Leather wear quality visual detection method and system

Abstract

The invention relates to the technical field of industrial image processing, in particular to a leather wear quality visual detection method and system. The method comprises the following steps: smoothing a leather image based on a plurality of smoothing scales to obtain a plurality of smooth images, the elimination degrees of leather textures in the plurality of smooth images being different; determining the wear degree of each smooth image; determining the real wear degree of the leather based on the wear degree of each smooth image and the smooth scale of each smooth image; and determining the leather quality based on the real wear degree. The method can accurately determine the leather quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial image processing, in particular to a leather wear quality visual detection method and system. BACKGROUND

[0002] In the production process of leather products, the wear area may affect the appearance and service life of the product. By detecting the wear area, quality problems can be found in time to ensure that the product meets the quality standards.

[0003] In related technologies, the main way of leather surface wear detection is manual visual inspection, relying on professional personnel to observe the leather surface with the naked eye to judge the leather wear condition, such as whether there are scratches, cracks or discoloration, and then determine the leather quality.

[0004] However, manual visual inspection is easily affected by subjective factors such as fatigue and experience differences of the detector, and the wear judgment may not be accurate, resulting in low accuracy of leather quality detection. SUMMARY

[0005] In order to solve the technical problem of low accuracy of leather quality detection caused by manual visual inspection, the purpose of the present application is to provide a leather wear quality visual detection method and system, and the technical solution adopted is as follows: The embodiment of the present application provides a leather wear quality visual detection method, which comprises: smoothing a leather image based on a plurality of smoothing scales to obtain a plurality of smoothed images, the leather texture elimination degrees of which are different; determining the wear degree of each smoothed image; determining the real wear degree of the leather based on the wear degree of each smoothed image and the smoothing scale of each smoothed image; and determining the leather quality based on the real wear degree.

[0006] Optionally, the determination of the wear area of each smoothed image comprises: determining a best smoothed image from the plurality of smoothed images, the best smoothed image being a smoothed image that can eliminate the leather texture itself; performing threshold segmentation on the best smoothed image to obtain an initial wear area; and determining the wear area of other smoothed images based on the position of the initial wear area on the best smoothed image.

[0007] Optionally, the determination of the best smoothed image from the plurality of smoothed images comprises: determining the texture performance degree of each smoothed image in order from small to large smoothing scale until the texture performance degree of a first smoothed image is less than a texture performance degree threshold, the first smoothed image being any one of the plurality of smoothed images, and the texture performance degree being used to represent the display degree of the leather texture of a smoothed image; and determining the first smoothed image as the best smoothed image.

[0008] Optionally, the determining the texture performance degree of the first smoothed image comprises: performing threshold segmentation on the first smoothed image to obtain worn pixel points and non-worn pixel points in the first smoothed image; and determining the texture performance degree of the first smoothed image based on the number of the worn pixel points and the non-worn pixel points.

[0009] Optionally, the initial wear region comprises at least one first wear connected domain, and the determining the wear region corresponding to the second smoothed image based on the position of the initial wear region on the best smoothed image comprises: determining a geometric center of the at least one first wear connected domain, the second smoothed image being a smoothed image corresponding to a second smoothed scale, the second smoothed scale being an adjacent smoothed scale smaller than a maximum smoothed scale, the maximum smoothed scale being a smoothed scale corresponding to the best smoothed image; determining the geometric center of the at least one first wear connected domain as a clustering center, and performing a clustering operation on the second smoothed image to obtain at least one clustering cluster; and determining a region composed of an outer contour of the at least one clustering cluster as the wear region of the second smoothed image.

[0010] Optionally, the determining the wear degree of the second smoothed image based on the area and the number of connected domains of the wear region of the second smoothed image comprises: determining the number of wear connected domains corresponding to each clustering cluster; determining a ratio between the number of wear connected domains corresponding to the clustering cluster and the number of wear connected domains of a maximum clustering cluster as a weight of the each clustering cluster, the maximum clustering cluster being a clustering cluster including the most wear connected domains; and determining the wear degree of the second smoothed image based on the weight of each clustering cluster and the area of each clustering cluster.

[0011] Optionally, the leather wear quality visual detection method further comprises: performing morphological erosion on the wear region of each smoothed image to obtain the number of connected domains of the wear region of each smoothed image.

[0012] Optionally, the leather wear quality visual detection method further comprises: acquiring an initial leather image; performing grayscale processing on the initial leather image to obtain an initial grayscale image; and determining the initial grayscale image as the leather image.

[0013] The embodiment of the present application further provides a leather wear quality visual detection system, comprising a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of the leather wear quality visual detection method according to any one of the above.

[0014] The present application has the following advantages: The leather wear quality visual detection method provided by the embodiments of the present application can perform smoothing processing on the leather image based on multiple smoothing scales to obtain multiple smoothed images, then determine the wear degree of each smoothed image, determine the real wear degree of the leather based on the wear degree of each smoothed image and the smoothing scale of each smoothed image, and finally determine the leather quality based on the real wear degree. Since the leather texture elimination degrees of the multiple smoothed images obtained based on the multiple smoothing scales are different, the wear texture elimination degrees are also different, so the wear degrees under multiple smoothing scales can be obtained, the real wear degree of the leather obtained based on the wear degrees under multiple smoothing scales is more real and reliable, and the leather quality can be accurately determined based on this. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0016] Figure 1 A flowchart of a leather wear quality visual detection method provided by an embodiment of the present application; Figure 2 A flowchart of another leather wear quality visual detection method provided by an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of the leather wear quality visual detection method and system according to the present application are described in detail as follows by combining the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0019] In the production process of leather products, the wear area may affect the appearance and service life of the product. By detecting the wear area, quality problems can be found in time to ensure that the product meets the quality standards.

[0020] Currently, leather surface wear detection mainly relies on manual inspection or traditional image processing techniques. Manual inspection relies on professional personnel to observe the leather surface by naked eye and judge the wear condition such as scratches, cracks or discoloration. This method is intuitive and does not require complex equipment, but it is low in efficiency and is easily affected by subjective factors such as the fatigue of the inspector and the difference in experience, resulting in a high misjudgment rate.

[0021] Traditional image processing techniques analyze leather images through computer vision algorithms such as edge detection, threshold segmentation or morphological operations to automatically identify wear areas. This method has high automation and objectivity, can quickly process a large number of samples and generate quantitative data, greatly improving the detection efficiency and consistency.

[0022] However, the existing detection techniques still have the following defects: due to the existence of the inherent texture of the leather surface, since the natural texture presents a local gray level mutation similar to wear in the image, when directly detecting the wear of the leather using traditional threshold segmentation and edge detection, the inherent texture of the leather surface is often mistakenly divided into wear areas. Thus affecting the accuracy and reliability of the detection.

[0023] The specific scheme of the leather wear quality visual detection method and system provided by the present application will be described in detail below in combination with the drawings.

[0024] Please refer to Figure 1 which shows the flowchart of the leather wear quality visual detection method provided by an embodiment of the present application.

[0025] S101, smooth processing is performed on the leather image based on a plurality of smoothing scales to obtain a plurality of smoothed images.

[0026] Among the plurality of smoothed images, the leather texture is eliminated to different extents.

[0027] In the embodiment of the present application, the smoothing scale is a Gaussian filter smoothing scale, and the larger the smoothing scale, the greater the elimination degree of the leather texture.

[0028] It can be understood that the greater the elimination degree of the leather texture, the greater the elimination degree of the texture of the wear area.

[0029] Optionally, the leather image can be smoothed by a high-low filter.

[0030] It should be understood that the leather texture in different smoothed images is eliminated to different extents, and the smoothing degree is also different.

[0031] In an optional implementation, the leather image can be a leather image collected by an industrial-grade charge coupled device camera (CCD) camera.

[0032] Optionally, the resolution of the camera should be greater than or equal to 12 million pixels, the focal length of the micro lens is 60mm, the aperture is f / 8, the shooting distance is 50cm, and the image size is 512*512 pixels.

[0033] In an optional implementation, the leather image can be a gray image processed by the industrial-grade CCD camera.

[0034] Specifically, the initial leather image is collected by the above method, and then the initial leather image is processed to obtain an initial gray image; and the initial gray image is determined as the leather image.

[0035] Optionally, the gray processing can be performed by a histogram, and the histogram equalization can be used to enhance the overall contrast and eliminate the influence of too bright or too dark background and foreground on the picture.

[0036] It can be understood that the subsequent image processing based on the leather image after the gray processing can make the image processing simpler, and it is more convenient to perform threshold segmentation on the leather image based on the gray value of the leather image.

[0037] S102, determine the wear degree of each smooth image.

[0038] It should be understood that when the leather image is smoothed, not only the texture of the leather itself can be eliminated, but also the wear texture of the worn part on the leather can be eliminated.

[0039] It can be understood that because the smoothing degrees of different smooth images are different, the wear of the worn part on different smooth images is also different, and therefore the wear degree of each smooth image can be determined.

[0040] Optionally, the wear degree of each smooth image can be determined by the size of the wear area on each smooth image.

[0041] S103, determine the real wear degree of the leather based on the wear degree of each smooth image and the smoothing scale of each smooth image.

[0042] It can be understood that the wear degree on a single smooth image cannot represent the real wear degree of the leather, and therefore the real wear degree of the leather can be determined based on the wear degrees of multiple smooth images.

[0043] It should be understood that different smoothing scales produce different degrees of smoothing for the worn area and the unworn area of the leather, and the contrast between the two areas can to some extent reflect the wear depth of the worn area. The greater the contrast, the deeper the wear thickness of the worn area, and the more serious the wear degree. Therefore, different smoothing scales can be assigned corresponding weights based on the smoothing image of different smoothing scales. The greater the smoothing scale, the higher the wear weight. Finally, the wear degree of the leather of different smoothing scales is weighted and fused to obtain the final wear degree of the leather surface.

[0044] Optionally, the real wear degree of the leather image satisfies the following formula: ; wherein, represents the real wear degree of the leather, represents the number of the plurality of smoothing images, represents the wear degree of the first smoothing image, represents the wear degree of the first smoothing image, represents the wear degree of the first smoothing image.

[0045] It should be understood that since the wear degree is more serious in the smoothing image with a larger smoothing scale, the size of the weight can be determined by the smoothing scale. Since the weight influence coefficient of the smoothing scale on the wear degree should not be too large, the smoothing scale can be square root converted to make the weight change more gentle.

[0046] Optionally, the weight of one smoothing image satisfies the following formula: ; wherein, represents the wear degree of the first smoothing image, represents the wear degree of the first smoothing image, represents the wear degree of the first smoothing image. S104, determining the quality of the leather based on the real wear degree.

[0047] It should be understood that the greater the real wear degree, the worse the quality of the leather, and the smaller the real wear degree, the better the quality of the leather.

[0048] In an optional implementation, a quality interval can be demarcated, and the quality of the leather is determined based on the interval to which the real wear degree belongs.

[0049] In an optional implementation, the wear degree of each smoothing image can be normalized to make the real wear degree a constant less than or equal to 1, and the quality interval is set between 0 and 1.

[0050]

[0051] ​​For example, when the actual wear level is greater than or equal to 0.7, the leather is determined to be severely worn; when the actual wear level is less than 0.7 but greater than or equal to 0.3, the leather is determined to be slightly worn; and when the actual wear level is less than 0.3, the leather is determined to be normal leather.

[0052] In this embodiment, since the degree of leather texture elimination in the multiple smooth images obtained based on multiple smoothing scales is different, the degree of wear texture elimination is also different. Therefore, the wear degree under multiple smoothing scales can be obtained. The true wear degree of leather obtained based on the wear degree under multiple smoothing scales is more realistic and reliable. Based on this, the leather quality can be accurately determined.

[0053] Combination Figure 1 ,like Figure 2 As shown, the above S102 is mainly implemented through S201-S202.

[0054] S201. Determine the wear area for each smoothed image.

[0055] In this context, a wear region consists of at least one wear-connected domain.

[0056] It should be understood that wear on the leather surface is not necessarily a single piece, but may consist of multiple small wear areas. In the embodiments of this application, a wear connectivity region represents a small wear area.

[0057] Understandably, because the sharpness of each smoothed image is different, the number of worn connected regions displayed in the worn area of ​​each smoothed image is also different.

[0058] It should be understood that morphological erosion operations can highlight the main structure and eliminate slight adhesion. In one implementation of this application, morphological erosion can be performed on the worn area of ​​each smooth image to obtain the number of connected regions of the worn area of ​​each smooth image.

[0059] In one alternative implementation, each smoothed image can be thresholded to obtain worn and unworn regions.

[0060] In one implementation of this application, the best smoothed image can be determined from multiple smoothed images first, and the best smoothed image can be thresholded to obtain the initial wear region; then, based on the position of the initial wear region on the best smoothed image, the wear regions of other smoothed images can be determined.

[0061] The best smoothed image is one that can eliminate the texture of the leather itself.

[0062] It can be understood that, due to different texture performance of the leather in different smooth images under different smooth scales, there is a smooth scale that can make the texture of the leather just smooth for different smooth images, and at this time, the smooth image can be determined as the best smooth image, and the smooth scale is determined as the best smooth scale.

[0063] In an optional implementation, the texture performance of each smooth image can be determined in order of the smooth scale from small to large until the texture performance of a smooth image is less than the texture performance threshold (for example, the first smooth image), and then the first smooth image is determined as the best smooth image.

[0064] It should be understood that the texture performance is used to represent the display degree of the texture of the leather in a smooth image.

[0065] It can be understood that, the greater the smooth scale, the smaller the texture performance, and when a smaller smooth scale can just eliminate the texture of the leather, it is meaningless to perform filtering with a larger smooth scale, and it will reduce the texture performance of the wear area, and therefore, the best smooth scale is determined in order from small to large, so that a smooth image with the highest clarity and capable of eliminating the texture of the leather can be obtained.

[0066] It should be understood that the first smooth image is any one of the plurality of smooth images.

[0067] Optionally, a Gaussian filter strength range can be selected, and then the plurality of smooth scales can be obtained in a preset step size from the smallest smooth scale.

[0068] In an optional implementation, threshold segmentation can be performed on any smooth image (for example, the first smooth image) to obtain wear pixel points and non-wear pixel points in the first smooth image; and then the texture performance of the first smooth image is determined based on the number of the wear pixel points and the non-wear pixel points.

[0069] Optionally, the first smooth image can be segmented by Otsu threshold segmentation.

[0070] Optionally, the first smooth image can be segmented based on the Otsu threshold segmentation by the gray value of the smooth image.

[0071] It should be understood that, after the first smooth image is segmented, the foreground pixel points and the background pixel points of the first smooth image can be obtained, the foreground pixel points are the wear pixel points, and the background pixel points are the non-wear pixel points.

[0072] It can be understood that the number of worn-out pixel points can represent the texture performance degree of the worn-out area, and the number of non-worn-out pixel points can represent the texture performance degree of the leather texture. Therefore, based on the number of worn-out pixel points and the number of non-worn-out pixel points, the texture performance degree of the first smoothed image can be determined.

[0073] It should be understood that the leather texture performance degree needs to be determined based on the pixel points of the leather area, and therefore, the leather area needs to be determined from the first smoothed image.

[0074] Specifically, the smoothed image can be divided into a plurality of image blocks, and then the proportion ratio of the number of foreground pixel points and the number of background pixel points in each image block is determined. The image block with a proportion ratio less than a proportion threshold is determined as the image block of the leather area. The average value of the proportion ratio in the image block of the leather area is determined as the texture performance degree of the first smoothed image.

[0075] Exemplarily, the size of the image block can be 8*8 pixels, and the proportion threshold can be 0.7.

[0076] Optionally, the texture performance degree of a smoothed image satisfies the following formula: ; wherein, represents the texture performance degree, represents the proportion ratio of the image block, represents the number of image blocks with a proportion ratio less than 0.7.

[0077] It should be understood that based on the above formula, the leather area can be first screened out, and then based on the proportion ratio of the non-worn-out pixel points and the worn-out pixel points of the leather area, the texture performance degree obtained can accurately represent the display degree of the leather texture.

[0078] Optionally, when the texture performance degree is less than a texture performance degree threshold, the smoothed image can be determined as the best smoothed image.

[0079] It can be understood that since the texture performance degree can represent the display degree of the leather texture, when the texture performance degree is less than the texture performance degree threshold, it means that the leather texture in the smoothed image has been basically eliminated. At this time, the smoothed image is determined as the best smoothed image, and the best smoothed image obtained is more reliable.

[0080] In the embodiment of the present application, after obtaining the best smoothed image, the initial worn-out area of the best smoothed image can be obtained based on the above threshold segmentation result.

[0081] Optionally, the image block with a proportion ratio greater than or equal to 0.7 can be determined as the initial worn-out area. ​

[0082] In an optional implementation, since the plurality of smoothed images are obtained from a leather image, the approximate positions of the wear areas on the plurality of smoothed images are similar, and after the initial wear area of the best smoothed image is obtained, the wear area of the smoothed image corresponding to the adjacent smoothing scale can be traced according to the initial wear area.

[0083] Specifically, assuming that the adjacent smoothing scale is a second smoothing scale and the smoothed image corresponding to the second smoothing scale is a second smoothed image, the step of determining the wear area of the second smoothed image can be divided into steps one to three.

[0084] Step one, determine the geometric center of at least one first wear connected domain.

[0085] The at least one first wear connected domain is a wear connected domain included in the initial wear area.

[0086] In combination with the description of the above embodiments, it should be understood that at least one wear connected domain is included in a wear area, and in the embodiments of the present application, the wear connected domain included in the initial wear area is determined as the first wear connected domain.

[0087] It should be understood that since the initial wear area is the wear area of the best smoothed image and the smoothing scale of the best smoothed image is the maximum smoothing scale, the second smoothing scale is an adjacent smoothing scale smaller than the maximum smoothing scale.

[0088] It can be understood that the second smoothing scale is adjacent to the maximum smoothing scale, and therefore the definition of the second smoothed image is relatively close to the definition of the best smoothed image, and the difference between the wear area on the second smoothed image and the initial wear area is also relatively small, so that the wear area of the second smoothed image can be determined based on the initial wear area.

[0089] Optionally, morphological closing operation can be performed on the initial wear area to obtain at least one first wear connected domain included in the initial wear area.

[0090] In an optional implementation, the position of the at least one first wear connected domain on the second smoothed image can be determined based on the pixel position of the geometric center of the at least one first wear connected domain.

[0091] Step two, determine the geometric center of the at least one first wear connected domain as a clustering center, and perform clustering operation on the second smoothed image to obtain at least one clustering cluster.

[0092] Specifically, the second smooth image is clustered with at least one first wear communication domain as a clustering center to find an area with close distance and high pixel density in the second smooth image, so as to obtain at least one cluster, and the update and matching of the communication domain in the second smooth image can be realized, and each first wear communication domain corresponds to a matched cluster in the smooth image of the adjacent and smaller smooth scale.

[0093] Optionally, a clustering algorithm (density-based spatial clustering of applications with noise, DBSCAN) can be used for clustering.

[0094] Step three, the area composed of the circumscribed contour of the at least one cluster is determined as the wear area of the second smooth image.

[0095] Optionally, the wear area of the smooth image corresponding to the smaller smooth scale can be determined based on the geometric center of the wear communication domain included in the wear area of the second smooth image. The above steps one to three can be repeatedly executed to obtain the wear area of each smooth image in sequence.

[0096] It should be understood that the wear area of the smooth image corresponding to the adjacent smooth scale can be obtained in sequence based on the above steps one to three. Since the definition of the smooth image of the adjacent smooth scale is small, the difference between the wear areas is small, and therefore, the wear area of each smooth image can be accurately obtained based on the method, and the difference between the wear areas of different smooth images can be clearly reflected.

[0097] S202, determine the wear degree corresponding to each smooth image based on the area and the number of communication domains of the wear area of each smooth image.

[0098] It should be understood that the number of communication domains is the number of wear communication domains in the wear area of each smooth image.

[0099] It can be understood that for the smooth images of different smooth scales, the larger the wear area, the greater the wear degree of the leather, and the more the number of wear communication domains, the more scattered the wear area of the leather, and the smaller the wear degree.

[0100] The following takes the second smooth image as an example to illustrate the method for determining the wear degree of the smooth image.

[0101] Specifically, the number of wear communication domains corresponding to each cluster is determined, then the ratio between the number of wear communication domains corresponding to the cluster and the number of wear communication domains of the largest cluster is determined as the weight of each cluster, and finally, the wear degree of the second smooth image is determined based on the weight of each cluster and the area of each cluster.

[0102] wherein the maximum cluster is the cluster including the largest number of wear connected domains.

[0103] Optionally, the number of wear connected domains corresponding to each cluster can be obtained based on the morphological erosion operation.

[0104] Optionally, the number of wear connected domains of each cluster can be normalized to obtain the weight of the cluster.

[0105] Optionally, the weight of a cluster satisfies the following formula: ; wherein, W represents the weight of the i-th cluster, W represents the number of wear connected domains included in the i-th cluster, W represents the number of wear connected domains included in the maximum cluster. It should be understood that, based on the above formula, the weight of the cluster can be determined, which can avoid the weight being greater than 1 and can reflect the size of the number of connected domains included in the cluster.

[0106] Optionally, the wear degree of a smoothed image satisfies the following formula:

[0107] ; ; wherein, W represents the wear degree of a smoothed image, N represents the number of clusters in the smoothed image, W represents the weight of the i-th cluster, A represents the area of the i-th cluster. Based on the formula, the area of each cluster can be summed after being weighted, to obtain the wear degree of the smoothed image.

[0108] In the embodiments of the present application, since the larger the area of the wear region, the greater the wear degree of the leather, and the more the number of wear connected domains, it indicates that the wear region is more dispersed and the wear degree of the leather is smaller. Therefore, after the wear region of each smoothed image is determined, based on the area of the wear region of each smoothed image and the number of wear connected domains of the wear region, the wear degree of each smoothed image can be accurately represented.

[0109]

[0110] ​​​The application further provides a leather wear quality visual detection system, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0111] It should be noted that the above-mentioned embodiment sequence is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0112] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments.

Claims

1. A visual inspection method for leather wear quality, characterized in that, The method includes: The leather image is smoothed based on multiple smoothing scales to obtain multiple smoothed images, and the degree of leather texture elimination in the multiple smoothed images is different; Determine the degree of wear for each smoothed image; The true degree of wear on the leather is determined based on the degree of wear in each smoothed image and the smoothing scale of each smoothed image; The quality of the leather is determined based on the actual degree of wear.

2. The method for visually inspecting leather wear quality according to claim 1, characterized in that, Determining the degree of wear for each smoothed image includes: Determine the wear region for each smoothed image, wherein a wear region consists of at least one wear connected region; The degree of wear of each smoothed image is determined based on the area of ​​the worn region and the number of connected components in each smoothed image.

3. The method for visually inspecting leather wear quality according to claim 2, characterized in that, Determining the wear area of ​​each smoothed image includes: The optimal smoothing image is determined from the plurality of smoothing images, wherein the optimal smoothing image is a smoothing image that can eliminate the texture of the leather itself; The optimal smooth image is segmented using a threshold to obtain the initial wear region; Based on the location of the initial wear area on the best smoothed image, the wear areas of other smoothed images are determined.

4. The method for visually inspecting leather wear quality according to claim 3, characterized in that, Determining the optimal smoothed image from the plurality of smoothed images includes: The texture representation degree of each smoothed image is determined sequentially in order of increasing smoothness scale, until the texture representation degree of the first smoothed image is less than the texture representation degree threshold. The first smoothed image is any one of the plurality of smoothed images. The texture representation degree is used to characterize the degree of display of leather texture in a smoothed image. The first smoothed image is determined as the optimal smoothed image.

5. The method for visually inspecting leather wear quality according to claim 4, characterized in that, Determine the texture representation of the first smoothed image, including: Threshold segmentation is performed on the first smoothed image to obtain worn and unworn pixels in the first smoothed image; The texture representation of the first smoothed image is determined based on the number of worn pixels and the number of unworn pixels.

6. The method for visually inspecting leather wear quality according to claim 3, characterized in that, The initial wear region includes at least one first wear connected region. Based on the position of the initial wear region on the optimal smoothed image, the wear region corresponding to the second smoothed image is determined, including: Determine the geometric center of the at least one first worn connected region, the second smoothed image is the smoothed image corresponding to the second smoothed scale, the second smoothed scale is the adjacent smoothed scale smaller than the maximum smoothed scale, and the maximum smoothed scale is the smoothed scale corresponding to the best smoothed image; The geometric center of the at least one first worn connected domain is determined as the cluster center, and a clustering operation is performed on the second smooth image to obtain at least one cluster. The region formed by the outer contours of the at least one cluster is defined as the wear region of the second smoothed image.

7. The method for visually inspecting leather wear quality according to claim 6, characterized in that, The degree of wear in the second smoothed image is determined based on the area of ​​the worn region and the number of connected components, including: Determine the number of worn connected components corresponding to each cluster; The ratio between the number of worn connected components corresponding to the cluster and the number of worn connected components of the largest cluster is determined as the weight of each cluster, where the largest cluster is the cluster with the most worn connected components. The degree of wear on the second smoothed image is determined based on the weight and area of ​​each cluster.

8. The method for visually inspecting leather wear quality according to claim 2, characterized in that, The method further includes: Morphological erosion is performed on the worn region of each smoothed image to obtain the number of connected regions in the worn region of each smoothed image.

9. The method for visually inspecting leather wear quality according to claim 1, characterized in that, The method further includes: Acquire initial leather images; The initial leather image is converted to grayscale to obtain an initial grayscale image; The initial grayscale image is identified as the leather image.

10. A visual inspection system for leather wear quality, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the visual inspection method for leather wear quality as described in any one of claims 1-9.

Images