CN117115127A - Method, device, equipment and storage medium for detecting edge defects of product - Google Patents
Method, device, equipment and storage medium for detecting edge defects of product Download PDFInfo
- Publication number
- CN117115127A CN117115127A CN202311155916.XA CN202311155916A CN117115127A CN 117115127 A CN117115127 A CN 117115127A CN 202311155916 A CN202311155916 A CN 202311155916A CN 117115127 A CN117115127 A CN 117115127A
- Authority
- CN
- China
- Prior art keywords
- image
- standard
- contour
- edge
- detected
- 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 163
- 238000000034 method Methods 0.000 title claims abstract description 56
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 71
- 230000009466 transformation Effects 0.000 claims description 66
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000007797 corrosion Effects 0.000 claims description 7
- 238000005260 corrosion Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 10
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 8
- 238000013507 mapping Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 230000002950 deficient Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009643 growth defect Effects 0.000 description 2
- 239000013072 incoming material Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The disclosure provides a method, a device, equipment and a storage medium for detecting edge defects of a product, and relates to the technical field of data processing, wherein the method comprises the following steps: acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product; determining a standard contour of the image to be detected; acquiring the edge contour of the image to be detected; and determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected. The method can be applied to frequently switching scenes of different product shapes, and can realize efficient detection of product edge defects.
Description
Technical Field
The disclosure relates to the technical field of data processing, and in particular relates to a method, a device, equipment and a storage medium for detecting edge defects of a product.
Background
In the processing process of 3C products such as mobile phones, tablet computers and wearable equipment, a series of defects are generated in the current process section of the products due to imperfect processes or poor materials of incoming materials. If the defective product cannot be effectively intercepted, the defective product flows into the subsequent complex bonding process, so that the quality of the product is reduced, and the waste of processing resources is caused.
At present, the edges of the product are usually detected manually to determine whether the edges have defects, but the detection mode has the defects of low efficiency and low precision. Or the product edge is detected by deep learning, and a large number of samples are required to be collected in the method, so that the method is not suitable for a scene in which the product is frequently switched.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a device, and a storage medium for detecting an edge defect of a product, so as to at least solve the above technical problems in the prior art.
According to a first aspect of the present disclosure, there is provided a method of detecting an edge defect of a product, the method comprising:
acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product;
determining a standard contour of the image to be detected;
acquiring the edge contour of the image to be detected;
and determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected.
In one embodiment, the method further comprises:
obtaining a standard image of a standard product, wherein the standard image comprises edges of the standard product;
obtaining a standard outline of the standard image, wherein the standard product is a product without edge defects;
And constructing a shape matching model based on the standard outline of the standard product.
In an embodiment, the acquiring the standard contour of the standard image includes:
acquiring an edge contour point set of the standard image;
and determining a standard contour of the standard image corresponding to the edge contour point set through polygon approximation.
In an embodiment, the building a shape matching model based on the standard contour of the standard product includes:
carrying out morphological circular expansion on the standard contour of the standard product on the standard image, and then carrying out circular corrosion to obtain an annular region containing the standard contour;
determining a loop image of the standard product edge based on the loop region;
acquiring pyramid images of the annular image under a plurality of downsampling scales;
acquiring a sub-pixel edge point set of the annular image under pyramid images with different downsampling scales, and acquiring gradient amplitude values and gradient directions of all edge points through operators;
and storing all sub-pixel edge point sets, gradient amplitude values and gradient directions to form a shape matching model.
In an embodiment, the acquiring the standard contour of the image to be detected includes:
Determining a target contour from the shape matching model according to the image to be detected, wherein the target contour is a sub-pixel edge point set corresponding to any downsampling scale;
carrying out affine transformation for multiple times on the target profile and determining a target affine transformation matrix;
and determining the standard outline of the image to be detected based on the target affine transformation matrix and the standard image of the standard product.
In an embodiment, the determining the target affine transformation matrix includes:
carrying out affine transformation on the target profile for a plurality of times to obtain a plurality of point sets corresponding to affine transformation;
determining the gradient amplitude and the gradient direction of the contour point set of the image to be detected after each affine transformation;
for one of the affine transformed contour point sets, comprising: determining the correlation between the sum of all gradient amplitudes and the gradient direction of each point in the image to be detected and the gradient direction of the sub-pixel edge point set after affine transformation rotation;
determining a comprehensive evaluation result based on the sum of all gradient magnitudes and the correlation;
and taking an affine transformation matrix of affine transformation corresponding to the largest comprehensive evaluation result as a target affine transformation matrix.
In an embodiment, the determining the defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected includes:
subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set;
creating a k-d tree according to the subdivision standard contour point set, performing nearest neighbor searching, and determining standard contour point coordinates and nearest neighbor distances corresponding to each edge point in the edge contour of the image to be detected;
determining a defect contour point set based on standard contour point coordinates and nearest neighbor distances corresponding to all edge points;
and determining the defect size of the image to be detected according to the defect contour point set.
In an embodiment, the determining the defect contour point set based on the standard contour point coordinates and the nearest neighbor distance corresponding to all the edge points includes:
indexing edge points of the edge contour of the image to be detected, wherein the edge points are abnormal points when the nearest distance between the edge points and the corresponding standard contour points is larger than or equal to a first preset value;
searching a left cut-off index and a right cut-off index with nearest neighbor distances smaller than a second preset value on the left side and the right side of the abnormal point based on the index values; wherein the first preset value is greater than the second preset value;
And edge points between the left cut-off index and the right cut-off index form a defect contour point set corresponding to the abnormal points.
In an embodiment, the determining the defect size of the image to be detected according to the defect contour point set includes:
determining a minimum circumscribed rectangle formed by the defect contour point set;
the length and the width of the minimum circumscribed rectangle are the length and the width of a defect area corresponding to the defect contour point set; and/or
The area of the minimum circumscribed rectangle is the area of the defect area corresponding to the defect contour point set.
In an embodiment, after determining the defect contour point set, the method further includes:
determining the point corresponding to the value with the largest nearest neighbor distance in each defect contour point set as the farthest point, and forming the highest point set from all the farthest points;
and determining the defect type of the image to be detected based on the set of high points.
In an embodiment, the determining the defect type of the image to be detected based on the set of up points includes:
presetting a mapping relation between a defect type and a gray value threshold;
determining the gray value of any furthest point in the set of the up points;
and determining the defect type of the defect area where the farthest point is located according to the gray value and the mapping relation.
According to a second aspect of the present disclosure, there is provided a device for detecting edge defects of a product, the device comprising:
the image acquisition module is used for acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product;
the contour determining module is used for determining the standard contour of the image to be detected;
the edge contour acquisition module is used for acquiring the edge contour of the image to be detected;
and the defect determining module is used for determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected.
In an embodiment, the image acquisition module is further configured to:
obtaining a standard image of a standard product, wherein the standard image comprises edges of the standard product;
obtaining a standard outline of the standard image, wherein the standard product is a product without edge defects;
and constructing a shape matching model based on the standard outline of the standard product.
In an embodiment, the image acquisition module is further configured to:
acquiring an edge contour point set of the standard image;
and determining a standard contour of the standard image corresponding to the edge contour point set through polygon approximation.
In an embodiment, the image acquisition module is further configured to:
carrying out morphological circular expansion on the standard contour of the standard product on the standard image, and then carrying out circular corrosion to obtain an annular region containing the standard contour;
determining a loop image of the standard product edge based on the loop region;
acquiring pyramid images of the annular image under a plurality of downsampling scales;
acquiring a sub-pixel edge point set of the annular image under pyramid images with different downsampling scales, and acquiring gradient amplitude values and gradient directions of all edge points through operators;
and storing all sub-pixel edge point sets, gradient amplitude values and gradient directions to form a shape matching model.
In an embodiment, the contour determination module is further configured to:
determining a target contour from the shape matching model according to the image to be detected, wherein the target contour is a sub-pixel edge point set corresponding to any downsampling scale;
carrying out affine transformation for multiple times on the target profile and determining a target affine transformation matrix;
and determining the standard outline of the image to be detected based on the target affine transformation matrix and the standard image of the standard product.
In an embodiment, the contour determination module is further configured to:
carrying out affine transformation on the target profile for a plurality of times to obtain a plurality of point sets corresponding to affine transformation;
determining the gradient amplitude and the gradient direction of the contour point set of the image to be detected after each affine transformation;
for one of the affine transformed contour point sets, comprising: determining the correlation between the sum of all gradient amplitudes and the gradient direction of each point in the image to be detected and the gradient direction of the sub-pixel edge point set after affine transformation rotation;
determining a comprehensive evaluation result based on the sum of all gradient magnitudes and the correlation;
and taking an affine transformation matrix of affine transformation corresponding to the largest comprehensive evaluation result as a target affine transformation matrix.
In an embodiment, the defect determination module is further configured to:
subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set;
creating a k-d tree according to the subdivision standard contour point set, performing nearest neighbor searching, and determining standard contour point coordinates and nearest neighbor distances corresponding to each edge point in the edge contour of the image to be detected;
Determining a defect contour point set based on standard contour point coordinates and nearest neighbor distances corresponding to all edge points;
and determining the defect size of the image to be detected according to the defect contour point set.
In an embodiment, the defect determination module is further configured to:
indexing edge points of the edge contour of the image to be detected, wherein the edge points are abnormal points when the nearest distance between the edge points and the corresponding standard contour points is larger than or equal to a first preset value;
searching a left cut-off index and a right cut-off index with nearest neighbor distances smaller than a second preset value on the left side and the right side of the abnormal point based on the index values; wherein the first preset value is greater than the second preset value;
and edge points between the left cut-off index and the right cut-off index form a defect contour point set corresponding to the abnormal points.
In an embodiment, the defect determination module is further configured to:
determining a minimum circumscribed rectangle formed by the defect contour point set;
the length and the width of the minimum circumscribed rectangle are the length and the width of a defect area corresponding to the defect contour point set; and/or
The area of the minimum circumscribed rectangle is the area of the defect area corresponding to the defect contour point set.
In an embodiment, the defect determination module is further configured to:
determining the point corresponding to the value with the largest nearest neighbor distance in each defect contour point set as the farthest point, and forming the highest point set from all the farthest points;
and determining the defect type of the image to be detected based on the set of high points.
In an embodiment, the defect determination module is further configured to:
presetting a mapping relation between a defect type and a gray value threshold;
determining the gray value of any furthest point in the set of the up points;
and determining the defect type of the defect area where the farthest point is located according to the gray value and the mapping relation.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the methods described in the present disclosure.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the present disclosure.
The method for detecting the edge defect of the product comprises the steps of obtaining an image to be detected containing the edge of the product; determining a standard contour of the image to be detected and an edge contour of the image to be detected; and then determining defect information of the image to be detected according to the edge contour of the image to be detected and the standard contour of the image to be detected. The method can be applied to frequently switching scenes of different product shapes, and can realize efficient detection of product edge defects.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a schematic flow chart of a method for detecting edge defects of a product according to an embodiment of the disclosure;
FIG. 2 shows a schematic diagram of a configuration of a backlight imaging system according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of a method for detecting edge defects of a product according to an embodiment of the disclosure;
FIG. 4 illustrates a flow diagram of building a shape matching model according to an embodiment of the present disclosure;
FIG. 5 illustrates a flow diagram of acquiring a standard profile of an image to be detected in accordance with an embodiment of the present disclosure;
FIG. 6 illustrates a flow diagram of determining defect information for a product edge according to an embodiment of the present disclosure;
FIG. 7 is a flow chart of a method for detecting edge defects of a product according to an embodiment of the disclosure;
FIG. 8 shows a standard image schematic of a standard product of an embodiment of the present disclosure;
FIG. 9 illustrates a standard outline schematic of a standard image of a standard product of an embodiment of the present disclosure;
FIG. 10 shows a schematic diagram of an image to be inspected of a product to be inspected in an embodiment of the present disclosure;
FIG. 11 shows a schematic diagram of a standard profile of an image to be detected in an embodiment of the present disclosure;
FIG. 12 shows a schematic diagram of a subdivision standard contour of an image to be detected in an embodiment of the present disclosure;
FIG. 13 is a schematic diagram showing defect information of an image to be detected according to an embodiment of the present disclosure;
FIG. 14 is a schematic diagram showing a structure of a device for detecting edge defects of a product according to an embodiment of the disclosure;
Fig. 15 shows a schematic diagram of a composition structure of an electronic device according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, features and advantages of the present disclosure more comprehensible, the technical solutions in the embodiments of the present disclosure will be clearly described in conjunction with the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. Based on the embodiments in this disclosure, all other embodiments that a person skilled in the art would obtain without making any inventive effort are within the scope of protection of this disclosure.
Fig. 1 is a schematic flow chart of a method for detecting an edge defect of a product according to an embodiment of the disclosure, where the method includes:
s1, acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product.
The product may be a cover plate, a shell plate, a circuit board, etc. of a 3C electronic product such as a mobile phone, a tablet computer, a wearable device, etc., and a series of defects may be generated on the product edge due to imperfect process or poor material quality of the incoming material.
The gray level image of the product area is obtained as an image to be detected in a machine vision fixed single threshold mode, and as shown in fig. 2, a schematic structural diagram of a backlight imaging system provided by an embodiment of the disclosure is shown, the imaging system comprises a carrier for placing a product, a light source and a CCD camera, wherein the carrier is arranged between the light source and the CCD camera. And placing the product on a carrier, and acquiring a gray level image of the product by adopting a backlight imaging system to obtain an image to be detected of the product.
S2, determining the standard outline of the image to be detected.
S3, acquiring the edge contour of the image to be detected.
With the backlighting imaging system of fig. 2, the edge profile of the image to be detected, which is the set of points constituting the outer edge of the product, is obtained by means of a fixed single threshold. The product edge is used as a target area, the gray value is set to 0, the gray value of the background area is set to 255, the edge points of the product can be rapidly obtained, and the edge point set formed by all the edge points is the edge contour RealC.
S4, determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected.
And performing defect judgment by calculating the distance from the edge contour of the image to be detected to the standard contour to obtain defect information of the image to be detected, namely defect information of the edge of the product.
In one example, the method further comprises:
s5, obtaining a standard image of a standard product, wherein the standard image comprises edges of the standard product.
By the backlight imaging system of fig. 2, a standard product free from edge defects is placed on a stage, and a gray image thereof is photographed as a standard image.
S6, acquiring a standard outline of the standard image, wherein the standard product is a product without edge defects.
S7, constructing a shape matching model based on the standard outline of the standard product.
Wherein, obtain the standard outline of standard image, include:
s61, acquiring an edge contour point set of the standard image.
An edge contour point set of the standard image is acquired, including but not limited to a fixed threshold method, an adaptive threshold method, and an oxford method. In this embodiment, the backlight imaging system of fig. 2 is utilized to obtain the edge point set of the image to be detected by fixing a single threshold, the edge of the standard product is used as the target area, the gray value is set to 0, the gray value of the background area is set to 255, the edge point of the standard product can be obtained rapidly, and all the edge points form the edge contour point set of the standard product.
And further determining a standard contour of the standard image corresponding to the edge contour point set through polygonal approximation. The method specifically comprises the following steps:
s62, determining two points with farthest edge contour point concentration distances, and connecting the two points with the farthest points to obtain a first line segment.
S63, determining the distance between the farthest point of the contour point set and the first line segment.
S64, if the distance is smaller than a threshold value, the first line segment is used as a standard contour of the standard product.
And S65, if the distance is greater than a threshold value, taking the point farthest from the first line segment as a division point, wherein the division point is respectively connected with two end points of the first line segment to obtain a second line segment and a third line segment.
S66, determining the distance between the farthest point of the contour point set from the second line segment and the second line segment; and determining the distance between the farthest point of the contour point set from the third segment and the third segment.
If the distance between the point, farthest from the second line segment, of the second contour point set and the second line segment is smaller than a threshold value, the second line segment is reserved as a part of the standard contour; if the distance is greater than the threshold value, connecting the farthest point with two end points of the second line segment respectively to obtain new two line segments, repeating the operation to find the farthest point from the new line segment, and judging the relation between the distance and the threshold value.
S67, repeating the operation until all the distances are smaller than a threshold value, sequentially connecting fold lines formed by all the dividing points, and taking the fold lines as standard contours of the standard products.
In order to further reduce the number of edge points in the edge contour point set, the edge contour point set obtained in the step S61 is subjected to polygon approximation through the steps S62-S67, so as to obtain a standard contour model standard c of a standard product.
In one example, as shown in fig. 4, a flow chart for constructing a shape matching model based on a standard contour of the standard product includes:
and S71, carrying out morphological circular expansion and circular corrosion on the standard contour of the standard product on the standard image to obtain an annular region containing the standard contour.
Performing morphological circular expansion, expanding edge points, filling holes, and expanding the edges to the outside; the circular etching is further carried out in order to remove objects smaller than the structural elements. In this embodiment, the circular expansion radius and the circular corrosion radius are both exemplified by 3 pixel points, and after circular expansion and circular corrosion, the annular region including the standard profile ModelStandC is obtained. Based on this region, a ring-shaped image RingImg of the product edge can be obtained.
S72, determining an annular image of the edge of the standard product based on the annular region.
A ring image RingImg of the product edge can be obtained based on a ring region containing the standard contour modelstandby c.
S73, acquiring pyramid images of the annular image in a plurality of downsampling scales.
For example, taking the annular image as an original image, wherein the original image is a layer 0 image of the pyramid image; different sampling times correspond to different scales, and the pyramid image is obtained by downsampling 5 times.
S74, acquiring a sub-pixel edge point set of the annular image under pyramid images with different downsampling scales, and acquiring gradient amplitude values and gradient directions of all edge points through operators.
Taking an original image of the annular image as an example, acquiring a subpixel edge point set of the annular image RingImg based on a Canny edge detection algorithm, and acquiring gradient amplitude and gradient direction of edge points by utilizing a sobel operator.
S75, storing all sub-pixel edge point sets, gradient amplitude values and gradient directions to form a shape matching model.
And acquiring a subpixel edge point set of the annular image RingImg under different downsampling scales, and gradient amplitude values and gradient directions of edge points corresponding to the scales based on a Canny edge detection algorithm. And storing all the sub-pixel edge point sets, gradient amplitude values and gradient directions into a model file model ID. Shm to obtain a shape matching model. While storing the standard profile modelstandby c into the modeid.
In one example, as shown in fig. 5, a flowchart of acquiring a standard contour of the image to be detected includes:
s21, determining a target contour from the shape matching model according to the image to be detected, wherein the target contour is a sub-pixel edge point set corresponding to any downsampling scale.
Selecting a sub-pixel edge point set corresponding to the template image at a certain downsampling scale in steps S73-S74, and assuming that the sampling value is r. The higher the number of pyramid layers is, the larger the downsampling scale is, and the faster the matching speed is, but the edge information still exists under the image of the scale is ensured.
S22, carrying out affine transformation on the target contour for a plurality of times and determining a target affine transformation matrix.
The target contour is subjected to affine transformation by a plurality of angles θ ranging from (-180 °,180 °) to a translation distance t ranging from the upper left corner to the lower right corner of the standard image, wherein the translation unit is a pixel point, for example, 1 pixel point is translated once. For example, the target profile is translated once and then rotated multiple times over a range of (-180 °,180 °).
The left upper corner of the standard image is marked as (0, 0), the target outline is rotated by a certain angle theta and translated by a range of variation of a translation distance T to obtain an affine transformation matrix T,and carrying out affine transformation on the sub-pixel point set to obtain an affine-transformed point set TransC, wherein tx and ty are respectively the abscissa and the ordinate after affine transformation is carried out once.
In one example, determining the target affine transformation matrix includes:
Carrying out affine transformation on the target profile for a plurality of times to obtain a plurality of point sets corresponding to affine transformation;
determining the gradient amplitude and the gradient direction of the contour point set of the image to be detected after each affine transformation;
for one of the affine transformed contour point sets, comprising: determining the correlation between the sum of all gradient amplitudes and the gradient direction of each point in the image to be detected and the gradient direction of the sub-pixel edge point set after affine transformation rotation;
determining a comprehensive evaluation result based on the sum of all gradient magnitudes and the correlation;
and taking an affine transformation matrix of affine transformation corresponding to the largest comprehensive evaluation result as a target affine transformation matrix.
And calculating the gradient amplitude and gradient direction of the point set TransC of the image to be detected after affine transformation, calculating the sum of all gradient amplitudes to obtain Sobelamp V, calculating the correlation between the gradient direction t1 of each sub-pixel point in the image to be detected and the direction m1 after the gradient direction stored in the model file is subjected to angle rotation theta, wherein the sum of all gradient direction correlations is correV, and calculating according to the following formula (1).
Repeating the steps, calculating the gradient amplitude and gradient direction of the point set TransC of the image to be detected after all affine transformations, calculating the sum of Sobelamp V and correV, and taking the sum of Sobelamp V and correV as a comprehensive evaluation result, and marking an affine transformation matrix of affine transformation corresponding to the maximum comprehensive evaluation result as T.
And carrying out up-sampling operation on the offset in the affine transformation matrix T to obtain T' serving as a target affine transformation matrix.
Wherein,
s23, determining the standard outline of the image to be detected based on the target affine transformation matrix and the standard image of the standard product.
The standard contour teststandby c of the image to be detected is obtained by applying T' to the standard contour modelstandby of the standard product.
In one example, as shown in fig. 6, determining defect information of the product edge according to an edge contour of the image to be detected and a standard contour of the image to be detected includes:
s41, subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set.
Since the standard contour teststandard c of the image to be detected is obtained based on the standard contour modelstandard c of the standard product, and the standard contour modelstandard c of the standard product is obtained by polygon approximation storage, the distance between contour points is larger, often greater than 1 pixel point (pix), and in order to ensure the accuracy in defect detection, the standard contour teststandard c of the image to be detected needs to be subdivided, and the distance between adjacent points after subdivision is smaller than a set threshold, for example, the set threshold is 0.5pix.
Subdividing a standard contour of an image to be detected, including:
selecting any pair of adjacent points P1 and P2 of a standard contour TestStandC of an image to be detected, and calculating the distance between the two points as dis;
calculating a difference point Pt between the adjacent point pairs P1 and P2 by using the following formula (2)
Repeating the steps to obtain an interpolation point set between adjacent point pairs, inserting the difference point set into a standard contour TestStandC of an image to be detected, and obtaining a subdivision standard contour point set CalTestStandC if the distance between any two points is smaller than 0.5 pix.
S42, creating a k-d tree according to the subdivision standard contour point set, carrying out nearest neighbor searching, and determining standard contour point coordinates and nearest neighbor distances corresponding to each edge point in the edge contour of the image to be detected.
The data points in the subdivision standard contour point set calteststandard c are divided into a number of subspaces according to the distance dimension in k-dimensional space, thereby dividing the data points into different clusters. Each subspace corresponds to a node, and each node maintains its contained data points and its corresponding subspace.
Any one edge point in the edge contour RealC of the image to be detected is selected, the nearest neighbor standard point in the k-d tree is calculated, and the corresponding standard point coordinates and nearest neighbor distance are recorded. Repeating the operation on all edge points in the edge contour RealC of the image to be detected, respectively calculating standard points nearest to the edge points in the k-d tree, and recording coordinates of the corresponding standard points and nearest neighbor distances.
S43, determining a defect contour point set based on standard contour point coordinates corresponding to all edge points and nearest neighbor distances.
Obtaining a defect contour point set based on a dual-threshold decision rule, in one example, determining the defect contour point set based on standard contour point coordinates corresponding to all edge points and nearest neighbor distances, including:
s431, indexing edge points of the edge contour of the image to be detected, wherein when the nearest distance between the edge points and the corresponding standard contour points is greater than or equal to a first preset value, the edge points are abnormal points.
Indexing edge points of the edge contour RealC, starting with an index value j=0, and continuing to index downwards j=j+1 when the nearest distance between the edge point P and the corresponding standard contour point is smaller than a first preset value; otherwise, the edge point P is an outlier.
S432, searching a left cut-off index and a right cut-off index with the nearest neighbor distance smaller than a second preset value on the left side and the right side of the abnormal point based on the index value; wherein the first preset value is greater than the second preset value.
S433, edge points between the left cut-off index and the right cut-off index form a defect contour point set corresponding to the abnormal points.
Searching a left cut-off index and a right cut-off index with nearest neighbor distances smaller than a second preset value on the left side and the right side of the abnormal point P, wherein the left cut-off index and the right cut-off index are respectively used as a start point and an end point, and points between the start point and the end point form a defect contour point set corresponding to the edge point P.
S44, determining the defect size of the image to be detected according to the defect contour point set.
In one example, determining the defect size of the image to be detected from the defect contour point set includes:
s441, determining a minimum circumscribed rectangle formed by the defect contour point set;
s442, the length and the width of the minimum circumscribed rectangle are the length and the width of a defect area corresponding to the defect contour point set; and/or
S443, the area of the minimum circumscribed rectangle is the area of the defect area corresponding to the defect contour point set.
Selecting a defect contour point set, and determining a minimum circumscribed rectangle based on the defect contour point set, wherein the length and the width of the minimum circumscribed rectangle are the length and the width of a defect area; the area of the smallest bounding rectangle is the area of the defective area.
In one example, the method further comprises:
s45, determining the point corresponding to the value with the largest nearest neighbor distance in each defect contour point set as the farthest point, and forming a high point set from all the farthest points;
s46, determining the defect type of the image to be detected based on the set of the high points.
In one example, determining the defect type of the image to be detected based on the set of high points includes:
S461, presetting a mapping relation between the defect type and a gray value threshold;
s462, determining the gray value of any furthest point in the set of the up points;
s463, determining the defect type of the defect area where the farthest point is located according to the gray value and the mapping relation.
The defects of the product edge protrusions are defined as tooth growth defects, the defects of the product edge depressions are defined as bud defect, the tooth growth defects are formed when the gray value is smaller than a given gray value threshold value, and the bud defect is formed when the gray value is larger than the gray value threshold value.
After the defect type and the defect size in the image to be detected are determined, the final defect information is screened out according to the inspection rule of the product, so that the detection state of the current product is determined. For example, the defect type is bud defect, the size of the defect area is 0.5mm by 0.5mm, if the product inspection specification is that the length and width of the size of the defect area are not more than 1mm, and the edge of the product is qualified, the size of the defect area of the product is 0.5mm by 0.5mm, and the product is a qualified product. If the product inspection specification is that the length and width of the defect area are not more than 0.4mm, the defect area of the product is 0.5mm by 0.5mm, namely the defective product.
The qualified or unqualified products respectively flow into the corresponding qualified or unqualified flow channels, the products of the corresponding unqualified flow channels can be repaired or scrapped based on the defect types, and the products of the corresponding qualified flow channels flow into the downstream for other processes.
The application is illustrated below by way of an example in connection with a specific scenario.
Fig. 7 is a schematic flow chart of a method for detecting edge defects of a product, which includes:
s201, acquiring a standard image of a standard product.
By the backlight imaging system of fig. 2, a standard product without edge defects is placed on a stage, and a gray scale image thereof is photographed as a standard image, an example of which is shown in fig. 8.
S202, acquiring an edge contour point set of a standard image, and determining a standard contour of the standard image through polygon approximation; and building a shape matching model based on the standard contours of the standard product.
Wherein a standard outline of the standard sheet is shown in fig. 9.
S203, acquiring a gray scale image of the product to be detected as an image to be detected.
An example of an image to be detected is shown in fig. 10.
S204, loading a shape matching model and standard contours of standard products, and searching contours of the shape matching model in the image to be detected based on the shape matching model to find a target contour; carrying out affine transformation on the target contour for multiple times and determining a target affine transformation matrix; and applying the target affine transformation matrix to a standard image of a standard product to determine a standard contour of the image to be detected.
An example of a standard contour of an image to be detected is shown in fig. 11, and it can be seen that the distance between contour points is large.
S205, subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set.
The illustration of the subdivision of the standard set of contour points is shown in fig. 12, where it can be seen that the contour points are relatively dense and the distance between the contour points is small.
S206, calculating edge defects based on the subdivision standard contour point set and the edge contour of the image to be detected.
As shown in fig. 13, which is a defect information illustration, a minimum circumscribed rectangle approximation of the defect contour point set is constructed based on the defect contour point set, the length and width of the minimum circumscribed rectangle is the length and width characteristics of the defect, and the area of the region formed by the defect contour point set is the area characteristics of the defect. Further based on the gray value, the position of the product edge protrusion is determined to be a tooth defect (as indicated by the position of a mark 1 in fig. 11), and the product edge depression is determined to be a bud defect (as indicated by the position of a mark 2 in fig. 11).
S207, comparing the calculated defect information with a product inspection standard, and if the defect information meets the inspection standard, qualifying the edge of the product to be inspected; if the product to be detected does not meet the inspection standard, the edge of the product to be detected is not qualified.
According to an embodiment of the present disclosure, the present disclosure further provides a device for detecting an edge defect of a product, as shown in fig. 14, which is a schematic structural diagram of the device, including:
the image acquisition module 10 is used for acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product;
a contour determination module 20, configured to determine a standard contour of the image to be detected;
an edge contour obtaining module 30, configured to obtain an edge contour of the image to be detected;
the defect determining module 40 is configured to determine defect information of the product edge according to an edge contour of the image to be detected and a standard contour of the image to be detected.
In one example, the image acquisition module 10 is further configured to acquire a standard outline of a standard product, which is a product free of edge defects.
The apparatus further comprises: a construction module 50 for constructing a shape matching model based on the standard contours of the standard product.
In one example, the build module 50 is further to:
carrying out morphological circular expansion on the standard contour of the standard product on the standard image, and then carrying out circular corrosion to obtain an annular region containing the standard contour;
Determining a loop image of the standard product edge based on the loop region;
acquiring pyramid images of the annular image under a plurality of scales;
acquiring a sub-pixel edge point set of the annular image under pyramid images with different scales, and acquiring gradient amplitude values and gradient directions of all edge points through operators;
and storing all sub-pixel edge point sets, gradient amplitude values and gradient directions to form a shape matching model.
In one example, the contour determination module 20 is further to:
determining a target contour from the shape matching model according to the image to be detected;
carrying out affine transformation for multiple times on the target profile and determining a target affine transformation matrix;
and determining the standard outline of the image to be detected based on the target affine transformation matrix and the standard image of the standard product.
In one example, the contour determination module 20 is further to:
carrying out affine transformation on the target profile for a plurality of times to obtain a plurality of point sets corresponding to affine transformation;
determining the gradient amplitude and the gradient direction of the contour point set of the image to be detected after each affine transformation;
for one of the affine transformed contour point sets, comprising: determining the correlation between the sum of all gradient amplitudes and the gradient direction of each point in the image to be detected and the gradient direction of the sub-pixel edge point set after affine transformation rotation;
Determining a comprehensive evaluation result based on the sum of all gradient magnitudes and the correlation;
and taking an affine transformation matrix of affine transformation corresponding to the largest comprehensive evaluation result as a target affine transformation matrix.
In one example, defect determination module 40 is further to:
subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set;
creating a k-d tree according to the subdivision standard contour point set, performing nearest neighbor searching, and determining standard contour point coordinates and nearest neighbor distances corresponding to each edge point in the edge contour of the image to be detected;
determining a defect contour point set based on standard contour point coordinates and nearest neighbor distances corresponding to all edge points;
and determining the defect size of the image to be detected according to the defect contour point set.
In one example, defect determination module 40 is further to:
indexing edge points of the edge contour of the image to be detected, wherein the edge points are abnormal points when the nearest distance between the edge points and the corresponding standard contour points is larger than or equal to a first preset value;
searching a left cut-off index and a right cut-off index with nearest neighbor distances smaller than a second preset value on the left side and the right side of the abnormal point based on the index values; wherein the first preset value is greater than the second preset value;
And edge points between the left cut-off index and the right cut-off index form a defect contour point set corresponding to the abnormal points.
In one example, defect determination module 40 is further to:
determining a minimum circumscribed rectangle formed by the defect contour point set;
the length and the width of the minimum circumscribed rectangle are the length and the width of a defect area corresponding to the defect contour point set; and/or
The area of the minimum circumscribed rectangle is the area of the defect area corresponding to the defect contour point set.
In one example, defect determination module 40 is further to:
determining the point corresponding to the value with the largest nearest neighbor distance in each defect contour point set as the farthest point, and forming the highest point set from all the farthest points;
and determining the defect type of the image to be detected based on the set of high points.
In one example, defect determination module 40 is further to:
presetting a mapping relation between a defect type and a gray value threshold;
determining the gray value of any furthest point in the set of the up points;
and determining the defect type of the defect area where the farthest point is located according to the gray value and the mapping relation.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
Fig. 15 shows a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 15, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
Various components in device 800 are connected to I/O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as a method of detecting a defect in a product edge. For example, in some embodiments, the method of defect detection of product edges may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 800 via ROM 802 and/or communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the above-described method of defect detection of product edges may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the defect detection method of the product edge in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely specific embodiments of the disclosure, but the protection scope of the disclosure is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the disclosure, and it is intended to cover the scope of the disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A method for detecting edge defects of a product, the method comprising:
acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product;
determining a standard contour of the image to be detected;
acquiring the edge contour of the image to be detected;
and determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected.
2. The method according to claim 1, characterized in that the method further comprises:
obtaining a standard image of a standard product, wherein the standard image comprises edges of the standard product;
obtaining a standard outline of the standard image, wherein the standard product is a product without edge defects;
and constructing a shape matching model based on the standard outline of the standard product.
3. The method of claim 2, wherein the acquiring the standard outline of the standard image comprises:
acquiring an edge contour point set of the standard image;
and determining a standard contour of the standard image corresponding to the edge contour point set through polygon approximation.
4. A method according to claim 3, wherein said constructing a shape matching model based on a standard contour of said standard product comprises:
Carrying out morphological circular expansion on the standard contour of the standard product on the standard image, and then carrying out circular corrosion to obtain an annular region containing the standard contour;
determining a loop image of the standard product edge based on the loop region;
acquiring pyramid images of the annular image under a plurality of downsampling scales;
acquiring a sub-pixel edge point set of the annular image under pyramid images with different downsampling scales, and acquiring gradient amplitude values and gradient directions of all edge points through operators;
and storing all sub-pixel edge point sets, gradient amplitude values and gradient directions to form a shape matching model.
5. The method of claim 4, wherein the acquiring the standard contour of the image to be detected comprises:
determining a target contour from the shape matching model according to the image to be detected, wherein the target contour is a sub-pixel edge point set corresponding to any downsampling scale;
carrying out affine transformation for multiple times on the target profile and determining a target affine transformation matrix;
and determining the standard outline of the image to be detected based on the target affine transformation matrix and the standard image of the standard product.
6. The method of claim 5, wherein the determining the target affine transformation matrix comprises:
carrying out affine transformation on the target profile for a plurality of times to obtain a plurality of point sets corresponding to affine transformation;
determining the gradient amplitude and the gradient direction of the contour point set of the image to be detected after each affine transformation;
for one of the affine transformed contour point sets, comprising: determining the correlation between the sum of all gradient amplitudes and the gradient direction of each point in the image to be detected and the gradient direction of the sub-pixel edge point set after affine transformation rotation;
determining a comprehensive evaluation result based on the sum of all gradient magnitudes and the correlation;
and taking an affine transformation matrix of affine transformation corresponding to the largest comprehensive evaluation result as a target affine transformation matrix.
7. The method of claim 6, wherein determining defect information for the product edge based on the edge profile of the image to be inspected and the standard profile of the image to be inspected comprises:
subdividing the standard contour of the image to be detected to obtain a subdivision standard contour point set;
Creating a k-d tree according to the subdivision standard contour point set, performing nearest neighbor searching, and determining standard contour point coordinates and nearest neighbor distances corresponding to each edge point in the edge contour of the image to be detected;
determining a defect contour point set based on standard contour point coordinates and nearest neighbor distances corresponding to all edge points;
and determining the defect size of the image to be detected according to the defect contour point set.
8. A device for detecting edge defects of a product, the device comprising:
the image acquisition module is used for acquiring an image to be detected of a product, wherein the image to be detected is an image containing the edge of the product;
the contour determining module is used for determining the standard contour of the image to be detected;
the edge contour acquisition module is used for acquiring the edge contour of the image to be detected;
and the defect determining module is used for determining defect information of the product edge according to the edge contour of the image to be detected and the standard contour of the image to be detected.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311155916.XA CN117115127A (en) | 2023-09-07 | 2023-09-07 | Method, device, equipment and storage medium for detecting edge defects of product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311155916.XA CN117115127A (en) | 2023-09-07 | 2023-09-07 | Method, device, equipment and storage medium for detecting edge defects of product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117115127A true CN117115127A (en) | 2023-11-24 |
Family
ID=88798260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311155916.XA Pending CN117115127A (en) | 2023-09-07 | 2023-09-07 | Method, device, equipment and storage medium for detecting edge defects of product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117115127A (en) |
-
2023
- 2023-09-07 CN CN202311155916.XA patent/CN117115127A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021057848A1 (en) | Network training method, image processing method, network, terminal device and medium | |
CN110544258B (en) | Image segmentation method and device, electronic equipment and storage medium | |
CN111340752A (en) | Screen detection method and device, electronic equipment and computer readable storage medium | |
CN107918216B (en) | Image Mura defect evaluation method and system and readable storage medium | |
CN103235949B (en) | Image point of interest detection method and device | |
CN108830780B (en) | Image processing method and device, electronic device and storage medium | |
JP2022539912A (en) | Electronic device backplane appearance defect inspection method and apparatus | |
CN112534469B (en) | Image detection method, image detection device, image detection apparatus, and medium | |
CN113436100B (en) | Method, apparatus, device, medium, and article for repairing video | |
EP4350619A1 (en) | Battery cell squeeze damage detection method, apparatus and system | |
CN116559177A (en) | Defect detection method, device, equipment and storage medium | |
CN115147403A (en) | Method and device for detecting liquid pollutants, electronic equipment and medium | |
CN116342585A (en) | Product defect detection method, device, equipment and storage medium | |
CN113284113B (en) | Glue overflow flaw detection method, device, computer equipment and readable storage medium | |
CN116486126B (en) | Template determination method, device, equipment and storage medium | |
CN116385415A (en) | Edge defect detection method, device, equipment and storage medium | |
CN117115127A (en) | Method, device, equipment and storage medium for detecting edge defects of product | |
CN116228861A (en) | Probe station marker positioning method, probe station marker positioning device, electronic equipment and storage medium | |
CN116206125A (en) | Appearance defect identification method, appearance defect identification device, computer equipment and storage medium | |
CN115829929A (en) | Method, device and equipment for detecting defects of product surface image and storage medium | |
CN115063473A (en) | Object height detection method and device, computer equipment and storage medium | |
CN116579907B (en) | Wafer image acquisition method, device, equipment and readable storage medium | |
CN116342434B (en) | Image processing method, device, equipment and storage medium | |
CN116168442B (en) | Sample image generation method, model training method and target detection method | |
CN116542987B (en) | Image clipping method and device, electronic equipment 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 |