Image segmentation method, image segmentation device, material sorting equipment and storage medium

Abstract

The invention relates to the technical field of image processing, in particular to an image segmentation method, an image segmentation device, material sorting equipment and a storage medium. The image segmentation method is applied to the material sorting equipment and comprises the following steps: acquiring a to-be-processed image; determining material contour information of material adhesion in the to-be-processed image and a local image corresponding to the material contour information; determining candidate segmentation points for segmenting the local image based on the material contour information; determining a candidate segmentation path of the local image based on the plurality of extreme points in the local image; determining a target segmentation strategy based on a matching result between the candidate segmentation points and the candidate segmentation paths; and segmenting the local image according to the target segmentation strategy to obtain a target image. According to the method, the recognition precision of the adhesion position can be improved in a multi-dimensional feature coupling mode, the segmentation efficiency can be improved, the reliability, accuracy and robustness of the segmentation result can be guaranteed, and the material sorting performance of the material sorting equipment can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of image processing, and in particular to an image segmentation method, an image segmentation device, a material sorting device, and a computer-readable storage medium. Background Art

[0002] In the material mining and processing industry, material segmentation is a crucial link. With the development of digital image processing technology, material segmentation technology is also constantly improving. However, in actual operation, the low-contrast material segmentation process often faces the problem of whether to segment and how to segment finely. This is manifested in the problem of whether the "adhesive" stones with low imaging contrast can be segmented, and whether the stones that can be segmented can be accurately segmented along the actual segmentation line. This low-contrast "adhesive" stone segmentation problem not only increases the difficulty of segmentation, but also seriously affects the accuracy and precision of segmentation. Summary of the invention

[0003] In order to overcome the problems existing in the related art, an exemplary embodiment of the present disclosure provides an image segmentation method, which is applied to material sorting equipment, and the method includes: acquiring an image to be processed; determining material contour information of material adhesion in the image to be processed and a local image corresponding to the material contour information; based on the material contour information, determining candidate segmentation points for segmenting the local image; based on multiple extreme points in the local image, determining candidate segmentation paths of the local image; based on the matching results between the candidate segmentation points and the candidate segmentation paths, determining a target segmentation strategy; and segmenting the local image according to the target segmentation strategy to obtain a target image.

[0004] In some embodiments, the material sorting equipment includes a radiation collection device to obtain an image to be processed, including: obtaining a polarization image of the material through a polarized annular light source provided by the material sorting equipment; obtaining a radiation image of the material through the radiation collection device; determining the gradient information of the polarization image based on the polarization image, the radiation image and a local area selection threshold; and obtaining the image to be processed based on the gradient information and the radiation image.

[0005] In some embodiments, the material contour information includes coordinate information of multiple contour pixel points, and based on the material contour information, candidate segmentation points for segmenting the local image are determined, including: constructing a contour topology chain corresponding to the material contour information according to the coordinate information of the multiple contour pixel points; counting the number of occurrences of each contour pixel point in the contour topology chain; and using contour pixel points whose number of occurrences is greater than or equal to a first quantity threshold as candidate segmentation points for segmenting the local image.

[0006] In some embodiments, based on multiple extreme points in the local image, a candidate segmentation path of the local image is determined, including: determining the short side length of the local image; screening multiple extreme points in the local image based on the short side length to obtain a valid extreme point set; based on the valid extreme point set, performing concave point path analysis to determine the candidate segmentation path of the local image.

[0007] In some embodiments, based on the matching results between the candidate segmentation points and the candidate segmentation paths, a target segmentation strategy is determined, including: spatially aligning the candidate segmentation points with the candidate segmentation paths to determine the area to be segmented in the local image, the area to be segmented including concave point pairs and / or candidate segmentation points corresponding to the candidate segmentation paths; based on the number of target segmentations in the area to be segmented, a target segmentation strategy for processing the image to be segmented is determined.

[0008] In some embodiments, based on the number of target segmentations in the area to be segmented, a target segmentation strategy for processing the image to be segmented is determined, including: if the number of target segmentations is greater than or equal to a second number threshold, then the target segmentation strategy for processing the image to be segmented is determined to be a first segmentation strategy, and the first segmentation strategy includes performing image segmentation processing on the area to be segmented based on the neighborhood connectivity state between each two different segmentation points; if the number of target segmentations is less than the second number threshold, then the target segmentation strategy for processing the image to be segmented is determined to be a second segmentation strategy, and the second segmentation strategy includes performing image segmentation processing along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points.

[0009] In some embodiments, if there are multiple areas to be segmented, the image to be processed is segmented based on a target segmentation strategy to obtain a target image, including: determining the segmentation priority of each area to be segmented based on the distribution of concave point pairs and candidate segmentation points in each area to be segmented; determining the segmentation order of each area to be segmented according to the segmentation priority of each area to be segmented; and segmenting the image to be processed according to the segmentation order based on the target segmentation strategy of each area to be segmented to obtain a target image.

[0010] In some embodiments, the method further includes: detecting the segmentation validity of the target image based on image areas of the target image and the local image; or detecting the segmentation validity of the target image based on contours of the target image and the local image.

[0011] In a second aspect, the present disclosure also provides an image segmentation device, which is applied to material sorting equipment, and the device includes: an acquisition module, which is used to acquire an image to be processed; a first determination module, which is used to determine material contour information of material adhesion in the image to be processed and a local image corresponding to the material contour information; a second determination module, which is used to determine candidate segmentation points for segmenting the local image based on the material contour information; a third determination module, which is used to determine candidate segmentation paths of the local image based on multiple extreme points in the local image; a fourth determination module, which is used to determine a target segmentation strategy based on the matching results between the candidate segmentation points and the candidate segmentation paths; and a first processing module, which is used to segment the local image according to the target segmentation strategy to obtain a target image.

[0012] In a third aspect, the present disclosure further provides a material sorting device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor performs the image segmentation method provided in any of the above aspects by executing the computer instructions.

[0013] In a fourth aspect, the present disclosure further provides a computer-readable storage medium, which stores the following program, and the program is used to perform the image segmentation method provided in any of the above aspects.

[0014] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0015] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: According to the image segmentation method provided by the present disclosure, for the material contour information with material adhesion, the candidate segmentation points and candidate segmentation paths for possible image segmentation are determined from different dimensions, and based on the matching results of the candidate segmentation points and the candidate segmentation paths, the target segmentation strategy for image segmentation is determined. This can improve the recognition accuracy of the adhesion position by coupling multi-dimensional features, and then segment the local image according to the target segmentation strategy. This can not only improve the segmentation efficiency, but also help to ensure the reliability, accuracy and robustness of the segmentation results, thereby helping to ensure the subsequent material sorting quality and efficiency, and is beneficial to improving the material sorting performance of the material sorting equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present disclosure may be better understood by describing exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, in which:

[0017] Figure 1 It is a schematic diagram of the structure of a sorting device according to an exemplary embodiment of the disclosure;

[0018] Figure 2 is a flowchart of an image segmentation method according to an exemplary embodiment of the disclosure;

[0019] Figure 3 is a flowchart of an image segmentation method according to another exemplary embodiment of the present disclosure;

[0020] Figure 4 is a schematic block diagram of a material sorting system according to an exemplary embodiment of the disclosure;

[0021] Figure 5 It is a schematic block diagram of a material sorting device according to an exemplary embodiment of the disclosure. DETAILED DESCRIPTION

[0022] The specific implementation methods of the present disclosure will be described below. It should be noted that in the specific description of these implementation methods, in order to provide a concise description, it is impossible for this specification to provide a detailed description of all the features of the actual implementation methods. It should be understood that in the actual implementation of any implementation method, just as in the process of any engineering project or design project, in order to achieve the specific goals of the developer and to meet system-related or business-related restrictions, various specific decisions are often made, and this will also change from one implementation method to another. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the content disclosed by the present disclosure, some changes in design, manufacturing or production based on the technical content disclosed in the present disclosure are just conventional technical means, and should not be understood as insufficient content of the present disclosure.

[0023] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the usual meanings understood by persons with ordinary skills in the technical field to which the present disclosure belongs. The words "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "one" or "one" and the like do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before "include" or "comprise" cover the elements or objects listed after "include" or "comprise" and their equivalents, and do not exclude other elements or objects. Words such as "connect" or "connected" and the like are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0024] In the related technologies, in order to solve the problem of segmenting low-contrast "adhesive" stones, the focus is mainly on optimizing image processing algorithms and improving segmentation accuracy. Although existing image processing technologies can identify and process low-contrast "adhesive" materials in images to a certain extent, there are still many problems in practical applications. For example, on the one hand, due to the physical properties of the materials themselves and the complex scene environment, low-contrast situations are diverse and difficult to be effectively processed with a single algorithm; on the other hand, the existing segmentation algorithms cannot confirm the actual segmentation path when processing precise segmentation, resulting in inaccurate segmentation results that cannot meet the needs of practical applications.

[0025] To solve the above problems, an exemplary embodiment of the present disclosure provides an image segmentation method applied to a material sorting device. The material sorting device 100 can be used to sort materials, such as ores, metals, plastics, etc. Figure 1 As shown, the material sorting equipment 100 may include a feeding mechanism 110, a transmission mechanism 120, a detection mechanism 130 and a sorting device 140. The feeding mechanism 110 is used to feed the material to be sorted into the transmission mechanism 120. The transmission mechanism 120 may be a structure such as a conveyor belt or a chute, which is used to transport the material to be sorted fed by the feeding mechanism 110. The detection mechanism 130 is used to detect the material transported on the transmission mechanism 120 to detect whether the material is a material to be rejected; the material to be rejected refers to the material to be separated by the sorting equipment. The material to be rejected can be the required material or the unrequired material, as long as the material can be sorted. The sorting device 140 is used to reject the material to be rejected. The material sorting equipment 100 can be used for tasks such as ore sorting, food sorting or waste sorting, depending on the actual application requirements.

[0026] like Figure 2 As shown, the image segmentation method may include:

[0027] Step S210, obtaining an image to be processed.

[0028] The image to be processed can be understood as an image that can determine the distribution of materials. The image to be processed can be a radiographic image collected in real time during the material transmission process, or a binary image obtained after binarization of the radiographic image. The specific image can be determined according to actual needs. By obtaining the image to be processed, the distribution of materials during the transmission process can be determined so that targeted sorting can be performed later.

[0029] Step S220, determining the material contour information of the material adhesion in the image to be processed and the local image corresponding to the material contour information.

[0030] In order to facilitate the identification of the distribution of each material so that targeted sorting can be carried out later, contour recognition processing is performed on the processed image to determine the contour information of each material. However, during the actual material transmission process, some materials may adhere to other materials due to various reasons (such as friction, humidity or viscosity, etc.), and then during the contour recognition process, the contours of multiple adhered materials may be mistakenly identified as one contour. Among them, material adhesion may include but is not limited to at least one contact point or contact surface between multiple materials.

[0031] Therefore, in order to improve the accuracy of material sorting, each contour information is analyzed in a targeted manner according to the contour recognition processing result, and then the contour information of the material with material adhesion in the image to be processed is determined. In some examples, the targeted analysis of the contour information may include but is not limited to the analysis of any one or a combination of the following features: contour shape, size (for example, the area, perimeter, aspect ratio and other dimensional parameters of the contour), position, texture features, etc. The contour corresponding to the selected material contour information is more complex in shape and larger in area than the contour corresponding to the contour information of the normal material.

[0032] When the material contour information is determined, a local image corresponding to the material contour information is extracted from the image to be processed so that targeted segmentation processing can be performed later.

[0033] Step S230: determining candidate segmentation points for segmenting the local image based on the material contour information.

[0034] The candidate segmentation point can be understood as a potential segmentation point for segmenting the contour corresponding to the material contour information. The candidate segmentation point can be any one or more of the following feature points of the contour corresponding to the material contour information: the endpoints at both ends of the contour, the contour turning point, or the contour pixel point with the most drastic gray value change on the contour.

[0035] According to the material contour information, the geometric shape of its corresponding contour can be determined, and then by performing feature point detection on the contour, the candidate segmentation points on the contour corresponding to the material contour information can be quickly determined for segmenting the local image, so that the segmentation efficiency can be improved during subsequent image segmentation.

[0036] In some examples, the candidate segmentation points may be determined based on any of the following methods: based on the local grayscale changes of the contour, determined by a pre-trained machine model, or determined by using prior knowledge or constraints. For example, determining the candidate segmentation points based on the local grayscale changes of the contour may be determined by analyzing the local grayscale changes at different positions on the contour. Determining the candidate segmentation points by a pre-trained machine model may be automatically determined by using a pre-trained deep learning model or other machine learning model that can identify contour features and turning points. Determining the candidate segmentation points by using prior knowledge or constraints may be determined by using domain knowledge or a priori understanding of material properties.

[0037] Step S240, determining a candidate segmentation path of the local image based on a plurality of extreme value points in the local image.

[0038] Since the local image contains multiple materials that are adhered to each other, in order to facilitate targeted segmentation, the local image is processed by Euclidean distance transformation to determine the shortest distance from each pixel in the local image to the nearest object edge or background, and then multiple extreme points can be determined from it. Extreme points can be understood as pixels with the largest or smallest distance values. These points usually correspond to the edges or important feature points of the material image, so the location of the extreme points can be used as a segmentation reference.

[0039] However, since each extreme point can be at any position in the local image, depending on the actual image acquisition results, directly using the extreme points for segmentation may lead to unreasonable segmentation results. Therefore, based on the distribution of each extreme point in the local image, the candidate segmentation path for segmenting the local image is determined, so that the rationality and reliability of image segmentation can be improved during subsequent segmentation.

[0040] Step S250: determining a target segmentation strategy based on the matching result between the candidate segmentation points and the candidate segmentation paths.

[0041] Since the candidate segmentation points and the candidate segmentation paths are determined from two different dimensional directions, in order to improve the accuracy of image segmentation, the candidate segmentation points are matched with the candidate segmentation paths to obtain matching results. According to the matching results, the corresponding relationship between each candidate segmentation point and the candidate segmentation path can be determined, which helps to quickly determine the image segmentation process, and then obtain a target segmentation strategy adapted to the corresponding relationship, so that when the image segmentation is performed subsequently, the image segmentation can be completed accurately and reliably in a short time, thereby improving the image segmentation efficiency. Among them, the target segmentation strategy may include but is not limited to determining the segmentation order, segmentation direction, etc.

[0042] In some examples, in the process of matching the candidate segmentation points with the candidate segmentation paths, the matching may be performed based on the association between the candidate segmentation points and the candidate segmentation paths. For example, the association between each candidate segmentation point and each candidate segmentation path is determined respectively, and then the candidate segmentation path on which each candidate segmentation point may be a valid segmentation point is analyzed, thereby obtaining a matching result. In other examples, the matching result between the candidate segmentation point and the candidate segmentation path may be established based on the nearest neighbor matching algorithm or the greedy matching algorithm, thereby obtaining a matching result.

[0043] Step S260, segmenting the local image according to the target segmentation strategy to obtain the target image.

[0044] Through the target segmentation strategy, it is possible to clearly know how to perform targeted segmentation on the image to be processed, and then segment the image to be processed according to the target segmentation strategy. The segmentation position can be quickly located for targeted segmentation to obtain the target image, thereby effectively improving the segmentation efficiency and robustness, ensuring the quality and efficiency of material sorting, and helping to improve the material sorting performance of material sorting equipment.

[0045] According to the image segmentation method provided by the present invention, for the material contour information with material adhesion, the candidate segmentation points and candidate segmentation paths for possible image segmentation are determined from different dimensions, and based on the matching results of the candidate segmentation points and the candidate segmentation paths, the target segmentation strategy for image segmentation is determined. This can improve the recognition accuracy of the adhesion position by means of multi-dimensional feature coupling, and then segment the local image according to the target segmentation strategy. This can not only improve the segmentation efficiency, but also help to ensure the reliability, accuracy and robustness of the segmentation results, thereby helping to ensure the subsequent material sorting quality and efficiency, and is beneficial to improving the material sorting performance of the material sorting equipment.

[0046] In some embodiments, the material sorting equipment includes a radiation collection device, and the above step S210 may include the following steps:

[0047] Step a1, obtaining a polarization image of the material through a polarized annular light source provided by a material sorting device;

[0048] Step a2, obtaining a radiographic image of the material through a radiographic collection device;

[0049] Step a3, determining the gradient information of the polarization image based on the polarization image, the radiation image and the local area selection threshold;

[0050] Step a4, obtaining an image to be processed based on the gradient information and the ray image.

[0051] Since different types of materials may have similar appearance colors, such as coal and ore, quartz and mica, etc., during the image recognition process, misidentification may occur due to the low contrast between pixels.

[0052] In view of this, in order to improve the accuracy of material identification, the polarized annular light source provided by the material sorting equipment can be used to capture images of the material to eliminate or reduce the impact of specular reflection on low-contrast areas, thereby obtaining a polarized image that can enhance image quality and features. In some examples, the polarized annular light source includes an annular array light source and a polarizing filter. Since the annular array light source and the polarizing filter are both part of the material sorting equipment, in the process of image acquisition, the annular array light source and the polarizing filter in the material sorting equipment are used to form a polarized annular light source for image acquisition, which can not only effectively improve the utilization rate of the component structure, but also meet the demand for improving image accuracy without additional cost.

[0053] For material sorting equipment, the images used to identify materials and perform image segmentation are mainly radiographic images obtained by collecting images of materials through a ray collection device. The ray collection device may include but is not limited to an X-ray fluorescence spectrometer (XRF), a gamma-ray fluorescence spectrometer, or an X-ray computed tomography (X-ray CT).

[0054] Through the polarization image, the texture, reflection characteristics, color and other characteristics of the corresponding identified material surface can be determined. Through the ray image, the elemental composition and density of the corresponding identified material can be determined. In order to improve the accuracy of image segmentation, the ray image is analyzed to determine the connected body path, direction or other important information contained therein to obtain the analysis result. According to the analysis result, the local area to be analyzed in the polarization image can be determined, and then the threshold is selected according to the predetermined local area, and the brightness, contrast or other characteristics in the local area are processed in a targeted manner to improve the image quality and the detail clarity in the local area, so that the gradient information of the polarization image can be determined according to the specified gradient algorithm. Among them, the gradient information may include but is not limited to the size (amplitude) and direction of the gradient. Determining the gradient information in this way can better reflect the local features of the image and enhance the feature significance. Moreover, the local area selection threshold is analyzed, so there is no need to perform detailed gradient analysis on the entire image, which can reduce unnecessary calculation burden and improve processing speed.

[0055] After determining the gradient information of the polarization image, the gradient information is mapped onto the radiographic image to combine the polarization image with the radiographic image. This allows the fused image to simultaneously reflect the characteristic information that both images can provide, and further allows determining which local areas in the radiographic image are valid areas related to the material, thereby obtaining an image to be processed that can be used for image segmentation.

[0056] In some examples, in the process of determining the image to be segmented, image fusion can be performed based on the weight between the gradient information and the ray image, and then the fused image is binarized, and in the process of processing, the fused image is locally binarized in combination with the first weight of the gradient information and the second weight of the ray image, which can effectively reduce the occurrence of misidentification, so that when the contour recognition processing is performed on the obtained image to be processed later, the material contour can be better distinguished. That is, when the fused image is binarized, not only global binarization processing is performed, but also local binarization processing is performed, so that the obtained image to be processed can provide richer details and accurate contours as much as possible, and ensure the accuracy and reliability of subsequent material screening and image segmentation. Among them, the first weight of the gradient information and the second weight of the ray image can be determined according to demand. Since the gradient information is relatively accurate and reliable, the first weight can be greater than or equal to the second weight. For example, it can be determined that the first weight of the gradient information is 0.6 and the second weight of the ray image is 0.4, and then when the local binarization processing is performed later, the gradient information can be fully utilized to highlight the detailed features of the object image (for example, texture and surface structure), reduce noise interference, and thus help improve the accuracy of determining the image to be processed.

[0057] In other examples, the algorithm used for binarization of the fused image may be an Otsu algorithm that introduces a local contrast weight factor, so that in the process of global binarization, local binarization can also be performed. For example, when the fused image is binarized by the improved Otsu algorithm, the grayscale value corresponding to the pixel point with a pixel value less than 20 can be set to 0, the grayscale value corresponding to the pixel point with a pixel value greater than 180 can be set to 1, and the pixel point with a pixel value between 20-180 is selected by the first weight of the gradient information and the second weight of the ray image to determine the corresponding grayscale value, thereby obtaining the processed binary image. Wherein, if the grayscale value is 0, it indicates that the pixel point belongs to the background pixel, and if the grayscale value is 1, it indicates that the pixel point belongs to the material pixel. Alternatively, if the grayscale value is 1, it indicates that the pixel point belongs to the background pixel, and if the grayscale value is 0, it indicates that the pixel point belongs to the material pixel. The area corresponding to the pixel points with grayscale values ​​of 0 and 1 can be determined according to the needs, but the corresponding areas of the two are different. By performing image segmentation with the improved Otsu algorithm, we can fully consider the contrast of local areas, improve the accuracy of target recognition, and reduce the generation of artifacts. When processing edges and areas with rich textures, we can combine the local information around the pixels for comprehensive analysis to reduce the impact of noise on these local areas, thereby better retaining these details, which helps to improve the accuracy and reliability of distinguishing between materials and backgrounds.

[0058] In some application scenarios, it is predetermined that the grayscale value is 0, which indicates that the pixel belongs to the background pixel, and the grayscale value is 1, which indicates that the pixel belongs to the material pixel. Then, when the fused image is binarized, the grayscale value corresponding to the pixel with a pixel value less than 20 can be set to 0, and the grayscale value corresponding to the pixel with a pixel value greater than 180 can be set to 1. For the pixel with a pixel value between 20-180, if the calculated pixel value corresponding to the pixel with a pixel value between 20-180 is greater than 180 by combining the first weight of the gradient information and the second weight of the ray image, it is determined that the pixel is a pixel corresponding to the material, and the grayscale value corresponding to the pixel can be set to 1. If the calculated pixel value corresponding to the pixel with a pixel value between 20-180 is less than 20 by combining the first weight of the gradient information and the second weight of the ray image, it is determined that the pixel is a pixel corresponding to the background, and the grayscale value corresponding to the pixel can be set to 0.

[0059] In some embodiments, the material contour information includes coordinate information of a plurality of contour pixel points, and the above step S230 may include the following steps:

[0060] Step b1, constructing a contour topology chain corresponding to the material contour information according to the coordinate information of multiple contour pixel points;

[0061] Step b2, counting the number of occurrences of each contour pixel in the contour topology chain;

[0062] Step b3: taking contour pixel points whose occurrence times are greater than or equal to a first quantity threshold as candidate segmentation points for segmenting the local image.

[0063] Specifically, according to the coordinate information of each contour pixel point, the contour shape corresponding to the material contour information can be determined, and then the contour topology chain corresponding to the material contour information can be constructed, and the relative position relationship between each contour pixel point can be determined, which helps to determine the position relationship between multiple adhesion materials.

[0064] In some examples, in order to facilitate the determination of the positional relationship between each contour pixel point and avoid missing determination, each contour pixel point is stored in a specified order, and a contour topology chain corresponding to the material contour information is constructed to ensure the integrity of the contour. The specified order can be counterclockwise or clockwise, depending on the actual setting.

[0065] For the contour of a single material, in the corresponding contour topology chain, each contour pixel point only appears once. For the contour containing multiple materials, in the corresponding contour topology chain, the contour pixel point corresponding to the position where multiple materials intersect may appear multiple times, each time corresponding to a different material. Therefore, the minimum number of occurrences of contour pixels corresponding to the position where multiple materials intersect is predetermined, that is, the first quantity threshold. The number of occurrences of each contour pixel point in the contour topology chain is counted separately. If the number of occurrences of the contour pixel point is greater than or equal to the first quantity threshold, it can be determined that the contour pixel point corresponds to the position where multiple materials intersect. Therefore, in order to reduce the occurrence of missed recognition, the contour pixel points whose number of occurrences is greater than or equal to the first quantity threshold are used as candidate segmentation points for segmenting the local image to ensure the accuracy and robustness of image segmentation. In some examples, the first quantity threshold can be 2, which helps to ensure the completeness of the determination of the candidate segmentation points.

[0066] In some embodiments, the above step S240 may include the following steps:

[0067] Step c1, determining the length of the short side of the local image;

[0068] Step c2, screening multiple extreme value points in the local image based on the short side length to obtain a valid extreme value point set;

[0069] Step c3, based on the effective extreme point set, perform concave point path analysis to determine the candidate segmentation path of the local image.

[0070] Specifically, in a local image, an extreme point may be a point whose brightness or grayscale value is significantly higher or lower than that of the surrounding pixels, and may be a material edge, corner, or specific feature point. If the pixels between the mutually adhered materials are close, there may be a pseudo extreme point among the multiple extreme points. Since extreme points usually correspond to edges, corners, or other significant features in the image, in order to ensure the reliability of the determination of extreme points, extreme points are screened based on the short side length of the local image, thereby simplifying the screening difficulty and improving the screening efficiency, thereby quickly obtaining a valid extreme point set. In some examples, in image processing, maintaining certain proportional relationships is important for subsequent analysis. Short side screening can help maintain certain geometric features of the image, such as aspect ratio, which is beneficial for subsequent image registration or feature extraction. In other examples, in order to determine the validity of each extreme point, the minimum radius critical value of the extreme point is determined according to the short side length of the local image. For example, the minimum radius critical value is 1 / 3 of the short side length. If the radius of the extreme point is greater than the minimum radius critical value, it can be considered that the extreme point is more representative and belongs to a valid extreme point. If the radius of the extreme point is less than or equal to the minimum radius critical value, it can be considered that the extreme point is relatively normal, is misidentified, and is an invalid extreme point.

[0071] All extreme points in the effective extreme point set are effective extreme points. Therefore, according to the distribution of each extreme point, multiple extreme point paths can be obtained, and the shortest path can be used as the optimal path. Concave point pairs are detected along both sides of the optimal path. If a concave point pair is detected, the direction of the straight line connecting the concave point pair can be used as a candidate segmentation direction, and the path connecting the two concave points in the concave point pair can be used as a candidate segmentation path. Among them, the concave point is the contour pixel point where the gradient direction in the contour corresponding to the material contour information changes suddenly.

[0072] Screening extreme points by the short edge of the image can effectively reduce the computational burden and improve the processing speed. Then, the candidate segmentation path is determined based on the valid extreme point set, which can ensure the accuracy and reliability of the candidate segmentation path.

[0073] In some embodiments, the above step S250 may include the following steps:

[0074] Step d1, spatially aligning the candidate segmentation points with the candidate segmentation paths to determine the area to be segmented in the local image.

[0075] Specifically, since the candidate segmentation points and the candidate segmentation paths are determined by different processing methods, in order to ensure the reliability and accuracy of image segmentation, the candidate segmentation points and the candidate segmentation paths are spatially registered to merge the two, so as to clarify the candidate segmentation paths corresponding to each candidate segmentation point, thereby obtaining a reliable and accurate area to be segmented. The area to be segmented includes concave point pairs and / or candidate segmentation points corresponding to the candidate segmentation paths. That is, for the same area to be segmented, it may include concave point pairs and corresponding candidate segmentation points, or it may only include candidate segmentation points or concave point pairs.

[0076] Step d2, based on the number of target segmentations in the area to be segmented, determine the target segmentation strategy for processing the image to be segmented.

[0077] Specifically, according to the number of target segments in the area to be segmented, it can be determined that the area to be segmented needs to be divided into multiple local areas. If the number of target segments is small, the segmentation process is relatively simple, and only a simple segmentation operation may be required. If the number of target segments is large, the segmentation process is relatively complex, and multi-level segmentation may be required. Therefore, in order to improve the reliability and accuracy of image segmentation, the segmentation strategy corresponding to the number of target segments is used as the target segmentation strategy, so that in the segmentation process, the corresponding segmentation requirements can be met to ensure the flexibility and adaptability of image segmentation.

[0078] In some examples, if the number of target segmentations is greater than or equal to the second number threshold, the target segmentation strategy for processing the image to be segmented is determined to be the first segmentation strategy. The first segmentation strategy includes performing image segmentation processing on the area to be segmented based on the neighborhood connectivity state between each two different segmentation points. If the number of target segmentations is greater than or equal to the second number threshold, it indicates that the segmentation process is relatively complex. Therefore, in order to make the segmentation result more in line with the actual adhesion of the material, the first segmentation strategy is used as the target segmentation strategy, so that when the image is segmented subsequently, it can be segmented based on the neighborhood connectivity state between each two different segmentation points, so that the final segmentation result obtained can be accurate and reliable.

[0079] In other examples, if the number of target segmentations is less than the second number threshold, the target segmentation strategy for processing the image to be segmented is determined to be the second segmentation strategy. The second segmentation strategy includes performing image segmentation processing along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points. If the number of target segmentations is greater than the second number threshold, the segmentation process is relatively simple. Therefore, in order to make the segmentation result more consistent with the actual adhesion of the material, the second segmentation strategy is used as the target segmentation strategy, so that when the image segmentation is performed subsequently, the image segmentation processing can be performed along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points, so as to simplify the segmentation difficulty and improve the segmentation efficiency.

[0080] In some other embodiments, if there are multiple regions to be segmented, the above step S260 may include the following steps:

[0081] Step e1, determining the segmentation priority of each area to be segmented based on the distribution of concave point pairs and candidate segmentation points in each area to be segmented;

[0082] Step e2, determining the segmentation order of each area to be segmented according to the segmentation priority of each area to be segmented;

[0083] Step e3, based on the target segmentation strategy of each area to be segmented, the image to be processed is segmented in a segmentation order to obtain a target image.

[0084] Specifically, in order to improve the accuracy of image segmentation, the segmentation priority of each area to be segmented is determined according to the distribution of concave point pairs and candidate segmentation points in each area to be segmented. If the same area to be segmented includes both concave point pairs and candidate segmentation points, it means that no matter which method is used for image segmentation detection, the area to be segmented is an area that needs to be segmented, and the degree of segmentation is relatively complex. Therefore, the segmentation priority of the segmented area is the highest. If the same area to be segmented includes multiple concave point pairs or candidate segmentation points, it means that the area to be segmented needs to be segmented, but the degree of segmentation is somewhat complex. Therefore, the segmentation priority of the segmented area is relatively high. If the same area to be segmented includes only one concave point pair or candidate segmentation point, it means that the area to be segmented needs to be segmented, but the degree of segmentation is relatively simple. Therefore, the segmentation priority of the segmented area is the lowest.

[0085] According to the segmentation priority of each area to be segmented, the segmentation order of each area to be segmented is determined respectively, so as to ensure that the areas to be segmented that are difficult to segment are given priority in image segmentation processing, so as to reduce the influence of these areas to be segmented on subsequent segmentation, which is helpful to improve the overall segmentation quality, simplify the difficulty of subsequent image segmentation, and facilitate better management of segmentation resources.

[0086] In the process of image segmentation, each area to be segmented is segmented in turn according to the segmentation order using the corresponding target segmentation strategy. This can ensure that each area to be segmented can be subjected to targeted image segmentation processing, ensuring that the image segmentation process is both efficient and accurate while meeting the needs and characteristics of each area to be segmented, providing a reliable data basis for subsequent material identification and sorting, which is beneficial to improving the sorting performance of material sorting equipment.

[0087] In some optional implementation scenarios, the second quantity threshold can be 2. If the number of target segmentations is greater than or equal to 2, it indicates that the segmentation process is relatively complex. Therefore, when the first segmentation strategy is used to segment the area to be segmented, the following process can be used for processing: according to the multiple segmentation points included in the area to be segmented, two different segmentation points are selected at random, and the neighborhood connectivity state between the two segmentation points is determined. Among them, the segmentation point can be one of the candidate segmentation points or the concave point pair. If the neighborhood connectivity state is connected, it indicates that the contour where the two segmentation points are located is double-target adhesion, and then bidirectional cutting is performed. If the neighborhood connectivity state is not connected, it indicates that the contour where the two segmentation points are located is multi-target cross-adhesion, and then extreme point path segmentation is performed recursively to gradually narrow the segmentation from a large segmentation range, thereby obtaining the segmentation result of the area to be sorted.

[0088] If the target segmentation number is less than 2, it means that the segmentation process is relatively simple. Therefore, when the second segmentation strategy is used to segment the area to be segmented, the following process can be used: directly cut along the concave point along the gradient direction or the candidate segmentation point, and the attribution rule adopts the contour area weighted method to obtain the segmentation result of the area to be sorted.

[0089] In some embodiments, the above-mentioned image segmentation method may further include: based on the image areas of the target image and the local image, detecting the segmentation validity of the target image. In the actual contour detection process, impurities or the quality of the algorithm will affect the accuracy of the material contour information. Therefore, in order to determine whether the target image is valid, it is determined whether the geometric constraint index of the target image meets the requirements based on the image area of ​​the local image. According to the image area of ​​the local image, the minimum effective area critical value can be determined. For example, the minimum effective area critical value = the area of ​​the circumscribed rectangle * 5%. If the area difference between the target image and the local image is less than the minimum effective area critical value, it indicates that the image segmented out may be noise, and the segmentation belongs to invalid segmentation. If the area difference between the target image and the local image is greater than the minimum effective area critical value, it indicates that the image segmented out is a material image, and the segmentation belongs to effective segmentation.

[0090] In some other embodiments, the above-mentioned image segmentation method may further include: based on the contours of the target image and the local image, detecting the segmentation validity of the target image. That is, determining the Hausdorff distance between the contour of the target image and the contour of the local image. If the Hausdorff distance is less than or equal to the specified pixel difference distance, and the area difference between the target image and the local image is greater than the minimum effective area threshold, then the image segmented out is characterized as a material image, and the segmentation is a valid segmentation. If the Hausdorff distance is greater than or equal to the specified pixel difference distance, the segmentation is an invalid segmentation.

[0091] In some other embodiments, in order to make the contour of the target image clearer and the pixels between adjacent images smoother, a closing operation (eg, a 3×3 circular kernel) is performed on the target image, edge pixels are repaired, and the contour is fitted using a Bezier curve to improve smoothness.

[0092] In some optional application scenarios, the process of image segmentation performed by the material sorting device using the image segmentation method provided by the present disclosure can be as follows: Figure 3 As shown, the following steps are included:

[0093] The polarized image of the material is obtained by using the polarized annular light source provided by the material sorting equipment; and the radiographic image of the material is obtained by using the ray collection device.

[0094] The polarization image is fused with the radiation image, and the fusion result is globally and locally binarized to obtain the image to be processed. That is, based on the polarization image, the radiation image and the local area selection threshold, the gradient information of the polarization image is determined, and then the image is fused according to the gradient information, the radiation image, the first weight of the gradient information and the second weight of the radiation image, and the fused image is globally and locally binarized to obtain the image to be processed.

[0095] The material contour information of the material adhesion in the image to be processed is determined, and the contour topology chain corresponding to the material contour information is constructed according to the coordinate information of multiple contour pixels in the material contour information.

[0096] Determine the local image corresponding to the material contour information, perform extreme point detection, and obtain candidate segmentation paths.

[0097] Determine whether there are concave point pairs on both sides of the candidate segmentation path.

[0098] If there is a concave point pair, the candidate segmentation path is determined to be valid. If there is no concave point pair, the number of occurrences of each contour pixel point in the contour topology chain is counted to determine the candidate segmentation point.

[0099] Based on the matching results between the candidate segmentation points and the candidate segmentation paths, the area to be segmented and the corresponding priority are determined.

[0100] Determine the target number of segments for the area to be segmented.

[0101] If the number of target segmentations is less than the second number threshold, single target cutting is performed along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points.

[0102] If the target segmentation number is greater than or equal to the second number threshold, the neighborhood connectivity state between any two different segmentation points in the to-be-segmented area is determined. If the neighborhood connectivity state is connected, bidirectional cutting is performed. If the neighborhood connectivity state is not connected, extreme point path segmentation is performed recursively.

[0103] Determine whether the segmented contour is independent. If it is an independent contour, perform contour repair to obtain the target image.

[0104] Check the segmentation validity of the target image. If the segmentation of the target image is valid, then end.

[0105] If it is not an independent contour, the matching result between the candidate segmentation points and the candidate segmentation paths is re-executed to determine the area to be segmented and the corresponding priority.

[0106] According to the image segmentation method provided by the present disclosure, the efficiency and accuracy of data processing can be effectively improved. This optimization not only enables the system to maintain a stable and efficient operating state when processing large amounts of data, but also greatly improves the accuracy of data analysis and provides more reliable data support for decision-making.

[0107] In practical applications, by applying the image segmentation method provided by the present disclosure, users can obtain required information more quickly and improve work efficiency. At the same time, the present disclosure also reduces the error rate of data processing and reduces the decision-making risks caused by inaccurate data. In addition, the present disclosure also has good scalability and adaptability, and can be customized and optimized according to the needs of different users to meet the data processing needs in different fields and scenarios.

[0108] In summary, the image segmentation method provided by the present disclosure can bring significant technical effects and practical application value to users through its unique technical principles and innovative design. It not only improves data processing efficiency and accuracy, but also reduces decision-making risks, providing users with a more convenient and efficient data processing solution.

[0109] Based on the same inventive concept, the present disclosure also provides an image segmentation device. Figure 4 As shown, the image segmentation device 300 includes:

[0110] An acquisition module 310 is used to acquire an image to be processed;

[0111] A first determination module 320 is used to determine the material contour information of the material adhesion in the image to be processed and the local image corresponding to the material contour information;

[0112] A second determination module 330 is used to determine candidate segmentation points for segmenting the local image based on the material contour information;

[0113] A third determination module 340 is used to determine a candidate segmentation path of the local image based on a plurality of extreme value points in the local image;

[0114] A fourth determination module 350, configured to determine a target segmentation strategy based on a matching result between the candidate segmentation points and the candidate segmentation paths;

[0115] The first processing module 360 ​​is used to segment the local image according to the target segmentation strategy to obtain the target image.

[0116] In some embodiments, the material sorting equipment includes a radiation collection device, and the acquisition module 310 includes: a first acquisition unit, used to acquire a polarization image of the material through a polarized annular light source provided by the material sorting equipment; a second acquisition unit, used to acquire a radiation image of the material through the radiation collection device; a first processing unit, used to determine the gradient information of the polarization image based on the polarization image, the radiation image and the local area selection threshold; a second processing unit, used to obtain the image to be processed based on the gradient information and the radiation image.

[0117] In some embodiments, the material contour information includes coordinate information of multiple contour pixel points, and the second determination module 330 includes: a third processing unit, used to construct a contour topology chain corresponding to the material contour information based on the coordinate information of the multiple contour pixel points; a statistical unit, used to count the number of occurrences of each contour pixel point in the contour topology chain; a first screening unit, used to use contour pixel points whose number of occurrences is greater than or equal to a first quantity threshold as candidate segmentation points for segmenting local images.

[0118] In some embodiments, the third determination module 340 includes: a first determination unit, used to determine the short side length of the local image; a second screening unit, used to screen multiple extreme points in the local image based on the short side length to obtain a valid extreme point set; a fourth processing unit, used to perform concave point path analysis based on the valid extreme point set to determine the candidate segmentation path of the local image.

[0119] In some embodiments, the fourth determination module 350 includes: a second determination unit, used to spatially align the candidate segmentation points with the candidate segmentation paths, and determine the area to be segmented in the local image, wherein the area to be segmented includes concave point pairs and / or candidate segmentation points corresponding to the candidate segmentation paths; and a third determination unit, used to determine the target segmentation strategy for processing the image to be segmented based on the number of target segmentations in the area to be segmented.

[0120] In some embodiments, the third determination unit includes: a first performing unit, which is used to determine that the target segmentation strategy for processing the image to be segmented is a first segmentation strategy if the number of target segmentations is greater than or equal to a second number threshold, and the first segmentation strategy includes performing image segmentation processing on the area to be segmented based on the neighborhood connectivity state between each two different segmentation points; a second performing unit, which is used to determine that the target segmentation strategy for processing the image to be segmented is a second segmentation strategy if the number of target segmentations is less than the second number threshold, and the second segmentation strategy includes performing image segmentation processing along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points.

[0121] In some embodiments, if there are multiple areas to be segmented, the first processing module 360 ​​includes: a fifth processing unit, used to determine the segmentation priority of each area to be segmented based on the distribution of concave point pairs and candidate segmentation points in each area to be segmented; a sixth processing unit, used to determine the segmentation order of each area to be segmented according to the segmentation priority of each area to be segmented; and a seventh processing unit, used to segment the image to be processed according to the segmentation order based on the target segmentation strategy of each area to be segmented to obtain a target image.

[0122] In some embodiments, the image segmentation device 300 also includes: a first detection module, used to detect the segmentation validity of the target image based on the image areas of the target image and the local image; or a second detection module, used to detect the segmentation validity of the target image based on the contours of the target image and the local image.

[0123] Regarding the image detection device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0124] Based on the same inventive concept, Figure 5 As shown, one embodiment of the present disclosure provides a material sorting device. The electronic device includes: one or more processors 410, a memory 420, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5A processor 410 is taken as an example.

[0125] The processor 410 may be a central processing unit, a network processor or a combination thereof. The processor 410 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.

[0126] The memory 420 stores instructions executable by at least one processor 410, so that the at least one processor 410 executes the image segmentation method shown in the above embodiment.

[0127] The memory 420 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 420 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0128] The memory 420 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 420 may also include a combination of the above types of memory.

[0129] The electronic device also includes an input device 430 and an output device 440. The processor 410, the memory 420, the input device 430 and the output device 440 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0130] The input device 430 can receive input digital or character information and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 440 may include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display, and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0131] Based on the same inventive concept, the present disclosure further provides a computer-readable storage medium, which stores the following program, and the program is used to execute the image segmentation method of any of the aforementioned embodiments.

[0132] The present disclosure uses specific words to describe the embodiments of the present disclosure. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present disclosure. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present disclosure may be appropriately combined.

[0133] In the context of the present disclosure, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0134] Similarly, it should be noted that in order to simplify the description of the disclosure and thus help understand one or more application embodiments, in the above description of the embodiments of the disclosure, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of the disclosure are more than the features required for protection. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

[0135] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is only an example and does not constitute a limitation of the present disclosure. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and corrections to the present disclosure. Such modifications, improvements and corrections are suggested in the present disclosure, so such modifications, improvements and corrections still belong to the spirit and scope of the embodiments of the present disclosure.

Claims

1. An image segmentation method, characterized in that: Applied to material sorting equipment, the method comprises: Get the image to be processed; Determine material contour information of material adhesion in the image to be processed and a local image corresponding to the material contour information; Based on the material contour information, determining candidate segmentation points for segmenting the partial image; Determining a candidate segmentation path of the local image based on a plurality of extreme points in the local image; Determining a target segmentation strategy based on a matching result between the candidate segmentation points and the candidate segmentation paths; The local image is segmented according to the target segmentation strategy to obtain a target image.

2. The image segmentation method according to claim 1, characterized in that: The material sorting equipment includes a ray collection device, and the step of acquiring the image to be processed includes: Acquiring a polarized image of the material through the polarized annular light source provided by the material sorting equipment; Acquiring a radiographic image of the material through the ray collection device; Determining gradient information of the polarization image based on the polarization image, the radiation image, and a local area selection threshold; The image to be processed is obtained based on the gradient information and the radiographic image.

3. The image segmentation method according to claim 1, characterized in that: The material contour information includes coordinate information of a plurality of contour pixel points, and determining candidate segmentation points for segmenting the partial image based on the material contour information includes: Constructing a contour topology chain corresponding to the material contour information according to the coordinate information of the plurality of contour pixel points; Counting the number of occurrences of each contour pixel point in the contour topology chain; Contour pixel points whose occurrence times are greater than or equal to a first quantity threshold are used as candidate segmentation points for segmenting the partial image.

4. The image segmentation method according to claim 1, characterized in that: The step of determining a candidate segmentation path of the local image based on a plurality of extreme points in the local image comprises: Determining the length of the short side of the partial image; Based on the short side length, a plurality of extreme value points in the local image are screened to obtain a valid extreme value point set; Based on the effective extreme point set, concave point path analysis is performed to determine candidate segmentation paths for the local image.

5. The image segmentation method according to claim 3 or 4, characterized in that: The determining of the target segmentation strategy based on the matching result between the candidate segmentation point and the candidate segmentation path includes: Performing spatial registration of the candidate segmentation points and the candidate segmentation paths to determine a region to be segmented in the local image, wherein the region to be segmented includes concave point pairs and / or candidate segmentation points corresponding to the candidate segmentation paths; Based on the number of target segmentations in the area to be segmented, a target segmentation strategy for processing the image to be segmented is determined.

6. The image segmentation method according to claim 5, characterized in that: The determining of the target segmentation strategy for processing the image to be segmented based on the number of target segmentations in the area to be segmented comprises: If the target segmentation number is greater than or equal to the second number threshold, determining that the target segmentation strategy for processing the image to be segmented is a first segmentation strategy, wherein the first segmentation strategy includes performing image segmentation processing on the area to be segmented based on the neighborhood connectivity state between every two different segmentation points; If the target segmentation quantity is less than the second quantity threshold, the target segmentation strategy for processing the image to be segmented is determined to be the second segmentation strategy, and the second segmentation strategy includes performing image segmentation processing along the gradient direction of the concave point pairs in the area to be segmented or the candidate segmentation points.

7. The image segmentation method according to claim 6, characterized in that: If the number of the to-be-segmented regions is multiple, segmenting the to-be-processed image based on the target segmentation strategy to obtain a target image includes: Determine the segmentation priority of each of the regions to be segmented based on the distribution of the concave point pairs and the candidate segmentation points in each of the regions to be segmented; Determining the segmentation order of each of the regions to be segmented according to the segmentation priority of each of the regions to be segmented; Based on the target segmentation strategy of each of the to-be-segmented regions, the to-be-processed image is segmented in accordance with the segmentation order to obtain a target image.

8. The image segmentation method according to claim 1, characterized in that: The method further comprises: Detecting segmentation validity of the target image based on image areas of the target image and the partial image; or Based on the contours of the target image and the local image, the segmentation validity of the target image is detected.

9. An image segmentation device, characterized in that: Applied to material sorting equipment, the device comprises: An acquisition module, used for acquiring an image to be processed; A first determination module is used to determine the material contour information of the material adhesion in the image to be processed and the local image corresponding to the material contour information; A second determination module, used to determine candidate segmentation points for segmenting the partial image based on the material contour information; A third determination module, configured to determine a candidate segmentation path of the local image based on a plurality of extreme value points in the local image; A fourth determination module, configured to determine a target segmentation strategy based on a matching result between the candidate segmentation points and the candidate segmentation paths; The first processing module is used to segment the local image according to the target segmentation strategy to obtain a target image.

10. A material sorting device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor performs the image segmentation method according to any one of claims 1 to 8 by executing the computer instructions.

11. A computer-readable storage medium storing the following program, wherein the program is used to perform the image segmentation method according to any one of claims 1 to 8.

Images