110827235A (en)* | 2019-09-24 | 2020-02-21 | 苏州苏相机器人智能装备有限公司 | Steel plate surface defect detection method |
| CN111028215A (en)* | 2019-12-06 | 2020-04-17 | 上海大学 | Method for detecting end surface defects of steel coil based on machine vision |
| CN111340796A (en)* | 2020-03-10 | 2020-06-26 | 创新奇智(成都)科技有限公司 | Defect detection method and device, electronic equipment and storage medium |
| CN112508926A (en)* | 2020-12-16 | 2021-03-16 | 广州大学 | Method, system and device for detecting surface scratches of metal stamping part and storage medium |
| CN112686858A (en)* | 2020-12-29 | 2021-04-20 | 熵智科技(深圳)有限公司 | Visual defect detection method, device, medium and equipment for mobile phone charger |
| CN113686869A (en)* | 2021-07-19 | 2021-11-23 | 浙江中新电力工程建设有限公司配电分公司 | A device for identifying micro-defects in insulating blankets |
| CN115358982A (en)* | 2022-08-16 | 2022-11-18 | 佛山市南海区广工大数控装备协同创新研究院 | Motor core crack defect detection method and device and related equipment |
| CN116823742A (en)* | 2023-06-07 | 2023-09-29 | 上海晨兴希姆通电子科技有限公司 | Surface defect detection method and system for WLCSP chips after sealing and cutting |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288613A (en)* | 2011-05-11 | 2011-12-21 | 北京科技大学 | Surface defect detecting method for fusing grey and depth information |
| CN103207183A (en)* | 2011-12-28 | 2013-07-17 | 株式会社其恩斯 | Visual Inspection Device And Visual Inspection Method |
| CN104101601A (en)* | 2014-06-23 | 2014-10-15 | 深圳市大族激光科技股份有限公司 | Detection device and method for surface defects |
| CN104198494A (en)* | 2014-08-18 | 2014-12-10 | 苏州克兰兹电子科技有限公司 | On-line detection system for surface defects of plate strips |
| CN104792793A (en)* | 2015-04-28 | 2015-07-22 | 刘凯 | Optical defect detecting method and system |
| CN104792794A (en)* | 2015-04-28 | 2015-07-22 | 武汉工程大学 | Machine vision based optical film surface defect detecting method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288613A (en)* | 2011-05-11 | 2011-12-21 | 北京科技大学 | Surface defect detecting method for fusing grey and depth information |
| CN103207183A (en)* | 2011-12-28 | 2013-07-17 | 株式会社其恩斯 | Visual Inspection Device And Visual Inspection Method |
| CN104101601A (en)* | 2014-06-23 | 2014-10-15 | 深圳市大族激光科技股份有限公司 | Detection device and method for surface defects |
| CN104198494A (en)* | 2014-08-18 | 2014-12-10 | 苏州克兰兹电子科技有限公司 | On-line detection system for surface defects of plate strips |
| CN104792793A (en)* | 2015-04-28 | 2015-07-22 | 刘凯 | Optical defect detecting method and system |
| CN104792794A (en)* | 2015-04-28 | 2015-07-22 | 武汉工程大学 | Machine vision based optical film surface defect detecting method |
| Title |
|---|
| 刘哲等: "钢板表面缺陷检测与控制系统设计", 《天津市电视技术研究会2015年年会论文集》* |
| 王震宇: "基于机器视觉钢板表面缺陷检测技术研究", 《计算机与现代化》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108181324A (en)* | 2018-01-05 | 2018-06-19 | 佛山职业技术学院 | A kind of board surface detection method based on machine vision |
| CN108037135A (en)* | 2018-01-15 | 2018-05-15 | 佛山职业技术学院 | A kind of magnet ring surface defect detection apparatus and method |
| CN108921861A (en)* | 2018-05-15 | 2018-11-30 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of portable computer touch tablet edge detection method based on machine vision |
| CN109211919A (en)* | 2018-09-03 | 2019-01-15 | 珠海格力智能装备有限公司 | Method and device for identifying magnetic tile defect area |
| CN109211919B (en)* | 2018-09-03 | 2021-04-30 | 珠海格力智能装备有限公司 | Method and device for identifying magnetic tile defect area |
| CN109682820A (en)* | 2018-11-05 | 2019-04-26 | 苏州佳智彩光电科技有限公司 | A kind of defect automatic optical detection method of display screen |
| CN109636785A (en)* | 2018-12-07 | 2019-04-16 | 南京埃斯顿机器人工程有限公司 | A kind of visual processing method identifying particles of silicon carbide |
| CN110111301A (en)* | 2019-03-21 | 2019-08-09 | 广东工业大学 | Metal based on frequency-domain transform aoxidizes surface defect visible detection method |
| CN110189290A (en)* | 2019-04-08 | 2019-08-30 | 广东工业大学 | Method and device for detecting fine defects on metal surface based on deep learning |
| CN110038859A (en)* | 2019-05-24 | 2019-07-23 | 苏州贝亚敏光电科技有限公司 | A kind of cleaning path automatic monitoring method of laser cleaning equipment |
| CN110211120A (en)* | 2019-06-04 | 2019-09-06 | 北京航天宏图信息技术股份有限公司 | The corrosion degree of historical relic determines method, apparatus and electronic equipment |
| CN110223296A (en)* | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
| CN110223296B (en)* | 2019-07-08 | 2021-06-11 | 山东建筑大学 | Deformed steel bar surface defect detection method and system based on machine vision |
| CN110361395A (en)* | 2019-08-06 | 2019-10-22 | 天津日博工业技术有限公司 | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision |
| CN110827235A (en)* | 2019-09-24 | 2020-02-21 | 苏州苏相机器人智能装备有限公司 | Steel plate surface defect detection method |
| CN110827235B (en)* | 2019-09-24 | 2022-05-10 | 苏州苏相机器人智能装备有限公司 | Steel plate surface defect detection method |
| CN110672635A (en)* | 2019-12-04 | 2020-01-10 | 杭州利珀科技有限公司 | A kind of cloth defect detection device and real-time detection method |
| CN110672635B (en)* | 2019-12-04 | 2020-04-10 | 杭州利珀科技有限公司 | Cloth defect detection device and real-time detection method |
| CN111028215A (en)* | 2019-12-06 | 2020-04-17 | 上海大学 | Method for detecting end surface defects of steel coil based on machine vision |
| CN111340796A (en)* | 2020-03-10 | 2020-06-26 | 创新奇智(成都)科技有限公司 | Defect detection method and device, electronic equipment and storage medium |
| CN112508926A (en)* | 2020-12-16 | 2021-03-16 | 广州大学 | Method, system and device for detecting surface scratches of metal stamping part and storage medium |
| CN112686858A (en)* | 2020-12-29 | 2021-04-20 | 熵智科技(深圳)有限公司 | Visual defect detection method, device, medium and equipment for mobile phone charger |
| CN113686869A (en)* | 2021-07-19 | 2021-11-23 | 浙江中新电力工程建设有限公司配电分公司 | A device for identifying micro-defects in insulating blankets |
| CN115358982A (en)* | 2022-08-16 | 2022-11-18 | 佛山市南海区广工大数控装备协同创新研究院 | Motor core crack defect detection method and device and related equipment |
| CN116823742A (en)* | 2023-06-07 | 2023-09-29 | 上海晨兴希姆通电子科技有限公司 | Surface defect detection method and system for WLCSP chips after sealing and cutting |
| Publication | Publication Date | Title |
|---|---|---|
| CN107478657A (en) | Stainless steel surfaces defect inspection method based on machine vision | |
| CN117541588B (en) | Printing defect detection method for paper product | |
| CN109507192B (en) | A method for detecting surface defects of magnetic cores based on machine vision | |
| CN114881915B (en) | A method for detecting defects in the window area of mobile phone glass cover based on symmetry | |
| CN108665458B (en) | Method for extracting and identifying surface defects of transparent body | |
| CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
| CN114937055A (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN106247969B (en) | A deformation detection method of industrial magnetic core components based on machine vision | |
| CN115684176B (en) | Online visual detection system for film surface defects | |
| CN108629775A (en) | A kind of hot high-speed rod surface image processing method | |
| CN104198497B (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN104458766B (en) | A kind of cloth surface flaw detection method based on structural texture method | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN104134211B (en) | A Strip Defect Detection Method Based on Gaussian Filter Multi-resolution Filtering | |
| CN104318556B (en) | Silicon steel plate surface defect image detection method under oil pollution interference | |
| CN104964980B (en) | A kind of spark plug plate defectses detection method based on machine vision | |
| CN101387493A (en) | Non-contact photoelectric detection method for shape, position and size of iron tower component holes | |
| CN114565563B (en) | Color steel plate surface abnormity detection method based on artificial intelligence | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN111476792B (en) | A Method for Extracting the Image Profile of Strip Steel | |
| CN112669265B (en) | A method for surface defect detection based on Fourier transform and image gradient features | |
| CN109472788B (en) | A method for detecting flaws on the surface of aircraft rivets | |
| WO2017120796A1 (en) | Pavement distress detection method and apparatus, and electronic device | |
| CN109584215A (en) | Online visual inspection system of circuit board | |
| CN108020554A (en) | A kind of steel strip surface defect recognition detection method |
| 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | Application publication date:20171215 | |
| WD01 | Invention patent application deemed withdrawn after publication |