CN116703930B - Automobile rearview mirror mold forming detection method - Google Patents
Automobile rearview mirror mold forming detection method Download PDFInfo
- Publication number
- CN116703930B CN116703930B CN202310993049.0A CN202310993049A CN116703930B CN 116703930 B CN116703930 B CN 116703930B CN 202310993049 A CN202310993049 A CN 202310993049A CN 116703930 B CN116703930 B CN 116703930B
- Authority
- CN
- China
- Prior art keywords
- window
- corner points
- chessboard
- rearview mirror
- distance
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06T2207/30248—Vehicle exterior or interior
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
本发明涉及图像处理技术领域，具体涉及一种汽车后视镜模具成型检测方法，包括：采集汽车后视镜图像，进行灰度化处理，对灰度图像进行Harris角点检测，对汽车后视镜图像的灰度图像进行分割，根据窗口内角点的棋盘距离变化情况获取中心角点，分析窗口与窗口间中心角点的权重关系来自适应获取窗口程度确定目标缺陷区域并进行伪彩色标记处理。本发明通过获取灰度图像中Harris算子在目标区域和边缘噪声区域间的角点间差异情况，并获取角点位置通过自适应的棋盘距离对目标区域进行判断，可以准确的得到目标缺陷区域，避免边缘噪声区域对目标区域的干扰。
The invention relates to the technical field of image processing, and specifically relates to a method for detecting automobile rearview mirror mold molding, which includes: collecting automobile rearview mirror images, performing grayscale processing, performing Harris corner point detection on the grayscale image, and performing The grayscale image of the mirror image is segmented, the central corner point is obtained according to the change of the checkerboard distance of the corner point in the window, and the weight relationship between the central corner point between the window and the window is analyzed to adaptively obtain the window degree to determine the target defect area and perform pseudo-color marking processing. This invention can accurately obtain the target defect area by obtaining the difference between the corner points of the Harris operator in the grayscale image between the target area and the edge noise area, and obtaining the corner point position to judge the target area through adaptive checkerboard distance. , to avoid the interference of edge noise areas on the target area.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for detecting molding of an automobile rearview mirror mold.
Background
A series of machining operations are carried out on the surface of a rearview mirror model in the machining production process of the rearview mirror model, surface defects such as scratch and the like are inevitably generated in the machining process of the surface of the rearview mirror, whether defects are generated in the rearview mirror is usually detected manually, the traditional manual detection mode has the problems of low efficiency, time consumption and the like, the traditional angular point detection mode in digital image processing has the defect of low detection precision, noise points in images or edges and the like of the rearview mirror can be detected as target defects, and the automatic production requirements of a digital factory are difficult to meet.
According to the invention, through an image processing technology, the improved Harris corner operator is utilized to carry out mold forming detection on the rearview mirror mold, and the self-adaptive chessboard distance of the target area is scratched and judged according to the detection target change degree of the corner in each area. The defect problem on the surface of the rearview mirror model can be effectively found by improving the corner detection method, and the quality and the performance of the model are ensured to meet the standards and requirements.
Disclosure of Invention
The invention provides a method for detecting molding of an automobile rearview mirror mold, which aims to solve the existing problems.
The invention relates to a method for detecting the molding of an automobile rearview mirror mold, which adopts the following technical scheme:
the embodiment of the invention provides a method for detecting the molding of an automobile rearview mirror mold, which comprises the following steps:
acquiring a gray image of an automobile rearview mirror image and all angular points in the gray image, and presetting windows to divide the gray image to obtain windows of a plurality of automobile rearview mirror gray images;
obtaining the chessboard distance between two corner points according to the position information of any two corner points in the window, obtaining the chessboard distance degree between the corner points in the window according to the average chessboard distance, and obtaining the reference corner point of the window according to the chessboard distance degree;
obtaining the degree of density of corner points in the window, obtaining the chessboard distance between any two reference corner points in the window according to the position information of the two reference corner points, and obtaining the degree of correlation of the distance between the reference corner points in the window according to the chessboard distance between the reference corner points;
obtaining window degree of the automobile rearview mirror gray level image according to the density degree of the corner points in the window and the correlation degree of the reference corner point distance in the window, and obtaining a self-adaptively identified corner point window according to the window degree of the automobile rearview mirror gray level image;
taking the self-adaptive identified angular point window as a defect area window of the automobile rearview mirror image, and taking an area formed by all the defect area windows as a target defect area;
the chessboard distance degree between the corner points in the window is obtained according to the average chessboard distance, and the method comprises the following specific steps:
wherein ,representing the%>Corner points and->The degree of the chessboard distance between the individual corner points +.>Representing the%>Corner points and->Chessboard distance between corner points->Mean board distance representing corner points in window, +.>Representing the total number of corner points in the window, +.>Representing the total number of chessboard distances of corner points in the window;
the method for obtaining the reference corner of the window according to the chessboard distance degree comprises the following specific steps:
obtaining the chessboard distance degree among all the angular points in the window, presetting a k value, and taking the angular points corresponding to k chessboard distance degrees with the smallest chessboard distance degree as reference angular points of the window;
the method for obtaining the correlation degree of the distance between the reference corners in the window according to the chessboard distance between the reference corners comprises the following specific steps:
wherein ,representing the +.sup.th in the checkerboard distance between all reference corner points within the window>Distance of chessboard (I/O)>For the total number of board distances between reference corners in the window, < >>Indicate->The ratio of the individual board distances in board distances between all reference corner points,representing the correlation degree of the distance between the reference angular points in the window;
the window degree of the automobile rearview mirror gray level image is obtained according to the degree of the density of the corner points in the window and the degree of the correlation of the distance between the reference corner points in the window, and the method comprises the following specific steps:
wherein ,window level representing grey level image of automobile rearview mirror, < >>Representing reference corner distances within a windowDegree of relatedness (I)>Represents the degree of intensity of corner points in the window, +.>An exponential function with a base representing a natural constant.
Further, the specific acquisition method of the gray level image of the automobile rearview mirror image and all the angular points in the gray level image is as follows:
and shooting the produced and molded automobile rearview mirror by using an industrial camera to obtain an automobile rearview mirror image, further carrying out graying treatment on the automobile rearview mirror image to obtain a gray image of the automobile rearview mirror image, and carrying out Harris corner detection on the gray image to obtain all corners in the gray image.
Further, the preset window divides the gray level image to obtain a plurality of windows of the automobile rearview mirror gray level image, and the method comprises the following specific steps:
the method comprises the steps of performing coordinate system processing on a gray level image of an automobile rearview mirror image, taking the upper left corner of the gray level image as a coordinate origin, taking the left corner as an X axis from left to right, establishing a coordinate system for a Y axis from top to bottom, and presetting an initial window size as followsDividing the gray level image by using the initial window to obtain a plurality of +.>A window of size.
Further, the specific method for obtaining the average chessboard distance of the corner in the window is as follows:
obtaining the chessboard distance between all the corners in the window and the total number of the chessboard distances between the corners in the window, and recording the ratio of the sum of the chessboard distances between all the corners in the window and the total number of the chessboard distances between the corners in the window as the average chessboard distance between the corners in the window.
Further, the specific method for obtaining the degree of density of the corner points in the window is as follows:
acquiring the number of corner points in the window, acquiring the total number of pixel points in the window, and recording the number of the corner points in the window and the total number of the pixel points in the window as the degree of density of the corner points in the window.
Further, the method for obtaining the corner window adaptively identified according to the window degree of the gray level image of the automobile rearview mirror comprises the following specific steps:
taking outA window corresponding to a preset threshold interval is used as a corner window identified by the self-adaptive chessboard, and the window is +.>The window level of the gradation image of the automobile rearview mirror is represented.
The technical scheme of the invention has the beneficial effects that: according to the invention, an image processing technology is utilized, the acquired automobile rearview mirror die image is processed, the difference condition of Harris operator between the target area and the edge noise area in the gray level image is acquired, the target area is judged by acquiring the angular point position through the self-adaptive chessboard distance, the probability of the target defect area is analyzed by combining the change condition of the gray level value area of the original image, the target defect area can be accurately obtained, the interference of the edge noise area on the target area is avoided, and finally, the target area is subjected to pseudo-color processing, so that the positioning and observation of defects by subsequent staff are facilitated.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart showing steps of a method for detecting molding of a mold for an automobile rearview mirror according to an embodiment of the invention;
fig. 2 is a gray scale reference diagram of the automobile rearview mirror mold provided by the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of the method for detecting the molding of the automobile rearview mirror mold according to the invention in detail by combining the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of a mold forming detection method for an automobile rearview mirror, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for detecting molding of a mold for an automobile rearview mirror according to an embodiment of the invention is shown, the method includes the following steps:
and S001, collecting an automobile rearview mirror image, carrying out gray processing, and carrying out Harris corner detection on the gray image.
In this embodiment, the image processing technology is used to detect the mold of the automobile rearview mirror, and the image of the automobile rearview mirror is collected first.
Specifically, an industrial camera is utilized to shoot a produced and molded automobile rearview mirror to obtain an automobile rearview mirror image, further, the automobile rearview mirror image is subjected to gray processing to obtain a gray image of the automobile rearview mirror image, and then Harris corner points of the gray image are detected to obtain all the corner points in the gray image.
The scratch of the automobile rearview mirror is a surface defect such as scratch generated by the fact that the rearview mirror touches an obstacle in the processing process. In the gray level image, the difference of gray level values can be generated between the surface texture features of the scratch area and the surrounding normal area, please refer to fig. 2, fig. 2 is a gray level reference diagram of the automobile rearview mirror mold of the embodiment, fig. 2 mainly includes three areas, a black background area, a normal automobile rearview mirror mold area and a scratch area, defect detection can be performed on the obvious scratch area by edge detection and other methods, the scratch area mainly processed and analyzed in the embodiment is slightly scratched, the difference of gray level values can be generated between the surface texture features of the scratch area and the surrounding normal area due to the fact that the scratch area is not obvious, certain interference angular points can be generated by the edge and noise of the rearview mirror, and the conventional Harris angular point detection can not judge whether the angular points belong to target defects or interference sources, so that the target area is identified by adjusting the adaptive chessboard distance of the Harris operator.
So far, all corner points in the gray image are obtained.
Step S002, dividing the grayscale image of the automobile rearview mirror image.
The method is characterized in that tile segmentation processing is carried out on a gray level image of an automobile rearview mirror image, the distribution condition of the inner corners of a window is analyzed by selecting a tile window with the same size, and the information of the inner corners of the segmented window is obtained to judge and analyze a target area.
Specifically, the gray level image of the automobile rearview mirror image is subjected to coordinate system processing, the upper left corner of the gray level image is taken as the origin of coordinates, the left to right is taken as the X axis, the coordinate system is established for the Y axis from top to bottom, and the size of the preset initial window is as followsDividing the gray level image by using the initial window to obtain a plurality of +.>A window of size, simultaneously for several +.>Windows of size in left to right, top to bottomIs to a plurality of->The window with the size is numbered. In this embodiment, when the element in the gray-scale image is segmented by using the initial window, the boundary of the gray-scale image may be exceeded, and in this embodiment, the portion of the gray-scale image exceeding the boundary is interpolated by using the quadratic linear interpolation method to fill data.
To this end, a plurality ofThe sorting of the windows is completed simultaneously with the size of the windows.
And step S003, obtaining a reference corner point according to the chessboard distance change condition of the corner points in the window.
It should be noted that, the chessboard distance between the corner points is judged according to the distribution of all the corner points in the window. In Harris corner detection, the positioning of the corner is often extremely important in relation to the gray gradient change of the pixel points in the gray image, if the window is in a target defect area, the gray gradient change of the defect is more severe, the corner existing in the window is often denser, however, random noise sources often exist in the image or pseudo corner points appear at the edge of the rearview mirror in the image, and the random noise sources do not belong to the detected target area. And screening the pseudo-corner points and the noise interference source isocenter in the corner point detection through the self-adaptive chessboard distance to obtain a real target defect area.
It should be further noted that, because the defective target area is distributed in the bright and clean surface area of the rearview mirror in the image, the gray gradient of the pixel points of the target area is more intense, and the density of the number of corner points of the target area is higher. The gradient change of the pixel points in the edge noise area in the image is more severe, but noise is randomly distributed, so that the density of the number of corner points in the window is smaller. And through the analysis of the difference of the angular points between the two, the subsequent chessboard distance recognition processing is carried out on the area where the angular point is located by utilizing the segmentation window, so as to obtain the preference degree of the target area.
It should be noted that, according to the differential distribution situation of the corner points in the window, the corner points in the window in the image are detected by using the chessboard distance, when the corner points appear in the window, the corner points need to be marked, then the degree of density and the chessboard distance of the corner points in the window are identified, the corner points in the scratch target area are always in a higher density state in the window and the chessboard distance is closer, some noise sources at the edge are always more discrete, the corner point density state of the noise sources is lower, and the chessboard distance is farther.
Specifically, taking any window as an example, the chessboard distance between two corner points is obtained according to the position information of any two corner points in the window, and the chessboard distance is specifically as follows:
wherein ,representing the chessboard distance between any two corner points within the window, < >> andRepresenting the coordinates of any two corner points within the window, < >>Indicating that the maximum value is taken>The representation takes absolute value.
Further, an average chessboard distance is obtained according to the chessboard distance between two corner points, which is specifically as follows:
wherein ,mean board distance representing corner points in window, +.>Representing the%>Corner points and->The chessboard distance between the corner points and +.>，Representing the total number of corner points in the window, +.>Representing the total number of chessboard distances of corner points in the window.
Further, the chessboard distance degree is obtained according to the average chessboard distance, which is specifically as follows:
wherein ,representing the%>Corner points and->The degree of the chessboard distance between the individual corner points +.>Representing the%>Corner points and->Chessboard distance between corner points->Mean board distance representing corner points in window, +.>Representing the total number of corner points in the window, +.>Representing the total number of chessboard distances of corner points in the window. Obtaining the chessboard distance degree among all the corner points in the window, taking the corner points corresponding to k chessboard distance degrees with the smallest chessboard distance degree as the reference corner points of the window, and in the embodiment, describing k=5 as an example.
The target area is identified by the self-adaptive chessboard distance according to the position distribution condition of the corner points in the image after Harris corner point detection. When the correlation degree of the chessboard distances between the angular points is higher, the target degree of the region is larger, and when the correlation degree of the chessboard distances between the angular points is smaller, the target degree of the region is smaller, and the probability of belonging to an interference source is larger.
Specifically, the degree of density of the corner points in the window is obtained according to the number of the corner points in the window, and the method specifically comprises the following steps:
wherein ,represents the degree of intensity of corner points in the window, +.>Representing the number of corner points within the window. It should be noted that when the degree of intensity of corner points in the window is +.>The larger the scratch defect angleThe larger the probability of a point window, the denser the corner points in the window +.>The smaller the probability of belonging to an isolated interferer corner window is, the greater.
Thus, the degree of density of the center corner points and the corner points in the window is obtained.
And S004, determining a target defect area by analyzing the weight relation of the reference angular points in the window and adaptively acquiring the window degree, and performing pseudo-color marking processing.
It should be noted that, according to the gray level image, edge information such as some noise interference sources is also identified as corner points, but the positions of the corner points do not belong to the target area, and the corner points of the interference sources in the window are often less and are often far away from the target defect area. The defects are represented as a region in the original image, and the distances among the center angular points of the target defect regions are similar and denser.
Specifically, the chessboard distance between two reference corner points is obtained according to the position information of any two reference corner points in the window, and the chessboard distance is specifically as follows:
wherein ,representing the checkerboard distance between any two reference corner points within a window,/-> andRepresenting the coordinates of any two reference corner points, +.>Indicating that the maximum value is taken>Representation taking outAnd (5) pairing values. Similarly, the chessboard distances among all the reference angular points in the window are obtained, and the chessboard distances among all the reference angular points are built into a set +.>，Representing +.f. in the checkerboard distance between all reference corner points>Distance of chessboard (I/O)>Is the total number of chessboard distances between the reference corner points.
Further, the degree of correlation of the distance between the reference angular points is obtained according to the chessboard distance between the reference angular points, and is specifically as follows:
wherein ,representing the +.sup.th in the checkerboard distance between all reference corner points within the window>Distance of chessboard (I/O)>For the total number of board distances between reference corners in the window, < >>Indicate->The ratio of the individual board distances in board distances between all reference corner points,indicating how relevant the reference corner is to be from within the window. It should be noted that when the reference corner is far from the relevant degree +.>The more the trend toward 0, the more>The more towards 0 or 1, when +.>The closer to 0, the smaller the chessboard distance between the reference corner points, the more concentrated the reference corner points, and the closer and denser the distance between the corner points of the target defect area, therefore, the +.>The more 0 is approached, the concentration relation of the corner points of the target defect area can be reflected, when +.>The closer to 1, the smaller the chessboard distance among all the reference angular points is, the larger the chessboard distance among only a few of the reference angular points is, so that the more concentrated the angular points are, the larger the probability of the angular points of the reference angular points in the set, which belong to the target defect area, and the smaller the probability of the angular points of the interference source is.
Further, according to the degree of density of the corner points in the window and the degree of correlation of the distance between the reference corner points in the window, the window degree of the gray level image of the automobile rearview mirror is obtained, and according to the window degree, the corner point window identified by the self-adaptive chessboard is obtained, specifically as follows:
wherein ,window level representing grey level image of automobile rearview mirror, < >>Representing the degree of correlation of the distance between reference corner points in a window, +.>Represents the degree of intensity of corner points in the window, +.>An exponential function, representing the natural constant as a base, is used for normalization. It should be noted that, when the window level is larger, the probability of the corner window belonging to the target defect is larger. Further, take->And the corresponding window is used as the corner window identified by the self-adaptive chessboard, and all the corner windows identified by the self-adaptive chessboard are obtained.
Further, the area formed by the corner windows identified by the self-adaptive chessboard is used as a target defect area, the target defect area is subjected to pseudo-color processing, and the defect area in the automobile rearview mirror image can be effectively identified through the pseudo-color processing, so that the contrast ratio of the image is enhanced, and the effect of displaying the defect area is improved.
Thus, the molding detection of the automobile rearview mirror mold is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310993049.0A CN116703930B (en) | 2023-08-09 | 2023-08-09 | Automobile rearview mirror mold forming detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310993049.0A CN116703930B (en) | 2023-08-09 | 2023-08-09 | Automobile rearview mirror mold forming detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703930A CN116703930A (en) | 2023-09-05 |
| CN116703930B true CN116703930B (en) | 2023-10-31 |
Family
ID=87843705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310993049.0A Active CN116703930B (en) | 2023-08-09 | 2023-08-09 | Automobile rearview mirror mold forming detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703930B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120147309B (en) * | 2025-05-13 | 2025-09-16 | 东莞汇美模具制造股份有限公司 | A method for detecting rearview mirror mold precision based on machine vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103674961A (en) * | 2012-09-14 | 2014-03-26 | 株式会社其恩斯 | Appearance inspection device, appearance inspection method, and program |
| CN110276750A (en) * | 2019-06-17 | 2019-09-24 | 浙江大学 | A kind of extraction of any inclination angle wafer straight line side length and crystal grain area partition method |
| EP3556576A1 (en) * | 2018-04-18 | 2019-10-23 | Bridgestone Europe NV/SA | Process and system for the detection of defects in a tyre |
| CN112052782A (en) * | 2020-08-31 | 2020-12-08 | 安徽江淮汽车集团股份有限公司 | Around-looking-based parking space identification method, device, equipment and storage medium |
| WO2021138990A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Adaptive detection method for checkerboard sub-pixel corner points |
| CN113592826A (en) * | 2021-08-02 | 2021-11-02 | 佛山名奥弹簧开发有限公司 | Method and system for identifying surface defects of wire |
| CN115311292A (en) * | 2022-10-12 | 2022-11-08 | 南通创铭伊诺机械有限公司 | Strip steel surface defect detection method and system based on image processing |
| CN115984271A (en) * | 2023-03-20 | 2023-04-18 | 山东鑫科来信息技术有限公司 | Metal burr identification method based on angular point detection |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4562126B2 (en) * | 2004-09-29 | 2010-10-13 | 大日本スクリーン製造株式会社 | Defect detection apparatus and defect detection method |
| CN111243032B (en) * | 2020-01-10 | 2023-05-12 | 大连理工大学 | Full-automatic detection method for checkerboard corner points |
-
2023
- 2023-08-09 CN CN202310993049.0A patent/CN116703930B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103674961A (en) * | 2012-09-14 | 2014-03-26 | 株式会社其恩斯 | Appearance inspection device, appearance inspection method, and program |
| EP3556576A1 (en) * | 2018-04-18 | 2019-10-23 | Bridgestone Europe NV/SA | Process and system for the detection of defects in a tyre |
| CN110276750A (en) * | 2019-06-17 | 2019-09-24 | 浙江大学 | A kind of extraction of any inclination angle wafer straight line side length and crystal grain area partition method |
| WO2021138990A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Adaptive detection method for checkerboard sub-pixel corner points |
| CN112052782A (en) * | 2020-08-31 | 2020-12-08 | 安徽江淮汽车集团股份有限公司 | Around-looking-based parking space identification method, device, equipment and storage medium |
| CN113592826A (en) * | 2021-08-02 | 2021-11-02 | 佛山名奥弹簧开发有限公司 | Method and system for identifying surface defects of wire |
| CN115311292A (en) * | 2022-10-12 | 2022-11-08 | 南通创铭伊诺机械有限公司 | Strip steel surface defect detection method and system based on image processing |
| CN115984271A (en) * | 2023-03-20 | 2023-04-18 | 山东鑫科来信息技术有限公司 | Metal burr identification method based on angular point detection |
Non-Patent Citations (2)
| Title |
|---|
| "Harris Operator Corner Detection using Sliding Window Method";Jyoti Malik.et al;《International Journal of Computer Applications》;第22卷(第1期);全文 * |
| "机器视觉技术在注塑成型加工中的研究进展";刘志文等;《塑料工业》;第49卷(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703930A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112819772B (en) | High-precision rapid pattern detection and recognition method | |
| CN115063421B (en) | Pole piece region detection method, system and device, medium and defect detection method | |
| CN103914827B (en) | The visible detection method of weather strip for automobile profile defects | |
| CN114820773B (en) | Silo transport vehicle carriage position detection method based on computer vision | |
| CN117058147B (en) | Environment-friendly plastic product defect detection method based on computer vision | |
| CN115690105B (en) | Milling cutter scratch detection method based on computer vision | |
| CN115290663B (en) | Mini LED wafer appearance defect detection method based on optical detection | |
| CN115100191B (en) | Metal casting defect identification method based on industrial detection | |
| CN115082451B (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN120070391B (en) | Injection molded parts detection system and method | |
| CN117314894B (en) | A quick detection method for watch bottom cover defects | |
| CN117522864B (en) | European pine plate surface flaw detection method based on machine vision | |
| CN115274486B (en) | Semiconductor surface defect identification method | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN117522778A (en) | A hollow brick defect detection system | |
| CN113129265A (en) | Method and device for detecting surface defects of ceramic tiles and storage medium | |
| CN117635609B (en) | Visual inspection method for production quality of plastic products | |
| CN116703930B (en) | Automobile rearview mirror mold forming detection method | |
| CN117218086A (en) | A visual detection and evaluation method for scratch damage on the surface of ceramic materials | |
| CN120912615A (en) | Wafer defect identification method and system under multi-feature fusion | |
| CN117115172B (en) | Donkey-hide gelatin quality detection method and system based on machine vision | |
| CN116883401B (en) | Industrial product production quality detection system | |
| CN117333471A (en) | A backlight Mura defect detection method based on image reconstruction | |
| CN117325184A (en) | Visual perception system and method for fermented grain discharging robot facing complex environment |
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 |