CN117825379A

CN117825379A - Method, device, equipment and storage medium for detecting surface layer defect of pressure joint film

Info

Publication number: CN117825379A
Application number: CN202311525940.8A
Authority: CN
Inventors: 王梓琳; 熊星
Original assignee: Suzhou HYC Technology Co Ltd
Current assignee: Suzhou HYC Technology Co Ltd
Priority date: 2023-11-16
Filing date: 2023-11-16
Publication date: 2024-04-05

Abstract

The application relates to a method and a device for detecting surface defects of a pressure joint film, computer equipment and a storage medium. The method comprises the following steps: after the multispectral detection equipment shoots the pressure joint to be detected to obtain a depth map, obtaining the depth map; the pressure joint to be detected is covered with a film; extracting characteristic values of the depth map, and removing fault defects based on depth value differences of all pixel points in the depth map; converting the depth map into a gray map, determining the position of the plane defect based on the gray value difference of each pixel point in the gray map, and removing the position in the corresponding position of the depth map to obtain a defect-free depth map; performing plane fitting according to the characteristic values based on the defect-free depth map to obtain a standard plane of the film; and determining the surface layer defect of the crimping joint to be detected according to the standard plane and the original depth map without the defect. The invention realizes the automatic detection of the coated copper head, solves the problem of reflective coating and improves the detection efficiency.

Description

Method, device, equipment and storage medium for detecting surface layer defect of pressure joint film

Technical Field

The application relates to the technical field of pressure welding joints, in particular to a pressure welding joint film surface defect detection method, a pressure welding joint film surface defect detection device, computer equipment and a storage medium.

Background

The press-fit (copper) is generally used for connecting electronic communication between electronic components, such as connection of wires to a circuit board, and thus must have high precision and stability. However, the manufacturing of the crimp joint itself has some technical problems in that the surface is generally provided with minute irregularities due to the copper as a material, which negatively affects the connection performance, and the crimp joint is generally subjected to a plating process in order to improve the conductivity and corrosion resistance of the crimp joint.

In order to determine whether the crimp joint can be used normally, it is necessary to detect the surface defects of the crimp joint and determine whether the crimp joint has defects or whether the type and degree of the defects are within acceptable ranges. In the prior art, a photo of the press joint is obtained by means of optical photographing and then is subjected to identification treatment, however, the existence of a film leads to failure of the traditional optical detection method, and the depth information of defects is covered due to reflection of light.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a crimp film surface defect detection method, device, computer apparatus, and storage medium that can accurately detect crimp surface defects.

In a first aspect, the invention provides a method for detecting defects on a surface layer of a pressure joint film. The method comprises the following steps:

after the multispectral detection equipment shoots the pressure joint to be detected to obtain a depth map, obtaining the depth map; the pressure joint to be detected is covered with a film;

extracting characteristic values of the depth map, and removing fault defects based on depth value differences of all pixel points in the depth map;

converting the depth map into a gray map, determining the position of the plane defect based on the gray value difference of each pixel point in the gray map, and removing the position in the corresponding position of the depth map to obtain a defect-free depth map;

performing plane fitting according to the characteristic values based on the defect-free depth map to obtain a standard plane of the film;

and determining the surface layer defect of the crimping joint to be detected according to the standard plane and the original depth map without the defect.

In one embodiment, determining the location of the planar defect based on the gray value difference of each pixel point in the gray map includes:

binarizing the gray level map to obtain a binary map;

scanning the binary image, finding out a plane defect in the binary image, and determining a first defect position of the plane defect;

in the gray level map, a second defect position corresponding to the first defect position is determined, and the gray level value of the second defect position is amplified to be more than a preset gray level threshold value, so that the plane defect position is highlighted.

In one embodiment, the binarizing process for the gray scale map to obtain a binary map includes:

determining a chamfer area of a crimping joint to be detected in the gray level diagram;

and performing binarization processing based on the color difference between the pressure joint to be detected and the background area, and setting the background area and the chamfer area of the pressure joint to be detected to be white.

In one embodiment, based on the defect-free depth map, performing plane fitting according to the feature values to obtain a standard plane of the film, including:

acquiring initial coordinates of each point of the pressure joint to be detected in the defect-free depth map;

polynomial fitting is carried out on each initial coordinate, and standard plane coordinates are obtained;

and constructing a standard plane according to the standard plane coordinates.

In one embodiment, determining a skin defect of the crimp joint to be inspected based on the standard plane and the original depth map without the defect removed includes:

acquiring the height difference value of each pixel point in the original depth map without the defects removed relative to a standard plane;

judging whether pixel points with the height difference value larger than or equal to a preset height threshold value exist in the original depth map or not, and obtaining a judging result;

and determining the quality result of the pressure joint to be detected according to the judging result.

In one embodiment, the multispectral detection device further shoots the pressure joint to be detected to obtain a two-dimensional image; the method further comprises the steps of:

and detecting the two-dimensional image to determine the two-dimensional defect of the crimping joint to be detected in the two-dimensional image.

In a second aspect, the invention also provides a device for detecting the surface defects of the press joint film. The device comprises:

the depth map acquisition module is used for acquiring a depth map after the multispectral detection equipment shoots the pressure joint to be detected to acquire the depth map; the pressure joint to be detected is covered with a film;

the characteristic value extraction module is used for extracting characteristic values of the depth map and removing fault defects based on the depth value difference of each pixel point in the depth map;

the gray level map conversion module is used for converting the depth map into a gray level map, determining the position of the plane defect based on the gray level value difference of each pixel point in the gray level map, and removing the position in the corresponding position of the depth map to obtain a defect-free depth map;

the plane fitting module is used for carrying out plane fitting according to the characteristic values based on the defect-free depth map to obtain a standard plane of the film;

and the defect determining module is used for determining the surface layer defect of the crimping head to be detected according to the standard plane and the original depth map without the defect.

In a third aspect, the invention also provides a system for detecting the coating defects of the surface layer of the press joint. The system comprises:

the transmission device is used for supporting the crimping head to be detected and driving the crimping head to be detected to move;

the multispectral detection device is arranged in the moving direction of the to-be-detected pressure joint and is used for acquiring a depth map of the to-be-detected pressure joint based on multispectral monitoring;

the computer device is in communication connection with the multispectral detection device and is used for receiving the depth map; the computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the invention also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:

According to the method, the device, the computer equipment and the storage medium for detecting the surface defects of the pressure joint film, the depth map of the pressure joint to be detected is shot through the multispectral detection equipment, and the characteristic value of the depth map is extracted first. And removing fault defects through the depth map, converting the fault defects into a gray level map, removing plane defects through the gray level map, obtaining a defect-free depth map, and then fitting according to characteristic values based on the defect-free depth map to obtain a standard plane of the film. At the moment, the standard plane is a plane without defects, and the surface defects on the pressure joint film to be detected can be determined by comparing the depth map with the standard plane. Compared with the traditional technology adopting an optical imaging method, the method solves the problem that the defects on the surface of the thin film cannot be detected when the optical imaging passes through the thin film, and the defects on the surface of the thin film of the copper head can be accurately detected by adopting a multispectral detection method. The invention realizes the automatic detection of the coated copper head, can rapidly and accurately detect the depth defect under the copper head film, distinguishes OK and NG according to the detection requirement, solves the problem of reflective coating and improves the detection efficiency. The innovative technology not only saves time, but also improves the detection precision, and brings remarkable advantages for product quality control.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.

FIG. 1 is a diagram showing an application environment of a method for detecting defects on a surface layer of a pressure joint film according to an embodiment;

FIG. 2 is a flow chart of a method for inspecting defects on a surface of a pressure joint film according to one embodiment;

FIG. 3 is a schematic diagram of a principle of detecting a crimp joint to be detected using a multispectral detection device;

FIG. 4 is a schematic diagram of a principle of testing a crimp joint to be tested using a line laser;

FIG. 5 is a depth map of a pressure joint to be tested taken in one embodiment;

FIG. 6 is a gray scale image obtained by graying a depth image according to one embodiment;

FIG. 7 is a standard plan view of a fitting result in one embodiment;

FIG. 8 is a schematic diagram of threshold segmentation in one embodiment;

FIG. 9 is a flow chart of a method for inspecting surface defects of a pressure joint film according to another embodiment;

FIG. 10 is a schematic diagram of defect depth values obtained by taking a standard plane obtained by fitting after fault defects and plane defects are not removed as a reference in one embodiment;

FIG. 11 is a schematic representation of defect depth values obtained with reference to a standard plane obtained by fitting a defect-free depth map in one embodiment;

FIG. 12 is a schematic diagram of defects identified in one embodiment;

FIG. 13 is a schematic diagram of defects identified in another embodiment;

FIG. 14 is a block diagram of a device for inspecting surface defects of a pressure joint film according to one embodiment;

fig. 15 is an internal structural view of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The method for detecting the surface defects of the pressure joint film, provided by the embodiment of the application, can be applied to an application environment shown in fig. 1. The pressure joint 102 to be detected is located on the transmission device 104, the multispectral detection device 106 faces the pressure joint 102 to be detected, and is used for acquiring an image of the pressure joint 102 to be detected, and the multispectral detection device 106 communicates with the server 108 through a network. The data storage system may store data that the server 108 needs to process. The data storage system may be integrated on the server 108 or may be located on a cloud or other network server.

The transmission device 104 transmits movement of the crimp head 102 to be detected, the multispectral detection apparatus 106 is disposed above the movement route, detects the crimp head moving to the right below it to acquire an image, and then transmits the image to the server 108, and the server 108 judges the image to determine whether defect detection of the crimp head 102 to be detected is OK (pass) or NG (no good, no pass). The server 108 may be implemented as a stand-alone server or as a server cluster of multiple servers. In addition, a detection module may be provided on the multispectral detection device 106, so that the image does not need to be sent to the server 108 for defect detection by itself.

In an exemplary embodiment, as shown in fig. 2, a method for detecting a defect of a surface layer of a pressure-bonding-head film is provided, and the method is applied to the server 108 in fig. 1 for illustration, and includes the following steps 202 to 206. Wherein:

202, after a multispectral detection device shoots a pressure joint to be detected to obtain a depth map, obtaining the depth map; the pressure joint to be detected is covered with a film.

In the process of the press joint, in order to improve the electrical property, corrosion resistance and connection quality of the product, a passivation solution spraying process is often adopted, and a transparent film is generated after solidification and covers the surface of the press joint.

The multispectral detection device irradiates the pressure joint to be detected by using light rays with a plurality of wavelengths, and obtains different characteristic information about objects or scenes, such as colors, shapes, textures, temperatures, humidity, chemical components and the like by analyzing reflection spectrums of different wavebands, as shown in fig. 3, and fig. 3 is a schematic diagram of the principle of detecting the pressure joint to be detected by using the multispectral detection device.

Compared with the traditional 3D detection, the influence of film reflection can be avoided, as shown in fig. 4, fig. 4 shows a schematic diagram of the principle of testing the crimping joint to be detected by using line laser. The multispectral detection device is used for projecting a light source with a specific wavelength, and scattering and reflection of light are caused by defects and properties of the surface of the transparent material, so that the wavelength, the light intensity and the deviation in the spectrum change, and the conventional 3D detection device can only detect the defects of the copper surface through the thin film.

The depth map refers to an image in which distance information of the crimp distance from the multispectral detection apparatus is recorded, and illustratively, the depth information can be extracted therefrom by combining image processing and a deep learning algorithm after acquiring the multispectral image. As shown in fig. 5, fig. 5 illustrates a crimp depth map acquired in one embodiment.

And 204, extracting characteristic values of the depth map, and removing fault defects based on the depth value difference of each pixel point in the depth map.

The characteristic value refers to a characteristic value of the to-be-detected crimping head in the depth map, and illustratively comprises a characteristic edge of the to-be-detected crimping head and a depth value of a characteristic point. Optionally, this is achieved by SIFT (Scale-invariant feature transform, scale invariant feature transform), HOG (Histogram of Oriented Gradient, directional gradient histogram) or CNN (Convolutional Neural Networks, convolutional neural network).

Each pixel point in the depth map is represented by a depth value, which may be a number between 0 and 1. Fault defects mean that the depth values of the areas have significant differences, such as pit defects, etc. Judging whether the region is a fault defect by judging the difference of the depth values of a certain region and other regions, if the difference value of the depth value of the certain region and the difference value of the other regions are greater than or equal to the difference threshold value, judging the region as the fault defect, and removing the fault defect by filtering.

It will be appreciated that the step of removing the defect of the depth map is done in the server, after removing the fault defect, the original depth map remains without removing the defect.

And 206, converting the depth map into a gray map, determining the position of the plane defect based on the gray value difference of each pixel point in the gray map, and removing the position in the corresponding position of the depth map to obtain a defect-free depth map.

The value of each pixel in the gray-scale map represents the brightness or intensity of the pixel and no longer contains color information or depth information, as shown in fig. 6, fig. 6 shows the gray-scale map after the depth map is grayed out in one embodiment.

The planar defect refers to a defect having no depth difference or a small difference in depth value, such as an oxidation defect, a scratch defect, or the like. Such defects have a significant difference in gray value from the peripheral region under the gray map, so that the plane defect position is determined based on the difference in gray value. Since the gray level map and the depth map correspond in position, planar defects are removed by filtering at the corresponding positions in the depth map.

And removing the fault defect and the plane defect to obtain a defect-free depth map.

And 208, performing plane fitting according to the characteristic values based on the defect-free depth map to obtain a standard plane of the film.

The characteristic value at least comprises the position and the depth of the characteristic point, so that the three-dimensional coordinate of the crimping joint to be detected is obtained.

The plane fitting refers to a process of fitting feature points to a plane, and specifically, the plane fitting is performed based on feature values of the feature points on the basis of a defect-free depth map.

And 210, determining the surface layer defect of the crimping joint to be detected according to the standard plane and the original depth map without the defect.

The standard plane of the film refers to the surface layer plane of the film obtained by fitting, and the standard plane of the film is a non-defective flat plane due to fitting based on a non-defective depth map.

In the pressure joint film surface layer defect detection method, the depth map of the pressure joint to be detected is shot through the multispectral detection equipment, and the characteristic value of the depth map is extracted first. And removing fault defects through the depth map, converting the fault defects into a gray level map, removing plane defects through the gray level map, obtaining a defect-free depth map, and then fitting according to characteristic values based on the defect-free depth map to obtain a standard plane of the film. At the moment, the standard plane is a plane without defects, and the surface defects on the pressure joint film to be detected can be determined by comparing the depth map with the standard plane. Compared with the traditional technology adopting an optical imaging method, the method solves the problem that the defects on the surface of the thin film cannot be detected when the optical imaging passes through the thin film, and the defects on the surface of the thin film of the copper head can be accurately detected by adopting a multispectral detection method.

In one exemplary embodiment, determining a plane defect location based on a gray value difference of each pixel point in a gray map includes: binarizing the gray level map to obtain a binary map; scanning the binary image, finding out a plane defect in the binary image, and determining a first defect position of the plane defect; in the gray level map, a second defect position corresponding to the first defect position is determined, and the gray level value of the second defect position is amplified to be more than a preset gray level threshold value, so that the plane defect position is highlighted.

The binary image is an image with only two pixel values, including black and white. Each pixel can take only one of black (typically represented by 0) or white (typically represented by 1).

Each pixel point in the gray level image has a gray level value, the pixel value of each pixel point in the gray level image is converted into a binary image with only two values, so that the binary image can be obtained, and the converted binary image is convenient to analyze and process, such as image segmentation and the like.

Illustratively, the method for converting the gray level map into the binary map comprises a global threshold method, an adaptive threshold method, an Otsu threshold method, an edge detection method and a morphological operation method: morphological operations, and the like. In short, the gray threshold is set, and the gray value greater than or equal to or less than the gray threshold is marked with 0 or 1, so that binarization can be realized.

In one possible implementation, the binarizing the gray scale map to obtain a binary map includes: determining a chamfer area of a crimping joint to be detected in the gray level diagram; and performing binarization processing based on the color difference between the pressure joint to be detected and the background area, and setting the background area and the chamfer area of the pressure joint to be detected to be white.

The joint to be detected can be a cylinder, and the side edge of the upper top surface of the cylinder is a chamfer. The purpose of the chamfer is to avoid sharp protrusions damaging the circuit. The chamfer area is the area where the chamfer is located.

The chamfer area is not required to be subjected to defect detection, the chamfer area and the background area are set to be the same white, and the main body part of the crimping head to be detected is set to be black, so that the chamfer area is regarded as the background area in subsequent defect detection, and defect detection is not performed on the chamfer area. It should be noted that the joint to be inspected is not completely black, and the planar defect is white after the binarization process.

Since the gradation values of the planar defects have differences, the planar defects can be made to be conspicuous by setting gradation threshold values and converting into a binary image. And determining a first defect position of the plane defect in the binary image, and amplifying the gray value of the area to realize the salification corresponding to a second defect position in the gray image.

In this embodiment, the gray level map is converted into the binary map, so that the first defect position of the planar defect can be identified conveniently, and after the second defect position of the gray level map is corresponding to the first defect position of the gray level map, the gray level value of the pixel point of the second defect position of the gray level map is amplified to make the planar defect obvious.

In one exemplary embodiment, based on the defect-free depth map, performing a plane fit according to the feature values to obtain a standard plane of the thin film, comprising: acquiring initial coordinates of each point of the pressure joint to be detected in the defect-free depth map; polynomial fitting is carried out on each initial coordinate, and standard plane coordinates are obtained; and constructing a standard plane according to the standard plane coordinates.

Because the press joint is a copper coating film, the reference surface is found to be required to fit the film, the traditional plane fitting can be calculated based on the whole relative plane to obtain the reference surface, but because of the metal characteristic of a product, the press joint is not a relatively completely smooth plane, and convex hulls or pits with different heights can be generated due to the coating film, so that if the whole plane fitting is adopted, abnormal points are substituted into the press joint to destroy the fitting result.

After the fault defect and the plane defect are removed, the dead pixel equivalent to the depth map is removed, and fitting is performed based on the reserved pixel. After the position coordinates and depth values of the reserved pixel points are determined, the three-dimensional coordinates of each pixel point under a world coordinate system are obtained, and plane polynomial fitting is carried out by combining the characteristic values, so that fitted standard plane coordinates are obtained, and a standard plane is constructed. The feature value is a feature depth value in the depth map, and the fitting result is corrected based on the feature value. As shown in fig. 7, fig. 7 shows a standard plan schematic of the fitting result in one embodiment.

In this embodiment, after removing the fault defect and the plane defect, a defect-free depth map is obtained, and a fitting plane is obtained based on the feature value and the feature fitting of each pixel point of the defect-free depth map, so as to avoid substituting abnormal points to destroy the fitting result.

In one embodiment, determining a skin defect of a crimp joint to be inspected from a standard plane and an original depth map of the unremoved defect includes: acquiring the height difference value of each pixel point in the original depth map without the defects removed relative to a standard plane; judging whether pixel points with the height difference value larger than or equal to a preset height threshold value exist in the original depth map or not, and obtaining a judging result; and determining the quality result of the pressure joint to be detected according to the judging result.

The depth map is an image with depth values, and after a standard plane obtained by fitting is determined, the depth values of all pixel points in the depth map can be converted into a distance difference from the standard plane.

The original depth map without the defects removed comprises depth value information, a height threshold value is preset, the height difference value of each pixel point of the original depth map is compared with the height threshold value, and if the pixel points with the height difference value being larger than the height threshold value exist, the quality result of the pressure joint to be detected is considered to be NG. If no pixel point with the height difference value larger than the height threshold value exists, the quality result of the joint to be detected is regarded as OK, and the joint to be detected is qualified. As shown in fig. 8, fig. 8 illustrates a schematic of thresholding in one embodiment.

In this embodiment, the preset height threshold is used as a standard for judging whether the quality of the to-be-detected crimp joint is qualified, the comparison is performed based on the depth value of the depth map and the height difference value of the standard plane, and the quality judgment result is determined according to the comparison result, without constructing a point cloud model, so that the efficiency is improved.

In one embodiment, the multispectral detection device further shoots the pressure joint to be detected to obtain a two-dimensional image; the method further comprises the steps of: and detecting the two-dimensional image to determine the two-dimensional defect of the crimping joint to be detected in the two-dimensional image.

The two-dimensional image can be based on a multispectral detection principle or an optical principle, and the two-dimensional defect is detected through the two-dimensional image after the pressure joint to be detected is shot.

As shown in fig. 9, in one embodiment, a method for detecting a surface defect of a crimp film includes the steps of:

902, acquiring a depth map after the multispectral detection equipment shoots a pressure joint to be detected to obtain the depth map; the pressure joint to be detected is covered with a film.

And 904, extracting characteristic values of the depth map, and removing fault defects based on the depth value difference of each pixel point in the depth map.

And 906, converting the depth map into a gray map, and determining a chamfer area of the crimping joint to be detected in the gray map.

908, performing binarization processing based on the color difference of the pressure joint to be detected and the background area, and setting the chamfer areas of the background area and the pressure joint to be detected to be white.

910, scanning the binary image to find out the planar defect in the binary image, and determining the first defect position of the planar defect.

912, determining a second defect position corresponding to the first defect position in the gray map, and amplifying the gray value of the second defect position to be more than a preset gray threshold value to make the plane defect position be obvious; and removing the depth map from the corresponding position of the depth map to obtain a defect-free depth map.

914, obtaining initial coordinates of each point of the pressure joint to be detected in the defect-free depth map; polynomial fitting is carried out on each initial coordinate, and standard plane coordinates are obtained; and constructing a standard plane according to the standard plane coordinates.

And 916, obtaining the height difference value of each pixel point in the original depth map without removing the defects relative to the standard plane.

918, judging whether pixel points with height difference values larger than or equal to a preset height threshold value exist in the original depth map, and obtaining a judging result; and determining the quality result of the pressure joint to be detected according to the judging result.

And 920, detecting the two-dimensional image to determine the two-dimensional defect of the crimping joint to be detected in the two-dimensional image.

Referring to fig. 10 and 11, fig. 10 shows a depth value of a defect obtained by taking a standard plane obtained by fitting after fault defect and plane defect are not removed as a reference, and fig. 11 shows a standard plane obtained by fitting a defect-free depth map as a reference, and a measurement result is-12.699. The result of fig. 12 is closer to a true value.

Referring to fig. 12 and 13, fig. 12 and 13 respectively show defects identified by the defect detection method provided by the present invention, wherein the depth value of the defect obtained in fig. 12 is 18.057, and the depth value of the defect obtained in fig. 13 is-6.4822. The defect detection method provided by the invention can accurately identify the defect on the crimping joint to be detected.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a device for detecting the surface defects of the pressure joint film, which is used for realizing the method for detecting the surface defects of the pressure joint film. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of the embodiment of the device for detecting surface defects of the press joint film provided below may be referred to as the limitation of the method for detecting surface defects of the press joint film hereinabove, and will not be repeated herein.

In one exemplary embodiment, as shown in fig. 14, there is provided a pressure joint film skin defect detection apparatus 1400, comprising: a depth map acquisition module 1402, a feature value extraction module 1404, a grayscale map conversion module 1406, a plane fitting module 1408, and a defect determination module 1410, wherein:

the depth map obtaining module 1402 is configured to obtain a depth map after the multispectral detection device captures a pressure joint to be detected to obtain the depth map; the pressure joint to be detected is covered with a film.

The feature value extracting module 1404 is configured to extract a feature value of the depth map, and remove a fault defect based on a difference of depth values of pixels in the depth map.

The gray map conversion module 1406 is configured to convert the depth map into a gray map, determine a position of a planar defect based on a gray value difference of each pixel point in the gray map, and remove the planar defect in a corresponding position of the depth map to obtain a defect-free depth map.

The plane fitting module 1408 is configured to perform plane fitting according to the feature values based on the defect-free depth map, so as to obtain a standard plane of the thin film.

The defect determining module 1410 is configured to determine a surface defect of the crimp joint to be detected according to the standard plane and the original depth map without the defect removed.

In one embodiment, the gray map conversion module 1406 is further configured to binarize the gray map to obtain a binary map; scanning the binary image, finding out a plane defect in the binary image, and determining a first defect position of the plane defect; in the gray level map, a second defect position corresponding to the first defect position is determined, and the gray level value of the second defect position is amplified to be more than a preset gray level threshold value, so that the plane defect position is highlighted.

In one embodiment, the gray map conversion module 1406 is further configured to determine a chamfer area of the crimp joint to be inspected in the gray map; and performing binarization processing based on the color difference between the pressure joint to be detected and the background area, and setting the background area and the chamfer area of the pressure joint to be detected to be white.

In one embodiment, the plane fitting module 1408 is further configured to obtain initial coordinates of points of the crimp joint to be detected in the defect-free depth map; polynomial fitting is carried out on each initial coordinate, and standard plane coordinates are obtained; and constructing a standard plane according to the standard plane coordinates.

In one embodiment, the defect determining module 1410 is further configured to obtain a height difference value of each pixel point in the original depth map with no defect removed with respect to the standard plane; judging whether pixel points with the height difference value larger than or equal to a preset height threshold value exist in the original depth map or not, and obtaining a judging result; and determining the quality result of the pressure joint to be detected according to the judging result.

In one embodiment, the multispectral detection device further shoots the crimp joint to be detected to obtain a two-dimensional image; the device for detecting the surface defects of the press joint film further comprises:

the two-dimensional defect determining module is used for detecting the two-dimensional image to determine the two-dimensional defect of the crimping joint to be detected in the two-dimensional image.

All or part of each module in the pressure joint film surface layer defect detection device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 15. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing depth map data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements a method for detecting surface defects of a crimp film.

It will be appreciated by those skilled in the art that the structure shown in fig. 15 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application is applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a crimp-connector surface coating defect detection system is provided, comprising: the transmission device is used for supporting the crimping head to be detected and driving the crimping head to be detected to move; the multispectral detection device is arranged in the moving direction of the to-be-detected pressure joint and is used for acquiring a depth map of the to-be-detected pressure joint based on multispectral monitoring; the computer device is in communication connection with the multispectral detection device and is used for receiving the depth map; the computer device comprises a memory in which a computer program is stored and a processor which, when executing the computer program, carries out the steps of the method embodiments described above.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. The method for detecting the surface defects of the press-fit thin film is characterized by comprising the following steps of:

after the multispectral detection equipment shoots a pressure joint to be detected to obtain a depth map, acquiring the depth map; the pressure joint to be detected is covered with a film;

converting the depth map into a gray map, determining the position of a plane defect based on the gray value difference of each pixel point in the gray map, and removing the position in the corresponding position of the depth map to obtain a defect-free depth map;

and determining the surface defects of the pressure joint to be detected according to the standard plane and the original depth map without the defects.

2. The method of claim 1, wherein determining the location of the planar defect based on the gray value differences for each pixel in the gray scale map comprises:

binarizing the gray level map to obtain a binary map;

and in the gray level map, determining a second defect position corresponding to the first defect position, and amplifying a gray level value of the second defect position to be more than a preset gray level threshold value so as to make the plane defect position be obvious.

3. The method according to claim 2, wherein the binarizing the gray scale map to obtain a binary map comprises:

determining a chamfering area of the pressure joint to be detected in the gray level diagram;

and performing binarization processing based on the color difference between the to-be-detected pressure joint and the background area, and setting the background area and the chamfer area of the to-be-detected pressure joint to be white.

4. The method of claim 1, wherein said performing a plane fit based on said defect-free depth map based on said eigenvalues results in a standard plane of said film, comprising:

and constructing the standard plane according to the standard plane coordinates.

5. The method of claim 1, wherein the determining the surface defects of the pressure joint to be inspected from the standard plane and the original depth map without defects removed comprises:

acquiring the height difference value of each pixel point in the original depth map without the defect removed relative to the standard plane;

6. The method according to claim 1, wherein the multispectral detection device further captures the crimp-to-be-detected joint to obtain a two-dimensional image; the method further comprises the steps of:

7. A pressure bonded film skin defect detection device, the device comprising:

the depth map acquisition module is used for acquiring a depth map after the multispectral detection equipment shoots the pressure joint to be detected to obtain the depth map; the pressure joint to be detected is covered with a film;

and the defect determining module is used for determining the surface layer defect of the pressure joint to be detected according to the standard plane and the original depth map without the defect.

8. The utility model provides a press joint top layer coating film defect detection system which characterized in that includes:

the multispectral detection device is arranged in the moving direction of the pressure joint to be detected and is used for acquiring a depth map of the pressure joint to be detected based on multispectral monitoring;

the computer equipment is in communication connection with the multispectral detection equipment and is used for receiving the depth map; the computer device comprising a memory storing a computer program and a processor implementing the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.