CN112581473A - Method for realizing surface defect detection gray level image positioning algorithm - Google Patents
Method for realizing surface defect detection gray level image positioning algorithm Download PDFInfo
- Publication number
- CN112581473A CN112581473A CN202110196411.2A CN202110196411A CN112581473A CN 112581473 A CN112581473 A CN 112581473A CN 202110196411 A CN202110196411 A CN 202110196411A CN 112581473 A CN112581473 A CN 112581473A
- Authority
- CN
- China
- Prior art keywords
- detection
- positioning algorithm
- algorithm
- defining
- axis
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
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 Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for realizing a surface defect detection gray level image positioning algorithm, which comprises the following specific steps of: firstly, defining a matrix, wherein the matrix is used for extracting pixel mean value information of corresponding positions of an image; secondly, defining algorithm parameters, wherein the algorithm parameters comprise a detection direction, a detection area and an edge gradient threshold; thirdly, adopting a proper positioning algorithm according to the actual situation; aiming at the image with relatively clean edges, a mean value positioning algorithm is used; aiming at the image with complex background, a relative positioning algorithm is used; when the corner or the threaded column cannot be directionally positioned, a maximum (small) value positioning algorithm is used. The method based on the gray image positioning algorithm for realizing the surface defect detection can position the workpiece in the image so as to be beneficial to accurately detecting the surface defect of the workpiece in the image.
Description
Technical Field
The invention relates to the technical field of positioning algorithms, in particular to a method for realizing a surface defect detection gray level image positioning algorithm.
Background
In the visual inspection mass production project, because different cameras have certain deviation or rotation in the position of the workpiece in the image in the feeding process every time, the accurate detection of defects is obviously not facilitated, and therefore, when the picture is obtained, the position of the workpiece in the image needs to be positioned.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to solve the problems in the background art, a method for realizing a gray image positioning algorithm for detecting surface defects is provided, which can position a workpiece in an image so as to facilitate the accurate detection of the surface defects of the workpiece in the image.
The technical scheme adopted by the invention for solving the technical problems is as follows: a method for realizing a surface defect detection gray level image positioning algorithm comprises the following specific steps:
firstly, defining a matrix, wherein the matrix is used for extracting pixel mean value information of corresponding positions of an image;
secondly, defining algorithm parameters, wherein the algorithm parameters comprise a detection direction, a detection area and an edge gradient threshold;
thirdly, adopting a proper positioning algorithm according to the actual situation; aiming at the image with relatively clean edges, a mean value positioning algorithm is used; aiming at the image with complex background, a relative positioning algorithm is used; when the corner or the threaded column cannot be directionally positioned, a maximum (small) value positioning algorithm is used.
More specifically, in the foregoing technical solution, in the first step, when detecting the upper and lower edges, the matrix is set to be 2n × n.
More specifically, in the foregoing technical solution, in the first step, when detecting the left and right edges, the matrix is set to be n × 2 n.
More specifically, in the above technical solution, in the second step, the method for defining the detection direction includes: the X-axis is defined as the horizontal left and right detection directions, and the Y-axis is defined as the vertical up and down detection directions.
More specifically, in the above technical solution, in the second step, the method for defining the detection area includes: the edge position is detected in the designated area, and the method is suitable for irregular-shaped workpieces or image scenes with large background noise as much as possible.
More specifically, in the above technical solution, in the second step, the method for defining the edge gradient threshold includes: an edge gradient change detection threshold is set, and an edge is detected when the gradient exceeds the threshold.
More specifically, in the above technical solution, in the third step, the method of the mean value location algorithm includes the following specific steps:
the method comprises the following steps of firstly, defining the detected X and Y directions;
secondly, defining a detection area, wherein the general detection area is defined near the positioning point as much as possible;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the mean location algorithm is:
the system firstly calculates edge positions Lx1(X, Y) and Lx2(X, Y) … … LxN (X, Y) detected by a plurality of detection points which are evenly distributed on an X axis, then calculates the difference mean value of a plurality of adjacent Lx on the Y axis, abandons the points of which the adjacent difference values are larger than the difference mean value, and finally calculates the mean value of the rest Lx points on the Y axis;
the system firstly obtains edge positions Ly1(X, Y) and Ly2(X, Y) … … LyN (X, Y) detected by a plurality of detection points which are evenly distributed on the Y axis, then calculates the difference value average value of a plurality of adjacent Ly on the X axis, abandons the points of which the adjacent difference values are larger than the difference value average value, and finally obtains the average value of the rest Ly points on the X axis.
More specifically, in the above technical solution, in the method of the mean value location algorithm, the method of defining the X and Y directions of detection is as follows: if the position is positioned at the lower left corner, the X detection direction is from left to right, and the Y detection direction is from bottom to top; if the position is positioned at the upper left corner, the X detection direction is from left to right, and the Y detection direction is from top to bottom; if the position is located at the lower right corner, the X detection direction is from right to left, and the Y detection direction is from bottom to top; if positioned in the upper right corner, the X detection direction is from right to left and the Y detection direction is from top to bottom.
More specifically, in the above technical solution, in the third step, the method of the relative positioning algorithm includes the following specific steps:
the method comprises the following steps of firstly, defining a detected reference X axis or Y axis;
secondly, defining a detected area;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the relative positioning algorithm is: the relatively stable edge is selected first for detection.
More specifically, in the above technical solution, in the third step, the method of the maximum (small) value location algorithm includes the following specific steps:
the method comprises the following steps of firstly, defining a detected reference X axis or Y axis;
secondly, defining a detected area;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the maximum (small) value location algorithm is: when the corner or the threaded column cannot be positioned in the X and Y directions, the algorithm is set in the detection area according to the density to find a plurality of detection points, the point where the maximum (small) X is positioned in horizontal scanning, and the point where the maximum (small) Y is positioned in vertical scanning.
The invention has the beneficial effects that: the method for realizing the gray image positioning algorithm for detecting the surface defects can position the workpiece in the image so as to be beneficial to accurately detecting the surface defects of the workpiece in the image; because the position of the real object in the picture changes every time when the picture is actually taken on site, the outline of the real object can be effectively found through a positioning algorithm, each position of the real object in the picture is subjected to fine grinding analysis and detection, meanwhile, the requirement on the stability of the optical machinery is greatly reduced, and the labor force for site implementation is saved.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram of the definition of a detection zone in a localization algorithm;
FIG. 2 is a schematic diagram of a localization algorithm;
FIG. 3 is a schematic diagram of the logic of the mean location algorithm;
FIG. 4 is a schematic diagram of the relative positioning algorithm;
FIG. 5 is a schematic diagram of the relative positioning algorithm II;
fig. 6 is a schematic diagram of the principle of the maximum (small) value localization algorithm.
The reference numbers in the figures are: A. a horizontal detection zone; B. a vertical detection zone; C. detecting a horizontal edge; D. detecting a vertical edge; E. an object in the image; F. gradient changes of pixels in the image; H. a horizontal scanning direction; J. a horizontal scanning direction; K. vertical scanning direction; l, vertical scanning direction of 5 scanning lines; m, Y axial minimum; n, scanning lines by an algorithm; o, vertical scan direction.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
A method for realizing a gray image positioning algorithm for surface defect detection is disclosed, wherein the positioning algorithm is an edge detection algorithm and comprises the following specific steps:
the first step is to define a matrix for extracting the pixel mean information of the corresponding position of the image, so as to filter the influence of the tiny noise on the algorithm.
For upper and lower edge detection, the matrix may be set to 2n × n, where 2n represents a multiple of 2 pixels and n represents a multiple of pixels. Such as: the matrix may be set to 4 × 2.
For left and right edge detection, the matrix may be set to n × 2n, where n represents a multiple of pixels and 2n represents a multiple of 2 pixels. Such as: the matrix may be set to 2 x 4.
A second step, then, requires defining algorithm parameters including the detection direction (detected XY direction), the detection area (detection area in XY direction), and the edge gradient threshold (grayscale threshold).
I={{1,2,1,3},{2,2,3,2}} , G=average (I)=2
I denotes the pixel value distribution of a rectangular region (4 × 2) of the image, and G denotes the average pixel value of the rectangular region.
The definition method of the detection direction comprises the following steps: the X axis and the Y axis are respectively defined as a left detection direction, a right detection direction and an up detection direction and a down detection direction, namely the X axis is defined as a horizontal left detection direction, a horizontal right detection direction and the Y axis is defined as a vertical up detection direction and a vertical down detection direction. When the vertical edge of the object is detected, setting the detection direction from left to right or from right to left in the horizontal direction; when detecting the horizontal edge of the object, the vertical direction is set from top to bottom or from bottom to top.
Referring to fig. 1, the detection region (X, Y, Width, Height) is defined by: the edge positions are detected in the designated area (see a horizontal detection area at A in fig. 1, which contains a distinct horizontal edge of an object, and a vertical detection area at B in fig. 1, which contains a vertical edge of an object), so as to adapt to irregular-shaped workpieces or image scenes with large background noise as much as possible.
X represents the X coordinate and Y represents the Y coordinate.
The definition method of the edge gradient threshold is as follows: an edge gradient change detection threshold is set, and an edge is detected when the gradient exceeds the threshold.
And thirdly, adopting a proper positioning algorithm according to the actual situation.
Referring to fig. 2, a mean location algorithm is used for images with relatively clean edges (see horizontal edge detection at C in fig. 2 for calculating the Y coordinates of the anchor point; see vertical edge detection at D in fig. 2 for calculating the X coordinates of the anchor point).
The method of the mean value positioning algorithm comprises the following specific steps:
the method comprises the following steps of firstly, defining the X and Y directions of detection, and specifically comprises the following steps: if the position is positioned at the lower left corner, the X detection direction is from left to right, and the Y detection direction is from bottom to top; if the position is positioned at the upper left corner, the X detection direction is from left to right, and the Y detection direction is from top to bottom; if the position is located at the lower right corner, the X detection direction is from right to left, and the Y detection direction is from bottom to top; if positioned in the upper right corner, the X detection direction is from right to left and the Y detection direction is from top to bottom. The locating point is calculated by detecting the edge position of the real object in the picture, and the locating point can change along with the deviation of the position of the object in each picture, so that the locating point can change along with the real object in the picture linearly.
And a second step of defining a detection area, wherein the detection area is defined near the positioning point as much as possible. The positioning points of different pictures are different, and corners or obvious protruding positions are generally taken from the pictures as the positioning points according to the workpiece imaging effect. The anchor point is inside the detection area.
And step three, defining detection density, and evenly distributing detection points on the X and Y distances of the detection area.
Referring to FIG. 3, the mean location algorithm (E in FIG. 3 represents the object in the image; F in FIG. 3 represents the gradient change of the pixels in the image; N in FIG. 3 represents the scanning lines of the algorithm; the algorithm needs to detect the edge position information of the left side of the object, and when the scanning lines N of the algorithm scan from left to right, the algorithm calculates the edge position according to the gradient change of each pixel on each scanning line)
The algorithm logic is that the system firstly calculates the edge positions Lx1(X, Y) and Lx2(X, Y) … … LxN (X, Y) detected by a plurality of detection points which are evenly distributed on the X axis, then calculates the difference mean value of a plurality of adjacent Lx on the Y axis, abandons the points of which the adjacent difference values are larger than the difference mean value, and finally calculates the mean value of the rest Lx points on the Y axis;
the system firstly finds edge positions Ly1(X, Y) and Ly2(X, Y) … … LyN (X, Y) detected by a plurality of detection points which are evenly distributed on the Y axis, then calculates the difference mean value of a plurality of adjacent Ly on the X axis, abandons the points of which the adjacent difference values are larger than the difference mean value, and finally finds the mean value of the rest Ly points on the X axis;
see fig. 4, for background complex images, a relative positioning algorithm is used.
The method of the relative positioning algorithm comprises the following specific steps:
the first step, defining a reference X-axis or Y-axis of detection. The scan line width of the horizontal scan and the vertical scan is defined, for example, the scan line of the horizontal scan is from y =30 to y =60, the scan direction is from right to left (see H in fig. 4), for example, the scan line of the vertical scan is from x =300 to x =600, the scan direction is from top to bottom (see O in fig. 4)
And a second step of defining the detected area, such as a reference. The start and end positions of the horizontal scan and the vertical scan are defined. Such as from x =300 to x =600, from y =30 to y = 100.
And step three, defining detection density, and evenly distributing detection points on the X and Y distances of the detection area.
The logic of the relative positioning algorithm is: firstly, selecting a relatively stable edge to detect, if a horizontal X edge is relatively stable, detecting a transverse edge, and then confirming a longitudinal edge detection range by taking a Y coordinate of the transverse edge as a reference to detect.
Referring to fig. 5, after the detection areas at J are scanned horizontally and the X coordinate is obtained, the detection areas at K are defined based on the X coordinate and scanned vertically (offset from the X coordinate).
Referring to fig. 6, the maximum (small) value location algorithm is used when the corner or threaded post cannot be directionally located.
The method of the maximum (small) value positioning algorithm comprises the following specific steps:
the first step, defining a reference X-axis or Y-axis of detection. The scan line widths of the horizontal scan and the vertical scan are defined, for example, the scan line of the horizontal scan is from y =30 to y = 60.
And a second step of defining the detected area, such as a reference. The start and end positions of the horizontal scan and the vertical scan are defined. Such as from x =300 to x =600, from y =30 to y = 100.
And step three, defining detection density, and evenly distributing detection points on the X and Y distances of the detection area.
The logic of the maximum (small) value location algorithm is: when the corner or the threaded column cannot be positioned in the X and Y directions, the algorithm finds a plurality of detection points (see 5 scanning lines at L in FIG. 6) in the detection area according to density setting, positions the point where the largest (small) X is located in horizontal scanning, and positions the largest (small) Y is located in vertical scanning (see the minimum value in the Y-axis direction at M in FIG. 6).
The method based on the gray image positioning algorithm for realizing the surface defect detection can position the workpiece in the image so as to be beneficial to accurately detecting the surface defect of the workpiece in the image; because the position of the real object in the picture changes every time when the picture is actually taken on site, the outline of the real object can be effectively found through a positioning algorithm, each position of the real object in the picture is subjected to fine grinding analysis and detection, meanwhile, the requirement on the stability of the optical machinery is greatly reduced, and the labor force for site implementation is saved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention are equivalent to or changed within the technical scope of the present invention.
Claims (10)
1. A method for realizing a gray level image positioning algorithm for surface defect detection is characterized by comprising the following steps: the method comprises the following specific steps:
firstly, defining a matrix, wherein the matrix is used for extracting pixel mean value information of corresponding positions of an image;
secondly, defining algorithm parameters, wherein the algorithm parameters comprise a detection direction, a detection area and an edge gradient threshold;
thirdly, adopting a proper positioning algorithm according to the actual situation; aiming at the image with relatively clean edges, a mean value positioning algorithm is used; aiming at the image with complex background, a relative positioning algorithm is used; when the corner or the threaded column cannot be directionally positioned, a maximum (small) value positioning algorithm is used.
2. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the first step, the matrix is set to 2n × n when detecting the upper and lower edges.
3. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the first step, the matrix is set to be n × 2n when detecting the left and right edges.
4. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the second step, the definition method of the detection direction is as follows: the X-axis is defined as the horizontal left and right detection directions, and the Y-axis is defined as the vertical up and down detection directions.
5. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the second step, the definition method of the detection area is as follows: the edge position is detected in the designated area, and the method is suitable for irregular-shaped workpieces or image scenes with large background noise as much as possible.
6. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the second step, the edge gradient threshold is defined by: an edge gradient change detection threshold is set, and an edge is detected when the gradient exceeds the threshold.
7. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the third step, the mean value location algorithm is as follows:
the method comprises the following steps of firstly, defining the detected X and Y directions;
secondly, defining a detection area, wherein the general detection area is defined near the positioning point as much as possible;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the mean location algorithm is:
the system firstly calculates edge positions Lx1(X, Y) and Lx2(X, Y) … … LxN (X, Y) detected by a plurality of detection points which are evenly distributed on an X axis, then calculates the difference mean value of a plurality of adjacent Lx on the Y axis, abandons the points of which the adjacent difference values are larger than the difference mean value, and finally calculates the mean value of the rest Lx points on the Y axis;
the system firstly obtains edge positions Ly1(X, Y) and Ly2(X, Y) … … LyN (X, Y) detected by a plurality of detection points which are evenly distributed on the Y axis, then calculates the difference value average value of a plurality of adjacent Ly on the X axis, abandons the points of which the adjacent difference values are larger than the difference value average value, and finally obtains the average value of the rest Ly points on the X axis.
8. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 7, wherein: in the method of the mean value localization algorithm, the method for defining the X and Y directions of detection is as follows: if the position is positioned at the lower left corner, the X detection direction is from left to right, and the Y detection direction is from bottom to top; if the position is positioned at the upper left corner, the X detection direction is from left to right, and the Y detection direction is from top to bottom; if the position is located at the lower right corner, the X detection direction is from right to left, and the Y detection direction is from bottom to top; if positioned in the upper right corner, the X detection direction is from right to left and the Y detection direction is from top to bottom.
9. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the third step, the method of the relative positioning algorithm includes the following specific steps:
the method comprises the following steps of firstly, defining a detected reference X axis or Y axis;
secondly, defining a detected area;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the relative positioning algorithm is: the relatively stable edge is selected first for detection.
10. The method for realizing the gray scale image positioning algorithm for surface defect detection according to claim 1, wherein: in the third step, the method of the maximum (small) value positioning algorithm includes the following specific steps:
the method comprises the following steps of firstly, defining a detected reference X axis or Y axis;
secondly, defining a detected area;
defining detection density, and evenly distributing detection points on the distances X and Y of a detection area;
the logic of the maximum (small) value location algorithm is: when the corner or the threaded column cannot be positioned in the X and Y directions, the algorithm is set in the detection area according to the density to find a plurality of detection points, the point where the maximum (small) X is positioned in horizontal scanning, and the point where the maximum (small) Y is positioned in vertical scanning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110196411.2A CN112581473B (en) | 2021-02-22 | 2021-02-22 | Method for realizing surface defect detection gray level image positioning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110196411.2A CN112581473B (en) | 2021-02-22 | 2021-02-22 | Method for realizing surface defect detection gray level image positioning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112581473A true CN112581473A (en) | 2021-03-30 |
| CN112581473B CN112581473B (en) | 2021-05-18 |
Family
ID=75113952
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110196411.2A Active CN112581473B (en) | 2021-02-22 | 2021-02-22 | Method for realizing surface defect detection gray level image positioning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581473B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101029824A (en) * | 2006-02-28 | 2007-09-05 | 沈阳东软软件股份有限公司 | Method and apparatus for positioning vehicle based on characteristics |
| CN102971780A (en) * | 2011-07-11 | 2013-03-13 | 松下电器产业株式会社 | Display device |
| CN107832674A (en) * | 2017-10-16 | 2018-03-23 | 西安电子科技大学 | A kind of method for detecting lane lines |
| CN109934839A (en) * | 2019-03-08 | 2019-06-25 | 北京工业大学 | A kind of workpiece inspection method of view-based access control model |
| CN110763124A (en) * | 2019-11-22 | 2020-02-07 | 浙江梵隆汽车部件有限公司 | Rapid detection system and detection method for flatness and coaxiality of automobile steering wheel |
| CN110999273A (en) * | 2017-08-02 | 2020-04-10 | 歌乐株式会社 | Attachment detection device and vehicle system having same |
| CN211577000U (en) * | 2019-11-15 | 2020-09-25 | 湖南讯目科技有限公司 | Panel edge defect detection device and system |
| CN111968143A (en) * | 2020-07-22 | 2020-11-20 | 中国人民解放军国防科技大学 | Edge image extraction method and system based on correlated imaging |
| CN112258510A (en) * | 2020-12-22 | 2021-01-22 | 常州微亿智造科技有限公司 | Image anomaly detection method based on connected region algorithm |
-
2021
- 2021-02-22 CN CN202110196411.2A patent/CN112581473B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101029824A (en) * | 2006-02-28 | 2007-09-05 | 沈阳东软软件股份有限公司 | Method and apparatus for positioning vehicle based on characteristics |
| CN102971780A (en) * | 2011-07-11 | 2013-03-13 | 松下电器产业株式会社 | Display device |
| CN110999273A (en) * | 2017-08-02 | 2020-04-10 | 歌乐株式会社 | Attachment detection device and vehicle system having same |
| CN107832674A (en) * | 2017-10-16 | 2018-03-23 | 西安电子科技大学 | A kind of method for detecting lane lines |
| CN109934839A (en) * | 2019-03-08 | 2019-06-25 | 北京工业大学 | A kind of workpiece inspection method of view-based access control model |
| CN211577000U (en) * | 2019-11-15 | 2020-09-25 | 湖南讯目科技有限公司 | Panel edge defect detection device and system |
| CN110763124A (en) * | 2019-11-22 | 2020-02-07 | 浙江梵隆汽车部件有限公司 | Rapid detection system and detection method for flatness and coaxiality of automobile steering wheel |
| CN111968143A (en) * | 2020-07-22 | 2020-11-20 | 中国人民解放军国防科技大学 | Edge image extraction method and system based on correlated imaging |
| CN112258510A (en) * | 2020-12-22 | 2021-01-22 | 常州微亿智造科技有限公司 | Image anomaly detection method based on connected region algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112581473B (en) | 2021-05-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10775160B2 (en) | System and method for efficient surface measurement using a laser displacement sensor | |
| CN108362712B (en) | Substrate mother board and detection method thereof | |
| CN115170669B (en) | Identification and positioning method and system based on edge feature point set registration and storage medium | |
| CN106846412B (en) | Checkerboard angular point detection method and device | |
| WO2021179983A1 (en) | Three-dimensional laser-based container truck anti-hoisting detection method and apparatus, and computer device | |
| CN112581904B (en) | Moire compensation method for brightness gray scale image of OLED (organic light emitting diode) screen | |
| CN116165216B (en) | Liquid crystal display micro scratch flaw 3D detection method, system and computing equipment | |
| CN113137941B (en) | Method for testing product flatness based on point laser | |
| CN112833784B (en) | Steel rail positioning method combining monocular camera with laser scanning | |
| CN104331695A (en) | Robust round identifier shape quality detection method | |
| CN114463357B (en) | Method for determining dynamic information of medium pile in real time in dense medium coal dressing | |
| KR102023087B1 (en) | Method for camera calibration | |
| CN112797900B (en) | Multi-camera plate size measuring method | |
| CN112581473B (en) | Method for realizing surface defect detection gray level image positioning algorithm | |
| CN108230400B (en) | Self-adaptive coordinate reconstruction method suitable for laser cutting machine | |
| CN117474839A (en) | Workpiece defect detection method and device, electronic equipment and storage medium | |
| CN101685000B (en) | Computer system and method for image boundary scan | |
| KR101653861B1 (en) | Drawing data generating method, drawing method, drawing data generating apparatus and drawing apparatus | |
| US6571196B2 (en) | Size inspection/measurement method and size inspection/measurement apparatus | |
| CN116883295B (en) | Line scanning three-dimensional image acquisition vibration correction method and device and electronic equipment | |
| KR20200126921A (en) | A method for inspecting a skeleton wafer | |
| JP2009236550A (en) | Flaw detection method | |
| JP3031069B2 (en) | Appearance inspection method | |
| KR20070073078A (en) | Method for calibration of defected point coordinate for flat panel display | |
| JP3625237B2 (en) | Concavity and convexity measurement method and component storage method using the same |
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 |