Flexible material punching quality detection method and device, electronic equipment and storage medium

Abstract

The present application relates to the field of industrial machine vision and image processing technology, and is used for detecting the punching quality of flexible materials, in particular to a punching quality detection method and device of flexible materials, an electronic device and a storage medium, the punching quality detection method of flexible materials comprises the following steps: obtaining a to-be-detected image of the surface of the flexible material; correcting the to-be-detected image to obtain a corrected to-be-detected image; performing texture suppression processing on the corrected to-be-detected image to obtain a target to-be-detected image; calculating the inertia rate and the convexity of the target to-be-detected image; and obtaining the detection result of the punching quality of the flexible material based on the inertia rate and the convexity of the target to-be-detected image. The present application effectively solves the misjudgment problem caused by the stretching of the flexible material, and the detection yield of the stretched leather is improved by about 15% compared with the traditional roundness algorithm.

Description

Technical Field

[0001] This invention belongs to the field of industrial machine vision and image processing technology, specifically a method, device, electronic device and storage medium for detecting the quality of perforation in flexible materials. Background Technology

[0002] During the use of leather or synthetic leather, perforation is often required to improve properties such as breathability or light transmittance. For the quality inspection of perforations in leather, traditional detection methods based on global thresholding and morphology are commonly used. This method first acquires an image and performs binarization using manually set fixed parameters; then, it extracts the holes through connected component analysis; finally, it judges the quality based on roundness indicators. However, this method has the following problems: First, the threshold is rigid, resulting in high maintenance costs: the brightness of industrial light sources decays over time. In this method, once the brightness decreases, the fixed threshold cannot automatically follow, causing normal holes to be misjudged as background, requiring frequent shutdowns for manual calibration. Second, the geometric criteria are singular, leading to a high false negative rate: leather is normally subjected to tension and stretching. In this method, the roundness of the holes decreases after stretching, causing them to be misjudged as defective products. This method lacks the ability to distinguish between "stretching" and "tearing." Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, electronic device and storage medium for detecting the quality of perforations in flexible materials, which can accurately distinguish between noise, qualified deformed holes and tear defects.

[0004] According to one aspect of the present invention, a method for detecting the quality of perforations in flexible materials is provided, the method comprising:

[0005] Acquire the image of the surface of the flexible material to be tested; The image to be tested is corrected to obtain a corrected image to be tested; The texture suppression process is applied to the image to be corrected to obtain the target image to be tested. Calculate the inertia rate and convexity of the target image to be measured; The detection results of the perforation quality of flexible materials are obtained based on the inertia rate and convexity of the target image.

[0006] The beneficial effects are: This invention corrects the acquired image to remove the influence of non-uniformity of flexible materials on detection, resulting in a corrected image. Morphological background suppression is then applied to the corrected image to filter out skin texture interference, yielding the target image and improving detection accuracy. During the calculation of inertia rate and convexity, a grayscale histogram is statistically analyzed and Gaussian smoothed. The high-brightness characteristics of the vent holes are utilized to pinpoint the foreground peak of the histogram, allowing for dynamic calculation of the segmentation threshold based on the peak position. This enables automatic compensation for illumination changes. Furthermore, a cascaded classification strategy is employed, combining affine invariance inertia rate and convexity (characterizing edge integrity), to distinguish noise, qualified deformed holes, and torn defect holes.

[0007] According to another aspect of the present invention, a device for detecting the quality of perforations in flexible materials is provided, comprising: The acquisition unit is used to acquire the image of the surface of the flexible material to be tested. A correction unit is used to perform correction processing on the image to be tested to obtain a corrected image to be tested; The noise reduction unit is used to perform texture suppression processing on the image to be corrected to obtain the target image to be tested. The calculation unit is used to calculate the inertia rate and convexity of the target image under test; The result unit is used to acquire the inertia rate and convexity of the target image under test, and to obtain the detection result of the perforation quality of the flexible material based on the inertia rate and convexity of the target image under test.

[0008] According to another aspect of the present invention, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the above-described flexible material perforation quality inspection method.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program for causing a processor to execute the steps of the above-described flexible material perforation quality detection method.

[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a method for detecting the quality of perforation in flexible materials according to a specific embodiment of the present invention.

[0013] Figure 2 This is a block diagram illustrating the quality detection of perforation in flexible materials according to a specific embodiment of the present invention. Detailed Implementation

[0014] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Combination Figure 1 As shown, this invention provides a method for detecting the quality of perforations in flexible materials, such as... Figure 1 As shown, it includes the following steps: Preparation before testing: calibrate a 3×3 perspective transformation matrix M. persp And a 2×3 affine transformation matrix M affine Two ring buffers are created to store the camera's raw data stream and processed image data, respectively. The buffer size is set to 8192×10000 pixels to accommodate continuous scanning of large-format leather. A safe range for the dynamic threshold is set [T]. min ,T max ], such as [80,200], and the minimum effective connected area Area. min For example, 30 pixels; all of the above data can be stored in system memory, and after the system starts, it is read from the local XML format system configuration file.

[0016] Acquiring a test image of the flexible material surface includes acquiring a grayscale image of the flexible material surface and writing the image data into a raw buffer to form the test image I. raw (x,y); The image to be tested is corrected to obtain a corrected image to be tested, including: Iterate through the coordinates (x, y) of each pixel in the image to be tested, and use the perspective transformation matrix M perspCalculate its homogeneous coordinates [u,v,w] on the correction plane. T The calculation formula is shown below;

[0017] Calculate the normalized target coordinates (x', y') = (u / w, v / w); Since the calculated (x',y') is usually a floating-point number, the bilinear interpolation algorithm is used to calculate the gray value of the point to complete the perspective correction and obtain the perspective-corrected image; Apply affine transformation matrix M to the perspective-corrected image affine Eliminate shear deformation and generate a corrected image I. rect (x,y).

[0018] Texture suppression processing is performed on the image to be corrected to obtain the target image to be tested, including: Define a flat circular structuring element B with a size of 3×3, and its kernel matrix is ​​shown below;

[0019] Perform erosion operation: Traverse and correct the image under test I rect (x,y) is used to extract the minimum value within the area covered by the structuring element. Fine, bright noise from the skin texture is then removed to obtain the eroded image I. erode (x,y), the calculation formula is shown below;

[0020] In this formula, i represents the row index of structure element B, i.e., the offset relative to the horizontal axis, and j represents the column index of structure element B, i.e., the offset relative to the vertical axis.

[0021] Perform a dilation operation: Take the maximum value within the area covered by the structuring element in the eroded image to restore the main shape of the hole, thus obtaining the target image I. clean .

[0022] Calculate the inertia rate and convexity of the target image to be measured, including: Initialize an integer array of length 256, and iterate through the target image I to be tested. clean Count the frequency of each gray level to obtain the original histogram array H; To prevent spurious peaks from being generated by random noise, a one-dimensional normalized Gaussian convolution kernel of length 5 is constructed, G=[0.06,0.24,0.40,0.24,0.06], whose element sum is 1; Perform a convolution operation on the original histogram array H to obtain a smoothed histogram H', and its calculation formula is as follows;

[0023] Among them, i represents the gray level in this formula, with a range of 0 - 255; k represents the index of the convolution kernel. For a kernel with a length of 5, it is usually -2 to 2, and mirror padding is used for processing at the boundaries.

[0024] Scan the smoothed histogram H' in the high gray level interval [50, 255] to find the point with the largest value, denoted as the foreground main peak index P max ; Anomaly detection: If the frequency corresponding to P max is less than 0.1% of the total number of pixels, it is determined that the image is abnormal (blank or severely underexposed), terminate the subsequent detection steps and report an error; Starting from P max , perform a gradient search in the direction of decreasing gray level (index decreasing direction) to find the first local minimum point that satisfies H'[t] < H'[t 1] and H'[t] < H'[t + 1]. t is the index of the searched valley bottom, denoted as the valley bottom index t; Set the valley bottom index t as the optimal segmentation threshold T. If the calculated T exceeds the safe interval of the set dynamic threshold, force T = T last (the valid threshold of the previous frame).

[0025] Use the threshold T to perform binary processing on the image to generate a binary image I bin ; Adopt the two-pass scanning method (Two PassAlgorithm) to label the connected components. The first pass of scanning records the equivalent pairs, and the second pass of scanning analyzes the equivalent pairs and unifies the labels; For each labeled connected component Blobk, accumulate and calculate its zero-order moment M 00 (i.e., the area) and the first-order moment M 10 , M 01 , so as to obtain the centroid coordinates ([[]] , ) = (M 10 / M 00 , M 01 / M 00 ); Continue to calculate the second-order central moment μ 20 , μ 02 , μ 11 , and its calculation formula is as follows;

[0026] Where p represents the order of the moment in the x-direction, q represents the order of the moment in the y-direction, x represents the x-coordinate of a pixel in the connected domain, and y represents the y-coordinate of a pixel in the connected domain.

[0027] Construct the second-order moment covariance matrix and calculate its eigenvalues ​​λ1 (maximum eigenvalue) and λ2 (minimum eigenvalue), as shown in the following formula;

[0028] The two eigenvalues ​​represent the degree of divergence of the fitted ellipse along its major and minor axes, respectively. The inertia ratio (R) is calculated. inertia The calculation formula is shown below;

[0029] This feature represents the ratio of the minor axis to the major axis of the ellipse, ranging from (0,1]. When the hole is a perfect circle, R... inertia ≈1; When tensile deformation occurs, λ1 increases and λ2 decreases, resulting in R inertia decline.

[0030] The Graham scan method is used to extract the convex hull of edge pixels in connected components. Calculate the area of ​​a convex hull polygon using Green's Formula. hull ; Calculate convexity C onvex , is used to characterize the degree of indentation at the edge, and its calculation formula is shown below;

[0031] The detection results of the perforation quality of flexible materials are obtained based on the inertia rate and convexity of the target image: First-level filtering (noise removal): If the area of ​​the connected region is M 00 <Area min If it is determined to be residual texture noise, it will be discarded directly. Secondary judgment (tensile strength): If 0.5 <R inertia If the value is less than 0.9, it is considered a "qualified deformable hole". Although the hole is not perfectly round, it is considered to be a normal physical stretching of the flexible material and the drilling quality is deemed to be qualified. Level 3 decision (tear-resistant): If C onvex If the convexity is less than 0.85, regardless of the inertia rate value, it is judged as "edge tearing (NG)" because simple stretching will not cause a significant decrease in convexity. Level IV Judgment (Serious Defect): If R inertia <0.2, is judged as "crack or scratch (NG)"; The system counts the final number of qualified holes, updates the UI display, and sends the coordinates of abnormal holes to the lower-level PLC via the Modbus protocol for marking.

[0032] Combination Figure 2 As shown, embodiments of this application also provide a flexible material perforation quality inspection device, comprising: Storage unit, used to store configuration files; The acquisition unit is used to acquire the image of the surface of the flexible material to be tested. A correction unit is used to perform correction processing on the image to be tested to obtain a corrected image to be tested; The noise reduction unit is used to perform texture suppression processing on the image to be corrected to obtain the target image to be tested. The calculation unit is used to calculate the inertia rate and convexity of the target image under test; The result unit is used to acquire the inertia rate and convexity of the target image under test, and to obtain the detection result of the perforation quality of the flexible material based on the inertia rate and convexity of the target image under test.

[0033] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device enables the substrate drilling quality detection method provided in the above embodiments.

[0034] A computer system includes a Central Processing Unit (CPU), which performs various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) or loaded from storage into Random Access Memory (RAM), such as the methods described in the above embodiments. The RAM also stores various programs and data required for system operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0035] The following components are connected to the I / O interface: input sections including keyboards, mice, etc.; output sections including cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; storage sections including hard drives; and communication sections including network interface cards such as LAN (Local Area Network) cards and modems. The communication sections perform communication processing via networks such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical discs, magneto-optical discs, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as required.

[0036] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs various functions defined in the system of this application.

[0037] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0038] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0039] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0040] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for detecting the quality of substrate drilling. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0041] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the substrate drilling quality detection method provided in the various embodiments described above.

[0042] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

[0043] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0044] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for detecting the quality of perforations in flexible materials, characterized in that, Includes the following steps: Acquire the image of the surface of the flexible material to be tested; The image to be tested is corrected to obtain a corrected image to be tested; The image to be corrected is subjected to texture suppression processing to obtain the target image to be tested; Calculate the inertia rate and convexity of the target image under test; The detection results of the perforation quality of flexible materials are obtained based on the inertia rate and convexity of the target image.

2. The method for detecting the quality of perforation in flexible materials according to claim 1, characterized in that, The process of acquiring the image of the flexible material surface to be tested includes: acquiring a grayscale image of the flexible material surface.

3. The method for detecting the quality of perforation in flexible materials according to claim 1, characterized in that, The step of correcting the image to be tested to obtain a corrected image to be tested includes: Traverse each pixel in the grayscale image, calculate its homogeneous coordinates on the correction plane using the perspective transformation matrix, and calculate the normalized target coordinates. The grayscale value of the target coordinates is calculated using a bilinear interpolation algorithm to complete perspective correction and obtain a perspective-corrected image; An affine transformation matrix is ​​applied to the perspective-corrected image to eliminate shearing distortion and generate the corrected image to be tested.

4. The method for detecting the quality of perforation in flexible materials according to claim 1, characterized in that, The process of performing texture suppression processing on the image to be corrected to obtain the target image to be tested includes: Define a flat, circular structuring element; Traverse the image to be corrected, take the minimum value within the area covered by the structuring element, remove the fine skin texture highlights and noise, and obtain the eroded image; The maximum value within the area covered by the structuring element is taken from the eroded image to restore the main shape of the hole, thus obtaining the target image to be tested.

5. The method for detecting the quality of perforation in flexible materials according to claim 1, characterized in that, The calculation of the inertia rate and convexity of the target image to be measured includes: The gray-level histogram of the target image to be tested is statistically analyzed, and a one-dimensional smoothing process is performed using a discrete Gaussian convolution kernel to obtain a smoothed histogram. Search for the foreground peak of the grayscale histogram and dynamically calculate the optimal separation threshold based on the gradient descent principle; The target image to be tested is segmented using the aforementioned separation threshold, and connected components and their moment features are extracted using a two-pass scanning method. Analyze the eigenvalues ​​of the fitted ellipse to obtain the affine invariant inertia rate characteristics; Construct the convex hull of the connected components and calculate the convexity feature.

6. The method for detecting the quality of perforation in flexible materials according to claim 5, characterized in that, The process of statistically analyzing the grayscale histogram of the target image and performing one-dimensional smoothing using a discrete Gaussian convolution kernel includes: Initialize an integer array, iterate through the target image to be tested, count the frequency of each gray level, and obtain the original histogram array; Construct a one-dimensional normalized Gaussian convolution kernel and perform convolution operation on the original histogram array to prevent random noise from generating spurious peaks and obtain a smooth histogram.

7. The method for detecting the quality of perforation in flexible materials according to claim 6, characterized in that, During the convolution operation, the boundary is filled with a mirror image.

8. The method for detecting the quality of perforation in flexible materials according to claim 5, characterized in that, The process of searching for the foreground dominant peak of the grayscale histogram and dynamically calculating the optimal separation threshold based on the gradient descent principle includes: Scan the smooth histogram in the high grayscale range to find the point with the largest value, and record it as the foreground main peak index; If the frequency corresponding to the foreground main peak index is less than 0.1% of the total number of pixels, the image is judged to be abnormal, the subsequent detection steps are terminated and an error is reported; Starting from the foreground main peak index, perform gradient search towards lower grayscale to find the first local minimum point, which is then used as the valley. The index of the valley bottom is set as the optimal segmentation threshold; if the calculated segmentation threshold exceeds the preset safety range, the segmentation threshold is forced to be equal to the segmentation threshold of the previous frame.

9. A method for detecting the quality of perforation in flexible materials according to claim 5, characterized in that, The step of segmenting the target image using the separation threshold and extracting connected components and their moment features using a two-pass scanning method includes: The target image to be tested is binarized using the segmentation threshold to generate a binary image; Connected components are labeled using a two-pass scanning method: the first pass records equivalence pairs, and the second pass parses the equivalence pairs and unifies their labels; For each marked connected component, its zeroth moment and first moment are accumulated to obtain the centroid coordinates; Calculate the second-order central moment of the connected domain.

10. A method for detecting the quality of perforation in flexible materials according to claim 9, characterized in that, The analytical calculation of the eigenvalues ​​of the fitted ellipse includes: Construct a second-order moment covariance matrix, and use the second-order central moments of the connected domain to calculate the maximum and minimum eigenvalues ​​of the fitted ellipse. The maximum and minimum eigenvalues ​​represent the degree of divergence of the fitted ellipse in the directions of the major and minor axes, respectively. The inertia rate of the target image under test is calculated using the maximum and minimum eigenvalues.

11. A method for detecting the quality of perforation in flexible materials according to claim 5, characterized in that, The construction of the convex hull of the connected components and the calculation of convexity features include: The Graham scan method is used to extract the convex hull of edge pixels in connected components; Calculate the area of ​​a convex hull polygon using Green's theorem; Calculate the convexity of the target image to be tested.

12. The method for detecting the quality of perforation in flexible materials according to claim 5, characterized in that, The detection results of the perforation quality of flexible materials obtained based on the inertia rate and convexity of the target image include: If the area of ​​the connected component is less than the preset minimum effective connected component area, it is determined to be residual texture noise and is discarded directly. If 0.5 < inertia rate < 0.9, it is judged as "qualified deformable hole"; If the convexity is less than 0.85, regardless of the inertia rate value, it is judged as "edge tearing (NG)"; If the inertia rate is less than 0.2, it is judged as "crack or scratch (NG)".

13. A device for detecting the quality of perforation in flexible materials, characterized in that, include: Storage unit, used to store configuration files; The acquisition unit is used to acquire the image of the surface of the flexible material to be tested. A correction unit is used to perform correction processing on the image to be tested to obtain a corrected image to be tested; The noise reduction unit is used to perform texture suppression processing on the image to be corrected to obtain the target image to be tested. The calculation unit is used to calculate the inertia rate and convexity of the target image under test; The result unit is used to acquire the inertia rate and convexity of the target image under test, and to obtain the detection result of the perforation quality of the flexible material based on the inertia rate and convexity of the target image under test.

14. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the flexible material perforation quality inspection method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the flexible material perforation quality inspection method according to any one of claims 1 to 12.

Images