CN112991251A - Method, device and equipment for detecting surface defects - Google Patents
Method, device and equipment for detecting surface defects Download PDFInfo
- Publication number
- CN112991251A CN112991251A CN201911207458.3A CN201911207458A CN112991251A CN 112991251 A CN112991251 A CN 112991251A CN 201911207458 A CN201911207458 A CN 201911207458A CN 112991251 A CN112991251 A CN 112991251A
- Authority
- CN
- China
- Prior art keywords
- image
- gradient
- intensity
- product
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
Abstract
The invention discloses a method, a device and equipment for detecting surface defects, which are used for comparing a template image from two aspects of gradient strength and gradient direction, and can well highlight the defects and simultaneously reduce the occurrence of misjudgment. The method comprises the following steps: acquiring a gradient intensity image and a gradient direction image obtained by detecting a product; determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface; according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image; and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
Description
Technical Field
The invention relates to the technical field of industrial detection, in particular to a method, a device and equipment for detecting surface defects.
Background
The defect detection generally refers to the detection of defects on the surface of an article, and the detection of the defects on the surface mainly adopts a defect detection technology based on vision to detect the defects such as spots, pits, scratches, chromatic aberration, defects and the like on the surface of a workpiece.
The defect detection based on vision mainly comprises image acquisition, preprocessing, feature extraction and defect separation, wherein the key point is defect feature extraction, namely how to distinguish a defect part in a product from a background part of the product, most of the existing defect detection generally adopts gradient value difference to enhance the differentiability of the defect, but the defect detection is usually carried out only in the aspect of gradient strength, and because the background image of the product is usually not uniform, poor in consistency and large in interference, a single detection index in the aspect of gradient strength cannot well carry out defect feature extraction, the defect cannot be well separated, and the condition of defect misjudgment is easily generated.
Disclosure of Invention
The invention provides a method, a device and equipment for detecting surface defects, which are used for comparing gradient strength and gradient direction, inhibiting similar interference points by a non-maximum inhibition processing method, extracting defect characteristics more accurately, highlighting the defects well and reducing misjudgment.
In a first aspect, the present invention provides a method of surface defect detection, the method comprising:
acquiring a gradient intensity image and a gradient direction image obtained by detecting a product;
determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface;
according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image;
and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
As a possible implementation, determining a surface defect product from pixel values in the non-maximally suppressed image comprises:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
As a possible implementation manner, determining a surface defect product according to a pixel point belonging to a preset threshold range in the non-maximum suppression image includes:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
As a possible implementation manner, determining a surface defect product according to a pixel point belonging to a preset threshold range in the binary image includes:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As a possible implementation, the detecting the product to obtain the gradient strength image and the gradient direction image includes:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
As a possible implementation, determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image includes:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
As a possible implementation manner, performing non-maximum suppression processing on the gradient intensity value according to the gradient intensity value determined by the pixel point of the intensity difference image and the gradient direction value determined by the pixel point of the direction difference image to obtain a non-maximum suppression image includes:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
In a second aspect, the present invention provides an apparatus for surface defect detection, the apparatus comprising a gradient image acquisition module, a gradient difference image determination module, a non-maximum suppression processing module, and a defect product determination module, wherein:
the gradient image acquisition module is used for acquiring a gradient intensity image and a gradient direction image which are obtained by detecting a product;
a gradient intensity determining module, configured to determine an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determine a direction difference image according to the gradient direction image and the gradient direction template image, where the gradient intensity template image and the gradient direction template image are obtained by detecting a product with a defect-free surface;
the non-maximum inhibition processing module is used for carrying out non-maximum inhibition processing on the gradient intensity value according to the gradient intensity value determined by the pixel points of the intensity difference image and the gradient direction value determined by the pixel points of the direction difference image to obtain a non-maximum inhibition image;
and the defect product determining module is used for determining a product with surface defects according to the pixel values in the non-maximum suppression image.
As a possible implementation, the determining a defective product module is specifically configured to:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
As a possible implementation, the determining a defective product module is specifically configured to:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
As a possible implementation, the determining a defective product module is specifically configured to:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As a possible implementation, the gradient image acquisition module is specifically configured to:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
As a possible implementation, the determine gradient difference image module is specifically configured to:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
As a possible implementation, the non-maximum suppression processing module is specifically configured to:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
In a third aspect, the present invention provides an apparatus for surface defect detection, the apparatus comprising: a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of:
acquiring a gradient intensity image and a gradient direction image obtained by detecting a product;
determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface;
according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image;
and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
As a possible implementation, the processor is specifically configured to:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
As a possible implementation, the processor is specifically configured to:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
As a possible implementation, the processor is specifically configured to:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As a possible implementation, the processor is specifically configured to:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
As a possible implementation, the processor is specifically configured to:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
As a possible implementation, the processor is specifically configured to:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
In a fourth aspect, the present invention provides a computer storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
The method, the device and the equipment for detecting the surface defects have the following beneficial effects:
the method is used for comparing the gradient strength and the gradient direction, comparing the gradient strength in the gradient strength image and the gradient strength template image and the difference of the gradient direction in the gradient direction image and the gradient direction template image, restraining the interference caused by the background image of a product by a non-maximum restraining processing method, accurately detecting the gray level change of the image caused by the defect, well highlighting the defect and reducing the occurrence of misjudgment.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart of a method for surface defect detection according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an image of a product captured according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating gradient of pixel points in an image of a product acquired by using sobel algorithm according to an embodiment of the present invention;
FIG. 4 is a schematic view of an image of a product with a defect-free surface captured according to an embodiment of the present invention;
fig. 5 is a schematic diagram of performing non-maximum suppression processing on a gradient intensity value determined by a pixel point 5 in an intensity difference image according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating a detailed procedure for performing non-maximum suppression processing according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a binary image according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating an embodiment of a method for surface defect detection;
FIG. 9 is a schematic view of an apparatus for surface defect detection according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a surface defect detection apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The term "and/or" in the embodiments of the present invention describes an association relationship of associated objects, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The application scenario described in the embodiment of the present invention is for more clearly illustrating the technical solution of the embodiment of the present invention, and does not form a limitation on the technical solution provided in the embodiment of the present invention, and it can be known by a person skilled in the art that with the occurrence of a new application scenario, the technical solution provided in the embodiment of the present invention is also applicable to similar technical problems. In the description of the present invention, the term "plurality" means two or more unless otherwise specified.
The gradient strength and gradient direction proposed in the embodiment of the present invention will be briefly described below.
The gradient is essentially a first order partial differential vector, which is used to indicate that the directional derivative of a certain function at a certain point has a maximum along the direction, where the directional derivative of the function at this point has a maximum, called gradient direction, and the directional derivative along the gradient direction has a maximum, called gradient strength (also called modulus of gradient), and the specific gradient strength and gradient direction can be expressed by the following formulas:
1) the gradient can be expressed by the following equation:
wherein the content of the first and second substances,
grad (f) denotes gradient;
2) the gradient strength can be expressed by the following formula:
wherein mag (f) represents gradient strength;
3) the gradient direction can be expressed by the following formula:
where θ represents the gradient direction.
For most of the existing surface detection technologies, the difference between the gradient strength values determined by the pixels in the detection image and the gradient strength values determined by the pixels in the template image is usually adopted to determine whether defects exist, and since the detection is only performed in the aspect of the gradient strength, the change trend of the defect structure is not well distinguished, that is, the detection is not performed in the aspect of the gradient direction, for example, the same gradient strength value can have different gradient direction values, and in the same gradient direction, the detection of the gradient strength by the similar pixels may interfere, so that the detection result is inaccurate.
In order to solve the above technical problem, embodiments of the present invention provide a method for detecting surface defects, which considers detection from the gradient strength and the gradient direction, and can remove interfering pixels through non-maximum suppression processing, thereby more accurately detecting defective products.
As shown in fig. 1, the implementation flow of the method for detecting surface defects provided by the embodiment of the present invention is as follows:
in implementation, when a product is detected, the gradient strength and the gradient direction of each pixel point in the collected product image can be calculated by collecting the product image, so that the gradient strength value and the gradient direction value of each pixel point in the product image are obtained, the gradient strength image is determined according to the obtained gradient strength value of each pixel point, the gradient direction image is determined according to the obtained gradient direction value of each pixel point, and it can be understood that the gradient strength value of each pixel point is taken as a pixel value to obtain the gradient strength image, and the gradient direction value of each pixel point is taken as a pixel value to obtain the gradient direction image.
Alternatively, the captured image of the product may be as shown in fig. 2, wherein the box portion of the image is used to represent the defective portion of the product.
As an alternative embodiment, the gradient intensity image is obtained by detecting the product as follows:
and processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image.
In this embodiment, a sobel algorithm is used to calculate gradients of pixel points in an acquired image of a product, gradient strength of the pixel points in the image of the product is obtained according to the formula (2), and a gradient direction of the pixel points in the image of the product is obtained according to the formula (3).
As shown in fig. 3, the sobel algorithm is used to calculate the gradient of a pixel point in the collected image of the product, wherein, taking the pixel point 5 as an example, the gradient of the pixel point 5 is calculated according to the pixel values of the pixel points in 8 neighborhoods of the pixel point 5, and the calculation formula is as follows:
in the formula (4) and the formula (5), P1, P2, P3, P4, P6, P7, P8 and P9 respectively represent pixel values of pixel points 1, 2, 3, 4, 6, 7, 8 and 9;
the gradient strength of the pixel point P5 is calculated according to the formula (2), and the gradient direction of the pixel point P5 is calculated according to the formula (3).
It should be noted that, in the implementation, after the gradient intensity values of the image edge pixel points are calculated, the edges of the image may be filled by an interpolation method or an averaging method, and then the gradient intensity values of the edge pixel points are calculated.
in implementation, when a product with a defect-free surface is detected, an image of the product with the defect-free surface can be collected, the gradient strength and the gradient direction of each pixel point in the collected image of the product with the defect-free surface are calculated, so that the gradient strength value and the gradient direction value of each pixel point in the image of the product with the defect-free surface are obtained, a gradient strength template image is determined according to the obtained gradient strength value of each pixel point, and a gradient direction template image is determined according to the obtained gradient direction value of each pixel point.
Alternatively, the image of the product collected without surface defects may be as shown in FIG. 4.
The above-mentioned manner of collecting the image of the product includes, but is not limited to, a camera, an optical lens, a light source, etc. through a Charge Coupled Device (CCD) camera or a Complementary Metal Oxide Semiconductor (CMOS) chip, wherein the light source includes, but is not limited to, a halogen lamp, a fluorescent lamp, a light emitting diode, etc., and the present embodiment does not limit the manner of collecting the image of the product too much.
As an alternative embodiment, an intensity difference image is determined from the gradient intensity image and the gradient intensity template image by:
and obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value.
It is easy to understand that the gradient intensity image and the gradient intensity template image are obtained by calculating the gradient intensity of the pixel points in the image collected by the same product aiming at the image collected by the same product, so that the difference between the gradient intensity values determined by the pixel points at the same position in the gradient intensity image and the gradient intensity template image is used as a factor for detection by using the difference between the gradient intensity values in the gradient intensity image and the gradient intensity template image obtained by detecting the product, so as to obtain a new gradient intensity value, and the intensity difference image is determined according to the new gradient intensity value.
Optionally, if the new gradient strength value is smaller than zero, the direction difference image is determined according to an absolute value of the new gradient strength value.
It should be noted that the pixel value of the pixel point in the intensity difference image is the new gradient intensity value, and the new gradient intensity value obtained by subtracting the gradient intensity values determined by the pixel points at the same position is used as the pixel value of the pixel point at the same position, so that the intensity difference image is determined according to the new gradient intensity value obtained by subtracting the gradient intensity values determined by all the pixel points at the same position in the gradient intensity image and the gradient intensity template image;
for convenience of understanding, the relationship among the pixel values of the pixel points at the same position in the intensity difference image, the gradient intensity image and the gradient intensity template image is as follows:
the pixel value of a pixel point in the intensity difference image is equal to the pixel value of a pixel point in the gradient intensity image-the pixel value of a pixel point in the gradient intensity template image;
if the pixel value of the pixel point in the gradient intensity image is smaller than the pixel value of the pixel point in the gradient intensity template image, the pixel value of the pixel point in the intensity difference image is | the pixel value of the pixel point in the gradient intensity image-the pixel value of the pixel point in the gradient intensity template image |.
As an alternative implementation, the direction difference image is determined according to the gradient direction image and the gradient direction template image by:
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
It is easy to understand that the gradient direction image and the gradient direction template image are both acquired by aiming at the same product, and the gradient direction of the pixel points in the image acquired by the same product is calculated, so that the difference between the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image is used as another factor of detection by taking the difference between the gradient direction values in the gradient direction image and the gradient direction template image acquired by detecting the product as a difference, a new gradient direction value is obtained, and a direction difference image is determined according to the new gradient direction value.
Optionally, if the new gradient direction value is smaller than zero, the direction difference image is determined according to an absolute value of the new gradient direction value.
It should be noted that the pixel values of the pixels in the direction difference image are the new gradient direction values, and the new gradient direction values obtained by subtracting the gradient direction values determined by the pixels at the same position are used as the pixel values of the pixels at the same position, so that the direction difference image is determined according to the new gradient direction values obtained by subtracting the gradient direction values determined by all the pixels at the same position in the gradient direction image and the gradient direction template image;
for convenience of understanding, the relationship among the pixel values of the pixel points at the same position in the direction difference image, the gradient direction image and the gradient direction template image is as follows:
the pixel value of a pixel point in the direction difference image is equal to the pixel value of a pixel point in the gradient direction image-the pixel value of a pixel point in the gradient direction template image;
if the pixel value of the pixel point in the gradient direction image is smaller than the pixel value of the pixel point in the gradient direction template image, the pixel value of the pixel point in the direction difference image is | the pixel value of the pixel point in the gradient direction image-the pixel value of the pixel point in the gradient direction template image |.
As an alternative embodiment, the gradient intensity template image and the gradient direction template image are obtained after the product with no defect on the surface is detected in the following way:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image. For a specific calculation process, reference may be made to the description in step 100, and details are not described here.
102, performing non-maximum inhibition processing on the gradient intensity value according to the gradient intensity value determined by the pixel point of the intensity difference image and the gradient direction value determined by the pixel point of the direction difference image to obtain a non-maximum inhibition image;
the Non-Maximum Suppression (NMS) in the present embodiment may also be referred to as Non-Maximum Suppression (NMS), which may be understood as suppressing an element that is not a Maximum.
As an alternative embodiment, the non-maximally suppressed image is obtained by:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
In the specific implementation, two factors are required to be referred to in the non-maximum inhibition processing process, one is a gradient intensity value, and the other is a gradient direction value, because the pixel value of the pixel point in the intensity difference image is the gradient intensity value, and the pixel value of the pixel point in the direction difference image is the gradient direction value, the gradient direction value is referred to when the non-maximum inhibition processing is performed on the gradient intensity value, so that the detection is performed from two aspects of the gradient intensity and the gradient direction, the interference can be removed, and the defect can be detected more accurately.
As shown in fig. 5, the detailed description will be given by taking the non-maximum suppression processing as an example of the gradient intensity value determined by the pixel point 5 in the intensity difference image, wherein the gradient direction of the pixel point 5 is determined according to the gradient direction value of the pixel point at the same position in the intensity difference image as the pixel point 5 in the direction difference image.
As shown in fig. 6, the specific processing steps are as follows:
601, acquiring a pixel point which is adjacent to the pixel point 5 in the image with the intensity difference in the determined gradient direction;
as in fig. 5, the adjacent pixels of pixel 5 in the determined gradient direction are 1 and 9;
if the gradient intensity values of the pixel point 5, the pixel point 1 and the pixel point 9 in the intensity difference image are M5, M1 and M9 respectively;
603, judging whether the gradient intensity value of at least one adjacent pixel point is greater than the gradient intensity value of the pixel point 5, if so, executing a step 604, otherwise, executing a step 605;
And 103, determining a product with surface defects according to the pixel values in the non-maximum inhibition image.
As an optional implementation manner, the surface defect product is determined according to the pixel points belonging to the preset threshold range in the non-maximum suppression image.
Optionally, if a pixel point belonging to a preset threshold range exists in the non-maximum suppression image, determining that a product corresponding to the non-maximum suppression image is a surface defect product, otherwise, determining that the product corresponding to the non-maximum suppression image is not a surface defect product.
As an optional implementation manner, determining a surface defect product according to a pixel point belonging to a preset threshold range in the non-maximum suppression image includes:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
According to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range or not, the non-maximum suppression image is processed into a binary image in the following process:
setting the pixel value to be 1 if the pixel value in the non-maximum suppression image belongs to a preset threshold range, and setting the pixel value to be 0 if the pixel value in the non-maximum suppression image does not belong to the preset threshold range; or
Setting the pixel value to be 0 if the pixel value in the non-maximum suppression image belongs to a preset threshold range, and setting the pixel value to be 1 if the pixel value in the non-maximum suppression image does not belong to the preset threshold range.
One possible implementation manner is that if the pixel value in the non-maximum suppression image belongs to a preset threshold range, the pixel value is set to 1, and if the pixel value in the non-maximum suppression image does not belong to the preset threshold range, the pixel value is set to 0, and the binary image is as shown in fig. 7, where a white portion is a portion whose pixel value is 1 and is used for representing a defective portion of a product.
As an optional implementation manner, determining a surface defect product according to a pixel point belonging to a preset threshold range in the binary image includes:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As shown in fig. 8, the following describes specific implementation steps of a method for detecting surface defects according to this embodiment.
801, processing an acquired image of a product through a Sobel algorithm to obtain a gradient intensity image and a gradient direction image;
the steps 802 and 803 may be executed simultaneously.
and 806, determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
Based on the same inventive concept, the embodiment of the present invention further provides a device for detecting surface defects, and since the device is the device in the method in the embodiment of the present invention, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.
As shown in fig. 9, the apparatus includes a gradient image acquiring module 900, a gradient difference image determining module 901, a non-maximum suppression processing module 902, and a defect determining module 903, wherein:
an obtaining gradient image module 900, configured to obtain a gradient intensity image and a gradient direction image obtained by detecting a product;
a gradient difference determining image module 901, configured to determine an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determine a direction difference image according to the gradient direction image and the gradient direction template image, where the gradient intensity template image and the gradient direction template image are obtained by detecting a product with a defect-free surface;
a non-maximum suppression processing module 902, configured to perform non-maximum suppression processing on the gradient intensity value according to the gradient intensity value determined by the pixel point of the intensity difference image and the gradient direction value determined by the pixel point of the direction difference image, so as to obtain a non-maximum suppression image;
and a defect product determining module 903, configured to determine a product with a surface defect according to the pixel value in the non-maximum suppressed image.
As a possible implementation, the determine defective products module 903 is specifically configured to:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
As a possible implementation, the determine defective products module 903 is specifically configured to:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
As a possible implementation, the determine defective products module 903 is specifically configured to:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As a possible implementation, the acquire gradient image module 900 is specifically configured to:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
As a possible implementation, the determine gradient difference image module 901 is specifically configured to:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
As a possible implementation, the non-maximum suppression processing module 902 is specifically configured to:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
Based on the same inventive concept, the embodiment of the present invention further provides a device for detecting surface defects, and since the device is the device in the method in the embodiment of the present invention, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.
As shown in fig. 10, the apparatus includes: a processor 1000 and a memory 1001, wherein the memory 1001 stores program code, and when the program code is executed by the processor 1000, the processor 1000 executes the steps of:
acquiring a gradient intensity image and a gradient direction image obtained by detecting a product;
determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface;
according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image;
and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
As a possible implementation, the processor 1000 is specifically configured to:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
As a possible implementation, the processor 1000 is specifically configured to:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
As a possible implementation, the processor 1000 is specifically configured to:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
As a possible implementation, the processor 1000 is specifically configured to:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
As a possible implementation, the processor 1000 is specifically configured to:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
As a possible implementation, the processor 1000 is specifically configured to:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored, which when executed by a processor implements the following steps:
acquiring a gradient intensity image and a gradient direction image obtained by detecting a product;
determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface;
according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image;
and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of surface defect detection, the method comprising:
acquiring a gradient intensity image and a gradient direction image obtained by detecting a product;
determining an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determining a direction difference image according to the gradient direction image and the gradient direction template image, wherein the gradient intensity template image and the gradient direction template image are obtained after detecting a product with a defect-free surface;
according to the gradient strength value determined by the pixel point of the strength difference image and the gradient direction value determined by the pixel point of the direction difference image, carrying out non-maximum inhibition processing on the gradient strength value to obtain a non-maximum inhibition image;
and determining the product of the surface defect according to the pixel value in the non-maximum inhibition image.
2. The method of claim 1, wherein determining surface defect products from pixel values in the non-maximally suppressed image comprises:
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the non-maximum inhibition image.
3. The method of claim 2, wherein determining a surface defect product based on pixel points in the non-maximum suppressed image that fall within a predetermined threshold range comprises:
processing the non-maximum suppression image into a binary image according to whether the pixel value in the non-maximum suppression image belongs to a preset threshold range;
and determining a surface defect product according to the pixel points belonging to the preset threshold range in the binary image.
4. The method of claim 3, wherein determining the surface defect product according to the pixel points in the binary image belonging to the preset threshold range comprises:
if the number of the pixel points belonging to the preset threshold range is larger than a preset value, determining that a product corresponding to the binary image is a surface defect product; or
And if the area of the pixel points belonging to the preset threshold range in the binary image is larger than a preset value, determining that the product corresponding to the binary image is a surface defect product.
5. The method of claim 1, wherein detecting the product results in a gradient intensity image and a gradient direction image, comprising:
processing the acquired image of the product by a Sobel algorithm to obtain a gradient intensity image and a gradient direction image; or
The method for detecting the product with no defect on the surface to obtain the gradient intensity template image and the gradient direction template image comprises the following steps:
and processing the collected image of the product with a defect-free surface by a Sobel algorithm to obtain a gradient intensity template image and a gradient direction template image.
6. The method of claim 1, wherein determining an intensity difference image from the gradient intensity image and a gradient intensity template image, and determining a direction difference image from the gradient direction image and a gradient direction template image, comprises:
obtaining a new gradient intensity value by differentiating the gradient intensity values determined by the pixel points at the same positions in the gradient intensity image and the gradient intensity template image, and determining an intensity difference image according to the new gradient intensity value;
and obtaining a new gradient direction value by subtracting the gradient direction values determined by the pixel points at the same position in the gradient direction image and the gradient direction template image, and determining a direction difference image according to the new gradient direction value.
7. The method according to claim 1, wherein performing non-maximum suppression processing on the gradient intensity values according to the gradient intensity values determined by the pixel points of the intensity difference image and the gradient direction values determined by the pixel points of the direction difference image to obtain a non-maximum suppression image comprises:
setting the gradient intensity value of a target pixel point in the intensity difference image to be zero to obtain a non-maximum inhibition image;
the gradient intensity value determined according to at least one adjacent pixel point in the intensity difference image is larger than the gradient intensity value determined according to the target pixel point, the at least one adjacent pixel point is the adjacent pixel point in the gradient direction of the target pixel point, and the gradient direction of the target pixel point is determined according to the gradient direction value of the pixel point in the direction difference image, wherein the position of the pixel point in the intensity difference image is the same as that of the target pixel point.
8. An apparatus for surface defect inspection, the apparatus comprising a gradient image acquisition module, a gradient difference image determination module, a non-maximum rejection processing module, and a defective product determination module, wherein:
the gradient image acquisition module is used for acquiring a gradient intensity image and a gradient direction image which are obtained by detecting a product;
a gradient intensity determining module, configured to determine an intensity difference image according to the gradient intensity image and the gradient intensity template image, and determine a direction difference image according to the gradient direction image and the gradient direction template image, where the gradient intensity template image and the gradient direction template image are obtained by detecting a product with a defect-free surface;
the non-maximum inhibition processing module is used for carrying out non-maximum inhibition processing on the gradient intensity value according to the gradient intensity value determined by the pixel points of the intensity difference image and the gradient direction value determined by the pixel points of the direction difference image to obtain a non-maximum inhibition image;
and the defect product determining module is used for determining a product with surface defects according to the pixel values in the non-maximum suppression image.
9. An apparatus for surface defect inspection, the apparatus comprising: a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 7.
10. A computer storage medium having a computer program stored thereon, the program, when executed by a processor, implementing the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207458.3A CN112991251B (en) | 2019-11-29 | 2019-11-29 | Method, device and equipment for detecting surface defects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207458.3A CN112991251B (en) | 2019-11-29 | 2019-11-29 | Method, device and equipment for detecting surface defects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112991251A true CN112991251A (en) | 2021-06-18 |
| CN112991251B CN112991251B (en) | 2023-01-17 |
Family
ID=76330859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911207458.3A Active CN112991251B (en) | 2019-11-29 | 2019-11-29 | Method, device and equipment for detecting surface defects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991251B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419045A (en) * | 2022-03-30 | 2022-04-29 | 武汉中导光电设备有限公司 | Method, device and equipment for detecting defects of photoetching mask plate and readable storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007285754A (en) * | 2006-04-13 | 2007-11-01 | Seiko Epson Corp | Flaw detection method and flaw detector |
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
| US20110182495A1 (en) * | 2010-01-26 | 2011-07-28 | General Electric Company | System and method for automatic defect recognition of an inspection image |
| CN105675625A (en) * | 2016-03-03 | 2016-06-15 | 浙江大学 | Method for detecting fruit surface defects by virtue of segmentation of gradient iteration threshold |
| CN105891233A (en) * | 2016-05-26 | 2016-08-24 | 福州大学 | Intelligent detection system for surface defects of lens based on machine vision and implementation method of intelligent detection system |
| US20170278234A1 (en) * | 2014-12-15 | 2017-09-28 | Compagnie Generale Des Etablissements Michelin | Method for detecting a defect on a surface of a tire |
| CN107767369A (en) * | 2017-09-27 | 2018-03-06 | 杭州迈锐钶科技有限公司 | A kind of the defects of buret detection method and device |
| CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
| CN108230324A (en) * | 2018-01-31 | 2018-06-29 | 浙江理工大学 | Magnetic shoe surface microdefect visible detection method |
| CN108665458A (en) * | 2018-05-17 | 2018-10-16 | 杭州智谷精工有限公司 | Transparent body surface defect is extracted and recognition methods |
| CN109523541A (en) * | 2018-11-23 | 2019-03-26 | 五邑大学 | A kind of metal surface fine defects detection method of view-based access control model |
| CN110009601A (en) * | 2019-02-28 | 2019-07-12 | 南京航空航天大学 | Large-Scale Equipment irregular contour detection method of surface flaw based on HOG |
| CN110223296A (en) * | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
-
2019
- 2019-11-29 CN CN201911207458.3A patent/CN112991251B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007285754A (en) * | 2006-04-13 | 2007-11-01 | Seiko Epson Corp | Flaw detection method and flaw detector |
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
| US20110182495A1 (en) * | 2010-01-26 | 2011-07-28 | General Electric Company | System and method for automatic defect recognition of an inspection image |
| US20170278234A1 (en) * | 2014-12-15 | 2017-09-28 | Compagnie Generale Des Etablissements Michelin | Method for detecting a defect on a surface of a tire |
| CN105675625A (en) * | 2016-03-03 | 2016-06-15 | 浙江大学 | Method for detecting fruit surface defects by virtue of segmentation of gradient iteration threshold |
| CN105891233A (en) * | 2016-05-26 | 2016-08-24 | 福州大学 | Intelligent detection system for surface defects of lens based on machine vision and implementation method of intelligent detection system |
| CN108169236A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of cracks of metal surface detection method of view-based access control model |
| CN107767369A (en) * | 2017-09-27 | 2018-03-06 | 杭州迈锐钶科技有限公司 | A kind of the defects of buret detection method and device |
| CN108230324A (en) * | 2018-01-31 | 2018-06-29 | 浙江理工大学 | Magnetic shoe surface microdefect visible detection method |
| CN108665458A (en) * | 2018-05-17 | 2018-10-16 | 杭州智谷精工有限公司 | Transparent body surface defect is extracted and recognition methods |
| CN109523541A (en) * | 2018-11-23 | 2019-03-26 | 五邑大学 | A kind of metal surface fine defects detection method of view-based access control model |
| CN110009601A (en) * | 2019-02-28 | 2019-07-12 | 南京航空航天大学 | Large-Scale Equipment irregular contour detection method of surface flaw based on HOG |
| CN110223296A (en) * | 2019-07-08 | 2019-09-10 | 山东建筑大学 | A kind of screw-thread steel detection method of surface flaw and system based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| XIAOJING LIU 等: "Surface Defect Detection Based on Gradient LBP", 《2018 IEEE 3RD INTERNATIONAL CONFERENCE ON IMAGE, VISION AND COMPUTING (ICIVC)》 * |
| 赵丽花等: "基于图像梯度的印刷品缺陷检测算法研究", 《科技风》 * |
| 魏成禹 等: "轴承内套表面缺陷视觉检测装置的研制", 《中国硕士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114419045A (en) * | 2022-03-30 | 2022-04-29 | 武汉中导光电设备有限公司 | Method, device and equipment for detecting defects of photoetching mask plate and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112991251B (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11797886B2 (en) | Image processing device, image processing method, and image processing program | |
| CN109507192B (en) | Magnetic core surface defect detection method based on machine vision | |
| US9230318B2 (en) | Analysis of the digital image of the external surface of a tyre and processing of false measurement points | |
| WO2021109697A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
| CN109727244B (en) | Magnetic shoe surface crack detection method | |
| US20120207379A1 (en) | Image Inspection Apparatus, Image Inspection Method, And Computer Program | |
| CN111046862B (en) | Character segmentation method, device and computer readable storage medium | |
| CN111882568B (en) | Fire image edge extraction processing method, terminal and system | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| CN115880248B (en) | Surface scratch defect identification method and visual detection equipment | |
| JP7449507B2 (en) | Method of generating a mask for a camera stream, computer program product and computer readable medium | |
| CN113077437B (en) | Workpiece quality detection method and system | |
| JP2018096908A (en) | Inspection device and inspection method | |
| WO2021000948A1 (en) | Counterweight weight detection method and system, and acquisition method and system, and crane | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN112991251B (en) | Method, device and equipment for detecting surface defects | |
| WO2015115499A1 (en) | Tool inspection method and tool inspection device | |
| CN113935927A (en) | Detection method, device and storage medium | |
| JP2009198290A (en) | Flaw detection method and detector | |
| CN108269264B (en) | Denoising and fractal method of bean kernel image | |
| KR20160097651A (en) | Apparatus and Method for Testing Pattern of Sample using Validity Image Processing Technique, and computer-readable recording medium with program therefor | |
| CN115423756A (en) | Method for obtaining information of wafer edge point and positioning wafer | |
| CN115272173A (en) | Tin ball defect detection method and device, computer equipment and storage medium | |
| CN110021016B (en) | Calcification detection method | |
| CN113763491A (en) | Visual detection method for tobacco shred barrel residues |
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 | ||
| CB02 | Change of applicant information |
Address after: 230013 Southwest District of Hefei City, Anhui Province Applicant after: Hefei xinyihua Intelligent Machine Co.,Ltd. Address before: 230013 Southwest District of Hefei City, Anhui Province Applicant before: HEFEI SINEVA INTELLIGENT MACHINE Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |