CN116433584A - Surface defect detection method, system and storage medium for strip-shaped polishing template - Google Patents
Surface defect detection method, system and storage medium for strip-shaped polishing template Download PDFInfo
- Publication number
- CN116433584A CN116433584A CN202310122935.6A CN202310122935A CN116433584A CN 116433584 A CN116433584 A CN 116433584A CN 202310122935 A CN202310122935 A CN 202310122935A CN 116433584 A CN116433584 A CN 116433584A
- Authority
- CN
- China
- Prior art keywords
- contour
- defect
- detection area
- area
- main detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 325
- 238000001514 detection method Methods 0.000 title claims abstract description 288
- 238000005498 polishing Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 239000002023 wood Substances 0.000 claims abstract description 111
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000006073 displacement reaction Methods 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000013072 incoming material Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/30161—Wood; Lumber
-
- 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)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Optics & Photonics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application aims to provide a method, a system and a storage medium for detecting surface defects of an elongated polishing template, wherein the method comprises the following steps: acquiring the surface profile of a wood board to be detected; collecting point clouds of the wood board to be detected to represent real three-dimensional coordinates of the wood board to be detected; converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background; positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space; intercepting a contour line from the point cloud according to the wood board detection area to be detected; and obtaining defect information by calculating straight lines and fitting curves according to the intercepted contour lines. And the plurality of contours detect whether the object to be detected has defects or not by counting the number of the defect contours in all the contours and the number of the continuous defect contours. The invention can effectively improve the efficiency of detecting the surface defects of the strip-shaped polishing template.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method, a system and a storage medium for detecting surface defects of an elongated polishing template.
Background
In the wood processing process, the surface defects of the cut wood board need to be detected. Common wood board surface defects are: unevenness (e.g., bending deformation of a wood board), wormholes, cracks, bulges. In addition, burrs are present on the surface of the sawn board, which is manually or mechanically polished during the wood processing, but for various reasons, there are often insufficient polishing places, which affect the subsequent coloring and beauty, and thus the burr defect detection is also required.
The common defect detection flow is as follows: and acquiring an image of the surface of the wood board by using a camera, analyzing the image quality by combining an image processing program, and detecting the position where the defect exists. The image processing program is divided into a traditional image processing mode and a deep learning image processing mode, the scheme effectiveness is commonly established on the basis that the image can shoot out surface defects, but for the tiny but non-negligible defects in the depth direction of the wood board surface, the image imaging is difficult to show differences, so that the defects are not enough to be detected; in this regard, 3D cameras that can collect depth information of an object surface are used for wood defect detection, and common 3D cameras include a structured light camera and a laser displacement sensor. The process of wood board defect detection based on 3D cameras is approximately the same: collecting object surface depth data (such as depth map and point cloud data), detecting defects according to the depth map, acquiring a wood board surface gray level map and a height map (the height map contains surface depth information) by using a structured light camera, and detecting the defects by using an image processing mode; and acquiring data by using a laser displacement sensor, and performing defect detection by using an image processing program. Because of the self-restriction, the structured light camera has difficulty in considering the field of view and the precision for the slender object; the laser displacement sensor can acquire complete data, but performing defect detection based on an image processing program is difficult to expect for detection of surface burrs. And the laser displacement sensor adopts a contour mode to detect the conditions that a single defect exists and a detection area cannot be self-adaptive, and the like.
Disclosure of Invention
The invention aims to provide a method, a system and a storage medium for detecting surface defects of a strip polishing template, which are used for improving the efficiency of detecting the surface defects of the strip polishing template by utilizing the parallelism of a single contour line defect calculation and multi-contour comprehensive judgment defect detection algorithm and a single contour line defect calculation and multi-contour comprehensive judgment defect detection algorithm.
The application also provides a surface defect detection method of the strip-shaped polishing template, which comprises the following steps:
the method comprises the following steps:
acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
intercepting a contour line from the point cloud according to the wood board detection area to be detected;
dividing a region to be detected into a main detection region and a non-main detection region;
Calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
Optionally, the contour line is intercepted from the point cloud according to the detection area of the wood board to be detected, specifically:
dividing a wood board detection area to be detected into a main detection area and a non-main detection area;
intercepting contour set for sub-main detection, wherein the row-column index of any contour in the main detection is as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the line spacing of two adjacent contours of the point cloud, dx is the pointThe column spacing of two adjacent contours of the cloud, α, represents the tilt angle of the rectangle relative to the direction of motion.
Optionally, the calculating the defect size of the point set on each contour line in the main detection specifically includes:
Calculating the straightness of each contour line in the main detection: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
calculating the defect area of each contour line in the main detection: performing free curve fitting on the point set in the range of the contour line row and column; after fitting, the defect area of each contour line is calculated by taking the area formed by the contour line and the fitting curve as the defect area.
Optionally, the calculating of the defect area specifically includes: performing free curve fitting on the point set in the range of the contour line row and column; obtaining a fitting curve, after fitting, taking the area of the area above the fitting curve as positive, representing the bulge, the area of the area below the fitting curve as negative, representing the recess, the defect depth representing the maximum concave-convex size, and the defect width being the distance between adjacent intersection points; for the contour point of each 'defect' area, calculating the horizontal distance between the current contour point and the previous contour point on the contour line and the vertical distance between the current contour point and the fitting curve, multiplying the obtained horizontal distance by the vertical distance to obtain the area of the contour point, and summing the areas of all the contour points to obtain the defect area of the contour line.
Optionally, the main statistics detection inner contour line defect specifically includes:
carrying out statistical analysis on straightness and defect area information of each contour in main detection, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of straightness, area, defect depth and defect width of the contour in the main detection area is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH 4;
and (3) counting the output of the detection result of the inner outline of the main detection: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection has defects if any one of the defect contour number threshold value TH5 and the maximum value threshold value TH6 of the continuous defect contours is met.
In a second aspect, the present application further provides a system for detecting surface defects of an elongated sanding template, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a program of a surface defect detection method of an elongated polishing template, and the program of the surface defect detection method of the elongated polishing template realizes the following steps when being executed by the processor:
Acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
intercepting a contour line from the point cloud according to the wood board detection area to be detected;
dividing a region to be detected into a main detection region and a non-main detection region;
calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
Optionally, the contour line is intercepted from the point cloud according to the detection area of the wood board to be detected, specifically:
Dividing a wood board detection area to be detected into a main detection area and a non-main detection area; the method comprises the steps of carrying out a first treatment on the surface of the
Intercepting a contour set from a main detection area, wherein the row-column index of any contour in the main detection area is as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the row spacing of two adjacent contours of the point cloud, dx is the column spacing of two adjacent contours of the point cloud, and alpha represents the inclination angle of the rectangle relative to the motion direction.
Optionally, the calculating the defect size of the point set on each contour line in the main detection area specifically includes:
calculating the straightness of each contour line in the main detection area: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
the defect area is calculated specifically as follows: performing free curve fitting on the point set in the range of the contour line row and column; obtaining a fitting curve, after fitting, taking the area of the area above the fitting curve as positive, representing the bulge, the area of the area below the fitting curve as negative, representing the recess, the defect depth representing the maximum concave-convex size, and the defect width being the distance between adjacent intersection points; and calculating the horizontal distance between the current contour point and the previous contour point on the contour line and the vertical distance between the current contour point and the fitted curve, multiplying the obtained horizontal distance by the vertical distance to obtain the area of the contour point, and summing the areas of all the contour points to obtain the defect area of the contour line.
Optionally, the statistics of the defects of the inner contour line of the main detection area specifically includes:
carrying out statistical analysis on straightness and defect area information of each contour in a main detection area, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of straightness, area, defect depth and defect width of the contour in the main detection area is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH 4;
and (3) counting the output of the outline detection result in the main detection area: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection area has defects if any one of the contour line defect contour number in the main detection area is not smaller than the defect contour number threshold value TH5 and the maximum value of the continuous defect contour is not smaller than the maximum value threshold value TH6 of the continuous defect contour is met.
In a third aspect, the present application further provides a computer readable storage medium, where the computer readable storage medium includes a method program for detecting a surface defect of an elongated polishing template, where the method program for detecting a surface defect of an elongated polishing template, when executed by a processor, implements the steps of the method for detecting a surface defect of an elongated polishing template.
Therefore, the method, the system and the storage medium for detecting the surface defects of the strip-shaped polishing template are provided. The application provides a defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment. The single contour obtains defect information by calculating straightness and fitting curves, counts the number of defect contours, the number of continuous defect contours and the like in all contours, comprehensively judges whether the detected object has defects, eliminates accidental errors and obviously reduces the misjudgment rate. In addition, the parallelization of the defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment is realized. The efficiency of rectangular shape template surface defect detection of polishing has effectually been improved.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for detecting surface defects of a strip polishing template according to an embodiment of the present application;
fig. 2 is a schematic diagram of a detection area provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a pitch between two adjacent contour lines according to an embodiment of the present disclosure.
FIG. 4 is a schematic view of a free curve fit of a set of points within a range of contour lines provided by an embodiment of the present application;
fig. 5 is a block diagram of a surface defect detection system for an elongated polishing template according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, a flowchart of a method for detecting a surface defect of an elongated polishing template according to some embodiments of the present application is shown. The method for detecting the surface defects of the strip-shaped polishing template is used in terminal equipment, such as a computer terminal, a mobile phone terminal and the like. The method for measuring the contour degree of the workpiece comprises the following steps:
s101: acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
s102: converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
it should be noted that, the separation of the wood board data and the background is realized, because the wood board has a height relative to the background, and after the wood board is converted into the image, the gray values have obvious differences, so that the wood board and the background have clear boundaries, which is beneficial to extracting edges.
S103: positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
it should be noted that, the image edge method is adopted to locate the position information of the wood board,automatically generating a rectangular detection area, mapping the detection area into point cloud data to obtain a plank detection area in a three-dimensional space, wherein P is as shown in FIG. 2 1 P 2 P 3 P 4 The inclined inner frame rectangle is constituted to represent the detection area.
S104: intercepting a contour line from the point cloud according to the wood board detection area to be detected;
s105: calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
s106: calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
s107: and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
According to the embodiment of the invention, the contour line is intercepted from the point cloud according to the wood board detection area to be detected, specifically:
Dividing the wood board detection area to be detected, and dividing the to-be-detected area into a main detection area and a non-main detection area, wherein the area of the main detection area is larger than that of the non-main detection area.
Intercepting a contour set from a main detection area, wherein the row-column index of any contour in the main detection area is as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the line spacing of two adjacent contours of the point cloud,dx is the column spacing of two adjacent contours of the point cloud, and alpha represents the inclination angle of the rectangle relative to the motion direction.
It should be noted that, as a specific implementation, the application considers board inclination, and as shown in fig. 2, four corner points of the detection area are denoted as P 1 ～P 4 According to the coordinates of each angular point, a row and column value of the angular point in the point cloud can be obtained, the detection area is divided into a main detection area B, a non-main detection area A and a non-main detection area C based on the row and column values, defects are calculated based on the point cloud data in the non-main detection area A and the non-main detection area C, the defects are calculated based on the contour lines in the main detection area B, the fact that the lengths of the contour lines intercepted in the main detection area B are consistent is guaranteed, and parallel calculation is convenient.
In addition, the detection area is divided into a main detection area B, a non-main detection area A and a non-main detection area C, the contour line of the wood board surface is cut in the vertical movement direction, the B detection area can cut the contour line with the same length on the wood board surface, only one part of the point of the A, C detection area, which cuts the contour line due to the inclination of the wood board, comes from the wood board surface, and the other part comes from the background, so that if the defect is judged based on the defect area of the contour line and the defect width, erroneous judgment is easily caused. Therefore, the A, C detection area defect detection is based on the flatness of a plane formed by points in the area as a defect judgment basis, and the B detection area is based on the defect area calculated by the contour line and the like as a defect judgment basis;
then, the row, column start and column stop indexes of the first contour line are easily obtained according to the rectangular region and respectively marked as R 0 C 0_start C 0_end . The offset numbers of the column start and stop indexes of two adjacent contours are fixed. As shown in fig. 3. The line spacing of two adjacent contours of the point cloud is denoted as dy, the column spacing is denoted as dx, the unit mm, α represents the inclination angle of the rectangle with respect to the direction of motion (clockwise negative, counterclockwise positive), the two contour line offsets are offset= (dy tan α)/dx, the line start index difference representing two adjacent contours is offset, and the line index of any contour of the main detection area B is thus 
Wherein:
the above calculation is independent for each contour within the main detection area.
According to the embodiment of the invention, the defect size of the point set on each contour line in the main detection area is calculated specifically as follows:
calculating the straightness of each contour line in the main detection area: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
calculating the defect area of each contour line in the main detection: performing free curve fitting on the point set in the range of the contour line row and column; after fitting, the defect area of each contour line is calculated by taking the area formed by the contour line and the fitting curve as the defect area.
In calculating the defect area of the contour line, the point set in the range of the contour line is subjected to free curve fitting, and the defect on the curve is calculated, and as shown in FIG. 4, s1 to s4 represent the defect area in mm 2 The area above the curve is positive, the area below the curve is negative, the area below the curve is concave, the defect depth represents the maximum concave-convex size, the unit mm is combined with the defect width, and the unit mm can identify different types of defects.
According to the embodiment of the invention, the defect area is calculated specifically as follows: performing free curve fitting on the point set in the range of the contour line row and column; obtaining a fitting curve, after fitting, taking the area of the area above the fitting curve as positive, representing the bulge, the area of the area below the fitting curve as negative, representing the recess, the defect depth representing the maximum concave-convex size, and the defect width being the distance between adjacent intersection points; as shown in fig. 4, the contour points and the fitted curve intersect to form a plurality of "defect" areas (s 1 to s 4), and the area of each "defect" area is calculated by the following specific calculation method: for the contour point of each 'defect' area, calculating the horizontal distance between the current contour point and the previous contour point on the contour line and the vertical distance between the current contour point and the fitting curve, multiplying the obtained horizontal distance by the vertical distance to obtain the area of the contour point, and summing the areas of all the contour points to obtain the defect area of the contour line.
According to the embodiment of the invention, the statistics of the defects of the contour lines in the main detection area B is specifically as follows:
carrying out statistical analysis on straightness and defect area information of each contour in the main detection area B, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of the straightness of the contour in the main detection area B is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH4 is met;
and (3) counting the outline detection result output in the main detection area B: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection area B has defects if any one of the defect contour number threshold value TH5 and the maximum value threshold value TH6 of the continuous defect contours is met in the main detection area B.
In the calculation of the flatness of the non-primary detection a and the non-primary detection C, the flatness is calculated. Respectively calculating the planeness of point cloud data in the non-main detection A and the non-main detection C, then judging whether the non-main detection A and the non-main detection C have defects by referring to a straightness threshold TH1, and if the straightness of the non-main detection A is not smaller than the straightness threshold TH1, judging that the non-main detection A has defects; similarly, if the straightness of the non-main detection C is not less than the straightness threshold TH1, there is a defect.
As shown in fig. 5, the present invention also discloses a system for detecting surface defects of an elongated polishing template, which comprises: a memory 51 and a processor 52, wherein the memory 51 includes a program of a method for detecting surface defects of a strip-shaped polishing template, and the program of the method for detecting surface defects of the strip-shaped polishing template realizes the following steps when executed by the processor 52:
s101: acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
it should be noted that the system described in the present application may be applied to control terminal devices such as computers, industrial computers, etc. and used in combination with other devices.
As a specific embodiment, in this embodiment, the system for detecting the surface defect of the strip-shaped polishing template is applied to the visual detection platform; the visual detection platform is matched with the laser displacement sensor, the conveying platform and other devices to realize the detection of the surface defects of the strip-shaped polishing template. The detection process comprises the following steps: the laser displacement sensor is erected above the conveying platform, the wood board is placed on the conveying platform, the conveying platform moves along with the wood board at a constant speed, the contour data of the surface of the wood board are sensed and collected, then the contour data are transmitted to the visual detection platform for defect detection, and the detection result after detection is comprehensively judged and is output to the next station for processing.
The laser displacement sensor adopts a high-precision laser displacement sensor, namely a 3D camera; the depth data of the wood board surface, such as burrs with the height smaller than 5um, can be obtained, and the slender object can be measured without worrying about insufficient visual field or insufficient acquisition precision.
Vibration can be generated in the high-speed moving process of the conveying platform, one beneficial mode for eliminating the vibration is to improve the manufacturing quality of the platform, but at the same time, the cost is increased, and the other mode is to reduce the moving speed of the moving platform, so that the vibration is reduced, and the vibration and the manufacturing quality of the platform are not acceptable in practical application. If vibration fluctuation of the conveying platform is larger than the height of burrs on the surface of the wood board, even if the accuracy of data acquisition of the sensor is high, interference generated by the fluctuation cannot be eliminated, so that a detection result is inaccurate, and therefore, the application provides a defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment. For a single contour line, the vibration directions of points on the same contour line are consistent, and mutual dependency relationship does not exist between contour lines, so that the vibration influence of the wood board is negligible, and the requirement of high-speed acquisition can be met.
When the method for detecting the surface defects of the strip-shaped polishing template is executed, the 3D camera is erected above the moving platform, the moving platform is electrified in a correct connection mode, the wood board is placed on the moving platform, the height of the camera is adjusted to an optimal distance, and the parameters of the camera are adjusted until clear surface contours can be obtained.
The camera is triggered by an external encoder, the moving speed of the moving platform is kept at a proper frequency, and the acquired point cloud represents the real three-dimensional coordinates of the surface of the plank. Board point cloud is denoted as P s The size is M rows and N columns, and the rows and the columns are respectively distributed at equal intervals.
S102: converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
s103: positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
it should be noted that, the image edge method is adopted to locate the position information of the wood board, automatically generate a rectangular detection area, map the detection area to the point cloud data to obtain the wood board detection area in the three-dimensional space, as shown in fig. 2, P 1 P 2 P 3 P 4 The inclined inner frame rectangle is constituted to represent the detection area.
S104: intercepting a contour line from the point cloud according to the wood board detection area to be detected;
s105: calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
S106: calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
the flatness means flatness of the inner surface of the region, a threshold value of flatness may be set, and a judgment that a defect exists is made that the threshold value is larger
Flatness calculation mode: a set of three-dimensional points within the region is acquired, and a least squares plane is fitted with the points. The least square plane of the actual measured surface is used as an evaluation reference plane, and the distance between two containing planes which are parallel to the least square plane and have the smallest distance is used as a flatness error value.
S107: and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
According to the embodiment of the invention, the contour line is intercepted from the point cloud according to the wood board detection area to be detected, specifically:
dividing the wood board detection area to be detected into three detection areas, namely a main detection area B and a non-main detection area A, C;
intercepting a contour set from a main detection area B, wherein the row and column index of any contour in the area B is as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the row spacing of two adjacent contours of the point cloud, dx is the column spacing of two adjacent contours of the point cloud, and alpha represents the inclination angle of the rectangle relative to the motion direction.
It should be noted that, in the present application, the board inclination is considered, and as shown in fig. 2, four corner points of the detection area are denoted as P 1 ～P 4 The row and column values of each angular point coordinate in the point cloud can be obtained, and the detection area is divided intoABC three detection areas, for non-main detection areas A and C, defects are calculated based on point cloud data in the areas, and for main detection area B, defects are calculated based on contour lines, so that the lengths of contour lines intercepted in the main detection area B are consistent, and parallel calculation is convenient.
Then, the row, column start and column stop indexes of the first contour line are easily obtained according to the rectangular region and respectively marked as R 0 C 0_start C 0_end . The offset numbers of the column start and stop indexes of two adjacent contours are fixed. As shown in fig. 3. The line spacing of two adjacent contours of the point cloud is denoted as dy, the column spacing is denoted as dx, the unit mm, α represents the inclination angle of the rectangle with respect to the direction of motion (clockwise negative, counterclockwise positive), the two contour line offsets are offset= (dy tan α)/dx, the line start index difference representing two adjacent contours is offset, and the line index of any contour of the main detection area B is thus 
Wherein:
the above calculation is independent for each contour within the main detection area B. Therefore, the calculation can be realized in a parallel mode through the GPU, the high speed can still be kept for large-scale data (such as tens of thousands of contours), and finally N contour lines are obtained.
According to the embodiment of the invention, the defect size of the point set on each contour line in the main detection area B is calculated specifically as follows:
calculating the straightness of each contour line in the main detection area B: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
calculating the defect area of each contour line in the main detection area B: performing free curve fitting on the point set in the range of the contour line row and column; after fitting, the defect area of each contour line is calculated by taking the area formed by the contour line and the fitting curve as the defect area.
In calculating the defect area of the contour line, the point set in the range of the contour line is subjected to free curve fitting, and the defect on the curve is calculated, and as shown in FIG. 4, s1 to s4 represent the defect area in mm 2 The area above the curve is positive, the area below the curve is negative, the area below the curve is concave, the defect depth represents the maximum concave-convex size, the unit mm is combined with the defect width, and the unit mm can identify different types of defects.
And calculating the straightness and defect area information of each contour line through the steps.
In the method, the calculation of each contour line is independent, the parallelism calculation and the defect area algorithm are respectively parallelized, and the algorithm execution speed can be greatly improved.
According to the embodiment of the invention, the defect area is calculated specifically as follows: performing free curve fitting on the point set in the range of the contour line row and column; after fitting, the area above the curve is positive, the area below the curve is negative, the concave is represented, the defect depth represents the maximum concave-convex size, and the defect width is the distance between adjacent intersection points; and calculating to obtain the defect area of each contour line.
According to the embodiment of the invention, the statistics of the defects of the contour lines in the main detection area B is specifically as follows:
carrying out statistical analysis on straightness and defect area information of each contour in the main detection area B, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of the straightness of the contour in the main detection area B is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH4 is met;
And (3) counting the outline detection result output in the main detection area B: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection area B has defects if any one of the defect contour number threshold value TH5 and the maximum value threshold value TH6 of the continuous defect contours is met in the main detection area B.
In calculating the flatness of the non-main detection areas a and C, the flatness is calculated. The flatness of point cloud data in the non-main detection areas A and C is respectively judged, then a straightness threshold TH1 is referred to judge whether the non-main detection areas A and C have defects, and if the straightness of the non-main detection area A is not smaller than the straightness threshold TH1, the non-main detection area A has defects; similarly, if the straightness of the non-main detection area C is not less than the straightness threshold TH1, a defect exists.
To sum up, this application can distinguish worm hole, bellied detection through defect degree of depth, straightness accuracy, can distinguish through defect area, defect width to the burr region that the piece was not polished, combines the quantity threshold value of continuous judgement defect profile simultaneously, prevents to produce erroneous judgement to detection efficiency and accuracy have been improved.
In the embodiment, the laser displacement sensor is used for collecting complete contour data of the surface of the wood board, and the detection area is accurately positioned through 2D/3D combination, so that a contour line is automatically generated according to the detection area. The linear single-contour defect detection in the area eliminates the interference caused by the vibration of the platform, and combines the image processing technology to locate each contour detection range, so as to eliminate the interference of background and plank boundary data, and is simultaneously applicable to the condition of plank incoming material inclination, and the detection condition requirement is low and the human participation is less;
on the basis of collecting the complete scanning data of the wood board, a defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment is provided. Obtaining defect information by calculating straightness and fitting curves of the single profile, counting the number of defect profiles, the number of continuous defect profiles and the like in all profiles, comprehensively judging whether the detected object has defects, eliminating accidental errors and obviously reducing the misjudgment rate;
according to the method, in the process of capturing the plurality of contour lines and calculating the defects of the contour lines in the region B, parallelization calculation is realized based on the GPU, meanwhile, defect detection is carried out on the plurality of contour lines, the execution speed of an algorithm can be remarkably improved, the time consumption is reduced when a large number of contour lines are processed, and real-time online detection can be realized.
And parallelizing a defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment. And automatically calculating the detection area and defect information of each contour based on a GPU acceleration mode, and summarizing and outputting the defect contour information. The time consumption of detection is remarkably reduced based on parallelized contour defect calculation.
In a third aspect, the present application further provides a computer readable storage medium, where the computer readable storage medium includes a method program for detecting a surface defect of an elongated polishing template, where the method program for detecting a surface defect of an elongated polishing template, when executed by a processor, implements the steps of the method for detecting a surface defect of an elongated polishing template.
The application provides a method, a system and a storage medium for detecting surface defects of a strip-shaped polishing template. The application provides a defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment. The single contour obtains defect information by calculating straightness and fitting curves, counts the number of defect contours, the number of continuous defect contours and the like in all contours, comprehensively judges whether the detected object has defects, eliminates accidental errors and obviously reduces the misjudgment rate. In addition, the parallelization of the defect detection algorithm for single contour line defect calculation and multi-contour comprehensive judgment is realized. The efficiency of rectangular shape template surface defect detection of polishing has effectually been improved.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solution of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (10)
1. The method for detecting the surface defects of the strip-shaped polishing template is characterized by comprising the following steps of:
acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
intercepting a contour line from the point cloud according to the wood board detection area to be detected;
dividing a region to be detected into a main detection region and a non-main detection region;
calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
2. The method for detecting surface defects of an elongated polished template according to claim 1, wherein the contour line is intercepted from a point cloud according to a wood board detection area to be detected, specifically:
dividing a wood board detection area to be detected into a main detection area and a non-main detection area;
intercepting contours for sub-primary detectionThe row and column index of any outline in the main detection is set as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the row spacing of two adjacent contours of the point cloud, dx is the column spacing of two adjacent contours of the point cloud, and alpha represents the inclination angle of the rectangle relative to the motion direction.
3. The method for detecting surface defects of a strip-shaped polishing template according to claim 2, wherein the defect size of the point set on each contour line in the main detection is calculated specifically as follows:
calculating the straightness of each contour line in the main detection: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
Calculating the defect area of each contour line in the main detection: performing free curve fitting on the point set in the range of the contour line row and column; after fitting, the defect area of each contour line is calculated by taking the area formed by the contour line and the fitting curve as the defect area.
4. A method for detecting a surface defect of an elongated polished template according to claim 3, wherein the calculation of the defect area is specifically: performing free curve fitting on the point set in the range of the contour line row and column; obtaining a fitting curve, after fitting, taking the area of the area above the fitting curve as positive, representing the bulge, the area of the area below the fitting curve as negative, representing the recess, the defect depth representing the maximum concave-convex size, and the defect width being the distance between adjacent intersection points; and calculating the horizontal distance between the current contour point and the previous contour point on the contour line and the vertical distance between the current contour point and the fitted curve, multiplying the obtained horizontal distance by the vertical distance to obtain the area of the contour point, and summing the areas of all the contour points to obtain the defect area of the contour line.
5. The method for detecting surface defects of a strip-shaped polishing template according to claim 4, wherein the statistics main detection of internal contour line defects comprises the following steps:
Carrying out statistical analysis on straightness and defect area information of each contour in main detection, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of the straightness of the contour line in the sub-main detection area is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH4 is established;
and (3) counting the output of the detection result of the inner outline of the main detection: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection has defects if any one of the defect contour number threshold value TH5 and the maximum value threshold value TH6 of the continuous defect contours is met.
6. A system for detecting surface defects of an elongated sanding template, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a program of a surface defect detection method of an elongated polishing template, and the program of the surface defect detection method of the elongated polishing template realizes the following steps when being executed by the processor:
Acquiring the surface profile of a wood board to be detected; collecting a wood board point cloud to be detected according to the surface profile of the wood board to be detected so as to represent the real three-dimensional coordinates of the wood board to be detected;
converting the point cloud of the wood board to be detected into a height image, and displaying the boundary between the wood board to be detected and the background;
positioning the position information of the wood board to be detected by adopting an image edge method, automatically generating a rectangular detection area, mapping the detection area into the wood board point cloud data to be detected, and obtaining the wood board detection area to be detected in a three-dimensional space;
intercepting a contour line from the point cloud according to the wood board detection area to be detected;
dividing a region to be detected into a main detection region and a non-main detection region;
calculating the defect size of a point set of contour points on each contour line in the main detection area; counting defects of inner contour lines of the sub-main detection area;
calculating the flatness of the non-main detection area; judging whether the non-main detection area has defects or not;
and respectively judging whether defects exist in the main detection area and the non-main detection area and whether the positions and the sizes of the defects exist in the main detection area and the non-main detection area according to judging results of the main detection area and the non-main detection area.
7. The system for detecting surface defects of an elongated polished template according to claim 6, wherein the contour line is cut from the point cloud according to the wood board detection area to be detected, specifically:
Dividing a wood board detection area to be detected into a main detection area and a non-main detection area; the method comprises the steps of carrying out a first treatment on the surface of the
Intercepting a contour set from a main detection area, wherein the row-column index of any contour in the main detection area is as follows
Wherein:
offset＝(dy*tanα)/dx
wherein R is 0 For the line index of the first contour line in the region in the original data, C 0_start Column start index for first contour intercept range in region, C 0_end Intercepting a column termination index of a range for a first contour line in the region; dy is the row spacing of two adjacent contours of the point cloud, dx is the column spacing of two adjacent contours of the point cloud, and alpha represents the inclination angle of the rectangle relative to the motion direction.
8. The system for detecting surface defects of an elongated sanding template according to claim 7, wherein the calculating the defect size of the point set on each contour line in the main detection area is specifically:
calculating the straightness of each contour line in the main detection area: performing straight line fitting on the point set in the range of the contour line row, calculating the maximum distance from the point set to the fitted straight line, and recording the maximum distance as straightness;
the defect area is calculated specifically as follows: performing free curve fitting on the point set in the range of the contour line row and column; obtaining a fitting curve, after fitting, taking the area of the area above the fitting curve as positive, representing the bulge, the area of the area below the fitting curve as negative, representing the recess, the defect depth representing the maximum concave-convex size, and the defect width being the distance between adjacent intersection points; and calculating the horizontal distance between the current contour point and the previous contour point on the contour line and the vertical distance between the current contour point and the fitted curve, multiplying the obtained horizontal distance by the vertical distance to obtain the area of the contour point, and summing the areas of all the contour points to obtain the defect area of the contour line.
9. The method for detecting surface defects of a strip-shaped polished template according to claim 8, wherein the statistics of the internal profile defects of the main detection area is specifically as follows:
carrying out statistical analysis on straightness and defect area information of each contour in a main detection area, setting a straightness threshold TH1, an area threshold TH2, a defect depth threshold TH3 and a defect width threshold TH4, and judging that the contour is a defect contour if any one of straightness, area, defect depth and defect width of the contour in the main detection area is not smaller than the straightness threshold TH1, the area is not smaller than the area threshold TH2, the defect depth is not smaller than the defect depth threshold TH3 and the defect width is not smaller than the defect width threshold TH 4;
and (3) counting the output of the outline detection result in the main detection area: the total number of the contour lines is determined as the contour number of the defect contour, the maximum value of the continuous defect contour and the index information of each defect contour in the point cloud in total;
and setting a defect contour number threshold value TH5 and a maximum value threshold value TH6 of continuous defect contours, and judging that the main detection area has defects if any one of the contour line defect contour number in the main detection area is not smaller than the defect contour number threshold value TH5 and the maximum value of the continuous defect contour is not smaller than the maximum value threshold value TH6 of the continuous defect contour is met.
10. A computer-readable storage medium, wherein a method program for detecting surface defects of an elongated sanding template is included in the computer-readable storage medium, and the method program for detecting surface defects of an elongated sanding template, when executed by a processor, implements the steps of the method for detecting surface defects of an elongated sanding template according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122935.6A CN116433584A (en) | 2023-02-16 | 2023-02-16 | Surface defect detection method, system and storage medium for strip-shaped polishing template |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122935.6A CN116433584A (en) | 2023-02-16 | 2023-02-16 | Surface defect detection method, system and storage medium for strip-shaped polishing template |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116433584A true CN116433584A (en) | 2023-07-14 |
Family
ID=87091443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310122935.6A Pending CN116433584A (en) | 2023-02-16 | 2023-02-16 | Surface defect detection method, system and storage medium for strip-shaped polishing template |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116433584A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117862966A (en) * | 2024-03-12 | 2024-04-12 | 季华实验室 | Stamping part contour defect polishing control method and related equipment |
| CN118067624A (en) * | 2024-04-19 | 2024-05-24 | 宁德时代新能源科技股份有限公司 | Method, device and system for detecting battery before welding |
-
2023
- 2023-02-16 CN CN202310122935.6A patent/CN116433584A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117862966A (en) * | 2024-03-12 | 2024-04-12 | 季华实验室 | Stamping part contour defect polishing control method and related equipment |
| CN117862966B (en) * | 2024-03-12 | 2024-05-07 | 季华实验室 | Stamping part contour defect polishing control method and related equipment |
| CN118067624A (en) * | 2024-04-19 | 2024-05-24 | 宁德时代新能源科技股份有限公司 | Method, device and system for detecting battery before welding |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110095062B (en) | Object volume parameter measuring method, device and equipment | |
| CN108132017B (en) | Planar weld joint feature point extraction method based on laser vision system | |
| CN116433584A (en) | Surface defect detection method, system and storage medium for strip-shaped polishing template | |
| CN108537834B (en) | Volume measurement method and system based on depth image and depth camera | |
| CN110230998B (en) | Rapid and precise three-dimensional measurement method and device based on line laser and binocular camera | |
| CN112116619B (en) | Multi-line structured light system stripe center line extraction method based on structural constraint | |
| US10424078B2 (en) | Height measuring system and method | |
| CN110443243B (en) | Water level monitoring method, storage medium, network device and water level monitoring system | |
| CN109238084B (en) | Automatic guiding method for micro round hole measurement | |
| CN114396875B (en) | Rectangular package volume measurement method based on vertical shooting of depth camera | |
| CN111260708A (en) | Line structure optical center extraction method and system | |
| CN113074660B (en) | Surface shape measuring method for large-size transparent object | |
| CN102375619A (en) | Optical position input system and method | |
| CN116342718B (en) | Calibration method, device, storage medium and equipment of line laser 3D camera | |
| WO2023134251A1 (en) | Clustering-based light bar extraction method and apparatus | |
| CN116188544A (en) | Point cloud registration method combining edge features | |
| CN113052797A (en) | BGA solder ball three-dimensional detection method based on depth image processing | |
| CN111524134A (en) | Method and device for detecting regularity of honeycomb products on production line | |
| CN113095447B (en) | Detection method and system based on image recognition | |
| CN114049312A (en) | Belt coal flow visual identification method | |
| CN115511807B (en) | Method and device for determining position and depth of groove | |
| CN111462216A (en) | Method for determining circle center pixel coordinates in circular array calibration plate | |
| CN115018735A (en) | Fracture width identification method and system for correcting two-dimensional code image based on Hough transform | |
| CN109084721B (en) | Method and apparatus for determining a topographical parameter of a target structure in a semiconductor device | |
| CN114440768B (en) | Wafer detection method, device and equipment of 3D measuring machine and storage medium |
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 |