CN114202532A - Spraying defect detection method, device, equipment and storage medium - Google Patents
Spraying defect detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114202532A CN114202532A CN202111529643.1A CN202111529643A CN114202532A CN 114202532 A CN114202532 A CN 114202532A CN 202111529643 A CN202111529643 A CN 202111529643A CN 114202532 A CN114202532 A CN 114202532A
- Authority
- CN
- China
- Prior art keywords
- spraying
- target
- product
- detection area
- defect
- 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
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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method, a device and equipment for detecting a spraying defect and a storage medium. Wherein, the method comprises the following steps: acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with a target spraying product according to the description parameters of each spraying state; and if the defect quantization index is determined to be larger than or equal to the preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product. The embodiment of the invention solves the problem of judging whether the sprayed product is qualified or not, improves the detection capability of the sprayed product, and classifies the defect types of unqualified sprayed products.
Description
Technical Field
The embodiment of the invention relates to computer vision and data processing technologies, in particular to a method, a device, equipment and a storage medium for detecting a spraying defect.
Background
The existing spraying product has the problems that the viscosity and the water content of paint are influenced due to aging of equipment, poor debugging, temperature and humidity change in air and the like in the production process, so that the parameters of the spraying product are changed in the production process, and the pattern quality of the spraying product is finally influenced.
The inventor finds the defects in the prior art in the process of invention: the visual inspection of workers is the only means for solving the problem in the current factory, and a plurality of interference factors exist. For example, the interference factors may be factors such as human factors, light, weather, and the like, which cause a large amount of defective products to leak and flow out, and cause that unqualified spray products cannot be analyzed traceably. The standard of the sprayed product can not be quantized, so that the qualification judgment is purely subjective perception of individuals, and the quality and effective classification of the product can not be accurately judged. Therefore, the direct influence is that unqualified spray products appear in products delivered to customers due to different cognition, or the condition that the qualification rate of spray products which are too severely produced is too low is judged, and in any case, the direct influence can bring serious influence on the economic benefit and reputation of companies.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for detecting a spraying defect, which are used for judging whether a sprayed product is qualified or not and improving the detection capability of the sprayed product.
In a first aspect, an embodiment of the present invention provides a method for detecting a spraying defect, where the method includes:
acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image, wherein the target spraying product is obtained by spraying the outer surface of the target spraying product with a single color;
calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area;
calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter;
and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
Further, the acquiring a spraying detection gray scale image and identifying a target detection area matched with a target spraying product in the spraying detection gray scale image includes: acquiring an original shot image obtained after shooting the target spraying product, and performing binarization processing on the original shot image to obtain a spraying detection gray scale image; and identifying a closed area in the spraying detection gray-scale image through an edge detection technology, and determining the identified closed area as the target detection area.
Further, calculating a spraying state description parameter matched with the target spraying product according to the spraying color and the pixel value of each pixel point in the target detection area, and the method comprises the following steps: forming a regional pixel matrix according to the pixel value of each pixel point in the target detection region; forming a plurality of edge feature matrixes according to the area pixel matrix and a plurality of preset convolution kernels; wherein, different convolution kernels are used for extracting edge features of different positions in the target detection area; according to the edge extraction threshold determined by the spraying color, carrying out quantization processing on matrix elements in each edge characteristic matrix; and forming matrix element accumulated values respectively corresponding to each edge characteristic matrix according to the quantization processing result, wherein the matrix element accumulated values are used as the spraying state description parameters.
Further, calculating a spraying state description parameter matched with the target spraying product according to the spraying color and the pixel value of each pixel point in the target detection area, and the method comprises the following steps: and calculating the brightness value of the target detection area according to the brightness threshold value determined by the spraying color and the pixel value of each pixel point in the target detection area, and using the brightness value as the spraying state description parameter.
Further, the calculating of the spraying state description parameters matched with the target spraying product according to the form of the target detection area includes: calculating the perimeter and the area corresponding to the target detection area according to the form of the target detection area; and dividing the ratio of the circumference to the area as the spraying state description parameter.
Further, the calculating at least one spraying state description parameter matched with the target spraying product according to the pixel value of each pixel point in the target detection area includes: acquiring a standard spraying pattern matched with the target spraying product; calculating the pixel value of each pixel point in the target detection area and the pixel difference value between the pixel value of each pixel point in the standard spraying pattern; and taking the pixel difference value as the spraying state description parameter.
Further, the determining the defect type corresponding to the target spraying product includes: inputting the target detection area into a defect classification model trained in advance, and acquiring the defect type output by the defect classification model; wherein the defect types include: wire drawing, burrs, under-run, heavy oil, deformation, or skew.
In a second aspect, an embodiment of the present invention further provides a device for detecting a spraying defect, where the device for detecting a spraying defect includes:
the target detection area identification module is used for acquiring a spraying detection gray-scale image and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image, wherein the target spraying product is obtained by spraying the outer surface of the target spraying product by using a single color;
the spraying state description parameter calculation module is used for calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area;
the defect quantitative index calculation module is used for calculating a defect quantitative index matched with the target spraying product according to the spraying state description parameters;
and the defect type determining module is used for determining that the target spraying product is an unqualified spraying product and determining the defect type corresponding to the target spraying product if the defect quantization index is determined to be larger than or equal to a preset threshold value.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for detecting the spray defects according to any embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a storage medium readable by a computer, and having a computer program stored thereon, where the computer program is executed by a processor to implement the method for detecting a spraying defect according to any embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, a spraying detection gray-scale image is obtained, and a target detection area matched with a target spraying product is identified in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product. According to the embodiment of the invention, the problem of judging whether the sprayed product is qualified or not is solved, the detection capability of the sprayed product is improved, and the defect types of unqualified sprayed products are classified.
Drawings
Fig. 1 is a flowchart of a method for detecting a spraying defect according to an embodiment of the present invention;
FIG. 2 is a flowchart of another method for detecting defects in a coating according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for detecting a spraying defect according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention.
It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The terms "first" and "second," and the like in the description and claims of embodiments of the invention and in the drawings, are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not set forth for a listed step or element but may include steps or elements not listed.
Example one
Fig. 1 is a flowchart of a method for detecting a spraying defect according to an embodiment of the present invention. The embodiment can be applied to the condition that whether the spraying effect of the spraying product is qualified or not is detected after the spraying treatment is carried out on the outer surface of the product to obtain the spraying product. The method of the embodiment may be performed by a device for detecting a spraying defect, which may be implemented by software and/or hardware, and the device may be configured in a server or a terminal device.
Correspondingly, the method specifically comprises the following steps:
and S110, acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image.
Wherein the target spray product is obtained by spraying the outer surface of the target spray product with a single color.
The spraying detection gray-scale image can be an original shot image (generally, a color image) obtained by shooting a target spraying product, and the gray-scale image obtained by performing binarization processing on the original shot image. The spray-coated product can be a product for vehicles, aerospace devices, furniture manufacturing and the like. The target detection area may be an area in the spray detection gray scale where the target spray product is located.
Optionally, the obtaining a spraying detection gray scale image and identifying a target detection area matched with a target spraying product in the spraying detection gray scale image may include: acquiring an original shot image obtained after shooting the target spraying product, and performing binarization processing on the original shot image to obtain a spraying detection gray scale image; and identifying a closed area in the spraying detection gray-scale image through an edge detection technology, and determining the identified closed area as the target detection area.
The original shot image may be a color image obtained by shooting the target spray product with an electronic shooting device such as a camera and a mobile phone. The binarization processing may be to set the gray scale value of a point on the image to 0 or 255, that is, the whole image exhibits a distinct black-and-white effect, that is, a gray scale image with 256 brightness levels is selected by an appropriate threshold value to obtain a binarized image which can still reflect the whole and local features of the image. Edge detection techniques, which may be a fundamental problem in image processing and computer vision, aim to identify points in digital images where changes in brightness are significant, and significant changes in image properties typically reflect significant events and changes in properties. The closed region may be a target detection region where a target spray product match is found in the spray detection gray scale by an edge detection technique.
For example, assuming a car, the surface of the car needs to be painted with a red color. After the automobile is painted, the painting effect needs to be detected. The car needs to be photographed first and an original photographed image about the car can be obtained. Further, binarization processing needs to be performed on the original shot image, so as to obtain a spraying detection gray-scale image of the original shot image of the automobile. Since the original photographed image of the automobile is photographed, it cannot be completely avoided that other environments or things are not photographed. Therefore, the closed area is identified in the spraying detection gray-scale image through the edge detection technology, and the identified closed area is determined as the target detection area, namely the spraying detection gray-scale image needing to detect the automobile.
In this embodiment, the target spray product is first required to be photographed, and the original photographed image can be acquired. Specifically, the target spray product is obtained by spraying the outer surface of the target spray product with a single color. Further, binarization processing is carried out on the original shot image, and then a spraying detection gray level image is obtained. Correspondingly, a closed area is identified in the spraying detection gray scale image through an edge detection technology, and the identified closed area is determined as a target detection area.
The advantages of such an arrangement are: and performing binarization processing on the original shot image to obtain a spraying detection gray-scale image, further identifying a closed region in the spraying detection gray-scale image by an edge detection technology, and determining the closed region as a target detection region. Therefore, the area of the target spraying product in the original shot image can be directly positioned, and the target spraying product can be better detected.
S120, calculating at least one spraying state description parameter matched with the target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area.
The form of the target detection area may be a description of the shape of the target detection area of the target spray product in the captured image after the target spray product is captured, and may include parameter descriptions such as the perimeter of the target detection area and the area of the target detection area.
The spraying state description parameter may describe a spraying condition of the target spraying product, and may be obtained by jointly calculating a pixel value of each pixel point in the target detection area, a spraying color of the target spraying product, and a form of the target detection area.
Specifically, the painting status description parameter may be at least one item of image edge feature information corresponding to the target detection area, or image brightness description information of the target detection area, or information that may reflect the painting effect to a certain extent, such as a ratio of a perimeter to an area of the target detection area, which is not limited in this embodiment.
In a specific example, if the painting is performed uniformly enough when a single color is painted, the pixel values of the pixels in the target detection area should not be different greatly, and should be both white points or both black points, specifically, white points or black points, which is related to the actual painting color. Based on the above, after the brightness value of the target detection area is determined, the number value of the pixel points with poor spraying effect can be determined by combining the spraying color, and then the image brightness description information can be used as a spraying state description parameter.
And S130, calculating a defect quantization index matched with the target spraying product according to the spraying state description parameters.
The defect quantization index may be a value calculated by performing weighted summation according to a plurality of spray condition description parameters, and may reflect whether the target spray product is qualified or not according to the defect quantization index.
In the previous example, the spraying status description parameters matched with the target spraying product are calculated, specifically, the spraying status description parameters are respectively F1、F2、F3、F4And F5And the spray condition describing parameter F1Corresponding weight value alpha1Description of the spray State parameter F2Corresponding weight value alpha2Description of the spray State parameter F3Corresponding weight value alpha3Description of the spray State parameter F4Corresponding weight value alpha4And a spray condition description parameter F5Corresponding weight value alpha5. The value of the defect quantization index may be calculated, specifically, the defect quantization index may be calculated according to the following formula:
F＝α1F1+α2F2+α3F3+α4F4+α5F5
further, the magnitude of the value corresponding to the defect quantization index F may be determined.
S140, if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
The defect type can be a defect type possibly existing after the target spray product is sprayed, and can comprise defect types such as wire drawing, burrs, leaking bottoms, heavy oil, deformation or deflection.
In the previous example, when the defect quantization index F matched with the target spray product is calculated according to each spray state description parameter, it is required to determine whether the defect quantization index F is greater than or equal to a preset threshold value. If the defect quantization index F is larger than or equal to a preset threshold value, the target sprayed product is an unqualified sprayed product; and if the defect quantization index F is smaller than a preset threshold value, the target spray product is a qualified spray product. And classifying the defect types of the unqualified target spray products.
Optionally, the determining the defect type corresponding to the target spray product includes: inputting the target detection area into a defect classification model trained in advance, and acquiring the defect type output by the defect classification model; wherein the defect types include: wire drawing, burrs, under-run, heavy oil, deformation, or skew.
The defect classification model can be a model capable of classifying target detection areas corresponding to unqualified target spraying products. Specifically, the defect type output by the defect classification model may include stringiness, burrs, leaks, heavy oil, deformation, skew, or the like.
The advantages of such an arrangement are: the target detection area is input into a defect classification model trained in advance, so that the defect type output by the defect classification model can be obtained. Therefore, the defect type can be further reflected to workers according to the defect type, and unqualified spraying products can be processed in time.
According to the technical scheme provided by the embodiment of the invention, a spraying detection gray-scale image is obtained, and a target detection area matched with a target spraying product is identified in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product. According to the embodiment of the invention, the problem of judging whether the sprayed product is qualified or not is solved, the detection capability of the sprayed product is improved, and the defect types of unqualified sprayed products are classified.
Example two
Fig. 2 is a flowchart of another method for detecting a spraying defect according to an embodiment of the present invention. In this embodiment, at least one spraying status description parameter matched with the target spraying product is calculated according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area, and is further refined.
Correspondingly, the method specifically comprises the following steps:
s210, a spraying detection gray-scale image is obtained, and a target detection area matched with a target spraying product is identified in the spraying detection gray-scale image.
S220, calculating at least one spraying state description parameter matched with the target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area.
Specifically, S2201-S2203, S2211, S2221-S2222, and S2231-S2233 respectively describe four types of spraying status description parameters obtained by calculation, and in practical application, one item, multiple items, or all of the four types of spraying status description parameters may be calculated, and according to the calculation result, a defect quantification index matched with the target spraying product is calculated.
S2201, forming a regional pixel matrix according to the pixel value of each pixel point in the target detection region; forming a plurality of edge feature matrixes according to the area pixel matrix and a plurality of preset convolution kernels;
wherein, different convolution kernels are used for extracting edge features of different positions in the target detection area;
different pixel points correspond to different two-dimensional image coordinates, and an area pixel matrix can be formed by establishing mapping between the two-dimensional image coordinates and the matrix row and column positions. The area pixel matrix may be a matrix composed of pixel values of each pixel point in the target detection area to represent the target detection area. The preset convolution kernels can respectively extract different characteristics of the target detection area according to different convolution kernels. An edge feature matrix can be obtained by performing convolution solution on the area pixel matrix and a convolution kernel, and is used for describing an edge feature set obtained after the convolution kernel processing.
Specifically, the above calculation formula is as follows:
wherein, I is a spraying detection gray scale image for identifying a target detection area; i (x, y) is a pixel value corresponding to a pixel point at the x, y position in the target detection area; k is the convolution kernel, K (a, b) is the corresponding value in the convolution kernel; a and B are the length and width of the convolution kernel; x and Y are the sizes of the spraying detection gray level images for identifying the target detection area; g is the sum of all the features after the convolution kernel processing.
Specifically, convolution is performed according to a pixel value I (x, y) corresponding to a pixel point at an x, y position in the target detection region and a corresponding value K (a, b) in the convolution kernel, and an edge feature value G (x, y) corresponding to the x, y position in the edge feature matrix is solved. And adding all the edge characteristic values in the target detection area to obtain the sum G of all the characteristics after the corresponding convolution kernel processing. In the above formula, different convolution kernels can be selected for convolution, and different image features can be extracted respectively.
Illustratively, assume that the convolution kernels are each K1、K2、K3And K4Using the above convolution formula, the corresponding G can be obtained respectively1、G2、G3And G4。
S2202, according to the edge extraction threshold determined by the spraying color, the matrix elements in each edge characteristic matrix are quantized.
The edge extraction threshold may be a threshold set when the matrix elements in the edge feature matrix are determined to be black and white, and may further perform quantization processing on the matrix elements in each edge feature matrix.
When the selected spraying color is darker, but the color of the target spraying product is lighter relative to the spraying color, the selected threshold value is larger, namely larger than the edge extraction threshold value, the quantization value F is 1, and the color is judged to be white; on the other hand, the quantization value F is 0, and black is discriminated. And calculating the spraying state description parameters according to the quantized values obtained by the quantization processing.
When the selected spraying color is lighter, but the color of the target spraying product is darker than the spraying color, the selected threshold value is smaller, namely is larger than the edge extraction threshold value, the quantization value F is 0, and the target spraying product is judged to be black; on the other hand, the quantization value F is 1, and white is discriminated. And calculating the spraying state description parameters according to the quantized values obtained by the quantization processing.
Specifically, when the selected spraying color is darker, but the color of the target spraying product is lighter than the spraying color, the quantization processing can be performed according to the following formula:
when the matrix element in the edge feature matrix is greater than the edge extraction threshold 127, the quantization value F is 1, that is, white is determined. When the matrix elements in the edge feature matrix are less than or equal to the edge extraction threshold, the quantization value F is 0, that is, black is determined.
Illustratively, assume an edge feature matrix
The edge extraction threshold is set to 127. Specifically, when the matrix element in the edge feature matrix is greater than the edge extraction threshold, the quantization value F is 1, that is, white is determined. When the matrix elements in the edge feature matrix are less than or equal to the edge extraction threshold, the quantization value F is 0, that is, black is determined. Further, according to the quantization process, the edge feature matrix
Further, when the selected spraying color is lighter, but the color of the target spraying product is darker than the spraying color, the quantization process can be performed according to the following formula:
when the matrix element in the edge feature matrix is greater than the edge extraction threshold 127, the quantization value F is 0, that is, black is determined. When the matrix element in the edge feature matrix is less than or equal to the edge extraction threshold, the quantization value F is 1, that is, white is determined.
Illustratively, assume an edge feature matrix
The edge extraction threshold is set to 127. Specifically, when the matrix element in the edge feature matrix is greater than the edge extraction threshold, the quantization value F is 0, that is, black is determined. When the matrix element in the edge feature matrix is less than or equal to the edge extraction threshold, the quantization value F is 1, that is, white is determined. Further, according to the quantization process, the edge feature matrix
And S2203, according to the quantization processing result, matrix element accumulated values corresponding to each edge characteristic matrix are formed and used as the spraying state description parameters.
In the previous example, the edge feature matrix is calculated
And then, obtaining a quantization processing result, and further, calculating matrix element accumulated values respectively corresponding to each edge characteristic matrix to be used as the spraying state description parameters. Further, the spray condition describing parameter F13. Similarly, the corresponding F can be calculated2、F3And F4. Further, because the selected spray color is darker, the color of the target spray product is lighter than the spray color. When calculating F1、F2、F3And F4The larger the quantization value of (b), the more quantization values judged to be white. It is shown that the greater the probability of the target sprayed product being unqualified, the more specific the defect type corresponding to the target sprayed product may beIncluding a drain bottom, etc.
In the same way, the edge feature matrix is calculated
And then, obtaining a quantization processing result, and further, calculating matrix element accumulated values respectively corresponding to each edge characteristic matrix to be used as the spraying state description parameters. Further, the spray condition describing parameter F16. Similarly, the corresponding F can be calculated2、F3And F4. Further, because the selected spray color is lighter, the color of the target spray product is darker than the spray color. When calculating F1、F2、F3And F4The larger the quantization value of (a), the more the quantization value discriminated as black. The greater the probability that the target sprayed product after spraying is unqualified at this time, specifically, the defect type corresponding to the target sprayed product may include a missing bottom and the like.
S2211, calculating the brightness value of the target detection area according to the brightness threshold value determined by the spraying color and the pixel value of each pixel point in the target detection area, and using the brightness value as the spraying state description parameter.
The brightness threshold may be a threshold set for the brightness value of the target detection area.
Specifically, when the brightness value of the target detection area is greater than the brightness threshold, the pixel values of the pixels in the target detection area corresponding to the brightness threshold need to be accumulated, and the spraying status description parameter is calculated. For example, when the selected spray color is darker and the target spray product is lighter than the spray color, it may be determined that the spray color is less bright but the target spray product is more bright. Further, the greater the brightness threshold determined by the paint color. And calculating according to a formula F which is sum [ I (x, y) >190], wherein the larger the calculated value of the description parameter F of the spraying state is, the larger the probability that the target spraying product after spraying is unqualified is proved to be. On the contrary, the smaller the calculated F value of the spraying state description parameter is, the smaller the probability that the target spraying product after spraying is unqualified is proved to be.
Similarly, when the selected spraying color is lighter and the color of the target spraying product is darker than the spraying color, it may be determined that the brightness of the spraying color is higher, but the brightness of the color of the target spraying product is lighter. Further, the smaller the brightness threshold determined by the paint color. Therefore, the spraying state description parameter F can be calculated, and the spraying qualification rate of the target spraying product is further judged.
S2221, according to the form of the target detection area, calculating the perimeter and the area corresponding to the target detection area.
S2222, dividing the ratio of the circumference to the area as the description parameter of the spraying state.
The area corresponding to the target detection area may be calculated according to the form of the target detection area, specifically, by using the pixel value of each pixel point in the target detection area.
Illustratively, the spraying state description parameters can be calculated according to the form of the target detection area
When calculated F6The larger the value is, the longer the circumference of the target detection region is relative to the area of the target detection region, the longer the circumference of the target detection region is, and thus, the phenomenon of being unreasonable occurs. It can be shown that the greater the probability that the target sprayed product after spraying is unqualified, specifically, the defect type corresponding to the target sprayed product may include burrs or deformation. Conversely, the smaller the probability that the target spray product after spraying is defective at this time.
And S2231, acquiring a standard spraying pattern matched with the target spraying product.
The standard spraying pattern can be a spraying template pattern corresponding to the target spraying product.
S2232, calculating a pixel difference value between the pixel value of each pixel point in the target detection area and the pixel value of each pixel point in the standard spraying pattern.
The pixel difference value may be a difference value between a pixel value of each pixel in the target detection region and a pixel value of each pixel in the standard spraying pattern, and the pixel difference value is obtained.
And S2233, taking the pixel difference value as the spraying state description parameter.
Specifically, the spraying status description parameter F can be further calculated according to the pixel difference value7. When calculated F7The larger the difference value of the pixels between the pixel value of each pixel in the target detection area and the pixel value of each pixel in the standard spraying pattern is, the larger the probability that the target spraying product after spraying is unqualified is. When calculated F7The smaller the difference value, the smaller the pixel difference value between the pixel value of each pixel point in the target detection area and the pixel value of each pixel point in the standard spraying pattern, and the smaller the probability that the target spraying product after spraying is unqualified at this time.
Further, a spray condition describing parameter F7It is mainly reflected whether the image of the target spray product after spraying and the standard spray pattern have large area loss, so F7With respect to other spray condition describing parameters, F7The corresponding weighted value is larger, and the occupied proportion is higher.
And S230, calculating a defect quantization index matched with the target spraying product according to the spraying state description parameters.
S240, judging whether the defect quantization index is larger than or equal to a preset threshold value. If yes, go to S250; if not, go to S260.
And S250, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
And S260, determining the target spray product as a qualified spray product.
In the previous example, the parameters F are described according to the calculated spraying state1、F2、F3、F4、F5、F6And F7If different weights are assigned to different spray status description parameters, F can be set1、F2、F3、F4、F5、F6And F7Respectively corresponding weighted values of alpha1、α2、α3、α4、α5、α6And alpha7Then, the defect quantization index matched with the target spraying product can be calculated according to the following formula:
F＝α1(F1-β1)+α2(F2-β1)+α3(F3-β1)+α4(F4-β1)+α5(F5-β2)+α6F6+α7F7
and further, judging whether the target spraying product is qualified or not.
According to the technical scheme provided by the embodiment of the invention, a spraying detection gray-scale image is obtained, and a target detection area matched with a target spraying product is identified in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product. According to the embodiment of the invention, the spraying state description parameters are calculated by the method through various factors, so that the calculated spraying state description parameters are more accurate. And further, the defect quantization index is calculated according to the description parameters of the spraying state, so that whether the target spraying product is qualified or not is judged, the detection capability of the spraying product is improved, the defect types of unqualified spraying products can be classified, and the defect types are better fed back to workers for processing.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a device for detecting a spraying defect according to a third embodiment of the present invention, where the device for detecting a spraying defect according to the third embodiment of the present invention can be implemented by software and/or hardware, and can be configured in a server or a terminal device to implement a method for detecting a spraying defect according to the third embodiment of the present invention. As shown in fig. 3, the apparatus may specifically include: the device comprises a target detection area identification module 310, a spraying state description parameter calculation module 320, a defect quantization index calculation module 330 and a defect type determination module 340.
The target detection area identification module 310 is configured to obtain a spraying detection gray-scale image, and identify a target detection area matched with a target spraying product in the spraying detection gray-scale image, where the target spraying product is obtained by spraying an outer surface with a single color;
the spraying state description parameter calculating module 320 is configured to calculate at least one spraying state description parameter matched with the target spraying product according to at least one of a spraying color, a form of the target detection area, and a pixel value of each pixel point in the target detection area;
a defect quantitative index calculation module 330, configured to calculate a defect quantitative index matched with the target spray product according to each of the spray state description parameters;
the defect type determining module 340 is configured to determine that the target spray product is an unqualified spray product and determine a defect type corresponding to the target spray product if it is determined that the defect quantization index is greater than or equal to a preset threshold value.
According to the technical scheme provided by the embodiment of the invention, a spraying detection gray-scale image is obtained, and a target detection area matched with a target spraying product is identified in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product. According to the embodiment of the invention, the problem of judging whether the sprayed product is qualified or not is solved, the detection capability of the sprayed product is improved, and the defect types of unqualified sprayed products are classified.
On the basis of the foregoing embodiments, the target detection area identifying module 310 may be specifically configured to: acquiring an original shot image obtained after shooting the target spraying product, and performing binarization processing on the original shot image to obtain a spraying detection gray scale image; and identifying a closed area in the spraying detection gray-scale image through an edge detection technology, and determining the identified closed area as the target detection area.
On the basis of the foregoing embodiments, the spraying status description parameter calculating module 320 may be specifically configured to: forming a regional pixel matrix according to the pixel value of each pixel point in the target detection region; forming a plurality of edge feature matrixes according to the area pixel matrix and a plurality of preset convolution kernels; wherein, different convolution kernels are used for extracting edge features of different positions in the target detection area; according to the edge extraction threshold determined by the spraying color, carrying out quantization processing on matrix elements in each edge characteristic matrix; and forming matrix element accumulated values respectively corresponding to each edge characteristic matrix according to the quantization processing result, wherein the matrix element accumulated values are used as the spraying state description parameters.
On the basis of the foregoing embodiments, the spraying status description parameter calculating module 320 may be specifically configured to: and calculating the brightness value of the target detection area according to the brightness threshold value determined by the spraying color and the pixel value of each pixel point in the target detection area, and using the brightness value as the spraying state description parameter.
On the basis of the foregoing embodiments, the spraying status description parameter calculating module 320 may be specifically configured to: calculating the perimeter and the area corresponding to the target detection area according to the form of the target detection area; and dividing the ratio of the circumference to the area as the spraying state description parameter.
On the basis of the foregoing embodiments, the spraying status description parameter calculating module 320 may be specifically configured to: acquiring a standard spraying pattern matched with the target spraying product; calculating the pixel value of each pixel point in the target detection area and the pixel difference value between the pixel value of each pixel point in the standard spraying pattern; and taking the pixel difference value as the spraying state description parameter.
On the basis of the foregoing embodiments, the defect type determining module 340 may be specifically configured to: inputting the target detection area into a defect classification model trained in advance, and acquiring the defect type output by the defect classification model; wherein the defect types include: wire drawing, burrs, under-run, heavy oil, deformation, or skew.
The device for detecting the spraying defects can execute the method for detecting the spraying defects provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a structural diagram of a computer device according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the apparatus may be connected by a bus or other means, for example, in fig. 4.
The memory 420 serves as a computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the detection method of the spray defect in the embodiment of the present invention (for example, the target detection region identification module 310, the spray status description parameter calculation module 320, the defect quantization index calculation module 330, and the defect type determination module 340). The processor 410 executes various functional applications and data processing of the device by executing software programs, instructions and modules stored in the memory 420, so as to implement the above-mentioned method for detecting the spraying defects, which includes: acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the apparatus. The output device 440 may include a display device such as a display screen.
EXAMPLE five
Embodiments of the present invention also provide a computer-readable storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for spray defect detection, the method comprising: acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image; calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area; calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter; and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
Of course, the embodiment of the present invention provides a storage medium containing computer-readable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the method for detecting a spraying defect provided in any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the device for detecting a spraying defect, each included unit and module is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for detecting a spray defect is characterized by comprising the following steps:
acquiring a spraying detection gray-scale image, and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image, wherein the target spraying product is obtained by spraying the outer surface of the target spraying product with a single color;
calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area;
calculating a defect quantization index matched with the target spraying product according to each spraying state description parameter;
and if the defect quantization index is determined to be larger than or equal to a preset threshold value, determining that the target spraying product is an unqualified spraying product, and determining the defect type corresponding to the target spraying product.
2. The method of claim 1, wherein the obtaining a spray detection gray scale map and identifying a target detection area in the spray detection gray scale map that matches a target spray product comprises:
acquiring an original shot image obtained after shooting the target spraying product, and performing binarization processing on the original shot image to obtain a spraying detection gray scale image;
and identifying a closed area in the spraying detection gray-scale image through an edge detection technology, and determining the identified closed area as the target detection area.
3. The method according to claim 1 or 2, wherein the calculating of the painting status description parameter matching with the target painting product according to the painting color and the pixel value of each pixel point in the target detection area comprises:
forming a regional pixel matrix according to the pixel value of each pixel point in the target detection region; forming a plurality of edge feature matrixes according to the area pixel matrix and a plurality of preset convolution kernels;
wherein, different convolution kernels are used for extracting edge features of different positions in the target detection area;
according to the edge extraction threshold determined by the spraying color, carrying out quantization processing on matrix elements in each edge characteristic matrix;
and forming matrix element accumulated values respectively corresponding to each edge characteristic matrix according to the quantization processing result, wherein the matrix element accumulated values are used as the spraying state description parameters.
4. The method according to claim 1 or 2, wherein the calculating of the painting status description parameter matching with the target painting product according to the painting color and the pixel value of each pixel point in the target detection area comprises:
and calculating the brightness value of the target detection area according to the brightness threshold value determined by the spraying color and the pixel value of each pixel point in the target detection area, and using the brightness value as the spraying state description parameter.
5. The method according to claim 1 or 2, wherein the calculating of the spraying state description parameters matched with the target spraying product according to the form of the target detection area comprises:
calculating the perimeter and the area corresponding to the target detection area according to the form of the target detection area;
and dividing the ratio of the circumference to the area as the spraying state description parameter.
6. The method of claim 1 or 2, wherein the calculating at least one spray status description parameter matching the target spray product based on the pixel values of the pixels in the target detection region comprises:
acquiring a standard spraying pattern matched with the target spraying product;
calculating the pixel value of each pixel point in the target detection area and the pixel difference value between the pixel value of each pixel point in the standard spraying pattern;
and taking the pixel difference value as the spraying state description parameter.
7. The method of claim 1, wherein said determining a defect type corresponding to said target spray product comprises:
inputting the target detection area into a defect classification model trained in advance, and acquiring the defect type output by the defect classification model;
wherein the defect types include: wire drawing, burrs, under-run, heavy oil, deformation, or skew.
8. A device for detecting defects in a spray coating, comprising:
the target detection area identification module is used for acquiring a spraying detection gray-scale image and identifying a target detection area matched with a target spraying product in the spraying detection gray-scale image, wherein the target spraying product is obtained by spraying the outer surface of the target spraying product by using a single color;
the spraying state description parameter calculation module is used for calculating at least one spraying state description parameter matched with a target spraying product according to at least one of the spraying color, the form of the target detection area and the pixel value of each pixel point in the target detection area;
the defect quantitative index calculation module is used for calculating a defect quantitative index matched with the target spraying product according to the spraying state description parameters;
and the defect type determining module is used for determining that the target spraying product is an unqualified spraying product and determining the defect type corresponding to the target spraying product if the defect quantization index is determined to be larger than or equal to a preset threshold value.
9. Computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the method of detection of spray defects according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for detecting a spray defect according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529643.1A CN114202532A (en) | 2021-12-14 | 2021-12-14 | Spraying defect detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529643.1A CN114202532A (en) | 2021-12-14 | 2021-12-14 | Spraying defect detection method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114202532A true CN114202532A (en) | 2022-03-18 |
Family
ID=80653657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111529643.1A Pending CN114202532A (en) | 2021-12-14 | 2021-12-14 | Spraying defect detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202532A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114858737A (en) * | 2022-04-24 | 2022-08-05 | 广汽丰田汽车有限公司 | Automobile spraying quality detection method |
| CN115082463A (en) * | 2022-08-22 | 2022-09-20 | 聊城市宁泰电机有限公司 | Generator end cover visual detection method based on image data |
| CN115561249A (en) * | 2022-11-09 | 2023-01-03 | 松乐智能装备(深圳)有限公司 | Intelligent monitoring method and system for spraying equipment |
| CN116030065A (en) * | 2023-03-31 | 2023-04-28 | 云南琰搜电子科技有限公司 | Road quality detection method based on image recognition |
| CN117474910A (en) * | 2023-12-27 | 2024-01-30 | 陕西立拓科源科技有限公司 | Visual detection method for motor quality |
| CN117522775A (en) * | 2023-09-27 | 2024-02-06 | 湖南隆深氢能科技有限公司 | Product quality tracking method, system and medium based on CCM sheet coater |
| CN117522775B (en) * | 2023-09-27 | 2024-09-24 | 湖南隆深氢能科技有限公司 | Product quality tracking method, system and medium based on CCM sheet coater |
-
2021
- 2021-12-14 CN CN202111529643.1A patent/CN114202532A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114858737A (en) * | 2022-04-24 | 2022-08-05 | 广汽丰田汽车有限公司 | Automobile spraying quality detection method |
| CN115082463A (en) * | 2022-08-22 | 2022-09-20 | 聊城市宁泰电机有限公司 | Generator end cover visual detection method based on image data |
| CN115561249A (en) * | 2022-11-09 | 2023-01-03 | 松乐智能装备(深圳)有限公司 | Intelligent monitoring method and system for spraying equipment |
| CN116030065A (en) * | 2023-03-31 | 2023-04-28 | 云南琰搜电子科技有限公司 | Road quality detection method based on image recognition |
| CN117522775A (en) * | 2023-09-27 | 2024-02-06 | 湖南隆深氢能科技有限公司 | Product quality tracking method, system and medium based on CCM sheet coater |
| CN117522775B (en) * | 2023-09-27 | 2024-09-24 | 湖南隆深氢能科技有限公司 | Product quality tracking method, system and medium based on CCM sheet coater |
| CN117474910A (en) * | 2023-12-27 | 2024-01-30 | 陕西立拓科源科技有限公司 | Visual detection method for motor quality |
| CN117474910B (en) * | 2023-12-27 | 2024-03-12 | 陕西立拓科源科技有限公司 | Visual detection method for motor quality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114202532A (en) | Spraying defect detection method, device, equipment and storage medium | |
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN109598721B (en) | Defect detection method and device for battery pole piece, detection equipment and storage medium | |
| CN110596120A (en) | Glass boundary defect detection method, device, terminal and storage medium | |
| CN113379680B (en) | Defect detection method, defect detection device, electronic device and computer readable storage medium | |
| CN111582359B (en) | Image identification method and device, electronic equipment and medium | |
| CN113221881B (en) | Multi-level smart phone screen defect detection method | |
| CN106557740B (en) | The recognition methods of oil depot target in a kind of remote sensing images | |
| CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN112750113B (en) | Glass bottle defect detection method and device based on deep learning and linear detection | |
| CN116152261B (en) | Visual inspection system for quality of printed product | |
| CN111223078A (en) | Method for determining defect grade and storage medium | |
| CN117351001B (en) | Surface defect identification method for regenerated aluminum alloy template | |
| CN113221763A (en) | Flame identification method based on video image brightness | |
| CN117392042A (en) | Defect detection method, defect detection apparatus, and storage medium | |
| JP7383722B2 (en) | Method and system for defect detection in image data of target coatings | |
| CN112863194A (en) | Image processing method, device, terminal and medium | |
| CN114723728A (en) | Method and system for detecting CD line defects of silk screen of glass cover plate of mobile phone camera | |
| CN110751225A (en) | Image classification method, device and storage medium | |
| CN114612418A (en) | Method, device and system for detecting surface defects of mouse shell and electronic equipment | |
| CN116363136B (en) | On-line screening method and system for automatic production of motor vehicle parts | |
| CN118329910A (en) | Printing paper defect detection system and method based on machine vision | |
| CN117388261A (en) | Surface defect detection method, device, system, storage medium and computer equipment | |
| CN111523605B (en) | Image identification method and device, electronic equipment and 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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Jiannan Inventor after: Lu Gang Inventor before: Li Jiannan Inventor before: Xu Chengcong Inventor before: Lu Gang |
|
| CB03 | Change of inventor or designer information |