Tab folding detection method and device, electronic equipment and storage medium

Abstract

The invention provides a tab folding detection method and device, electronic equipment and a storage medium. The method comprises the following steps: performing skeleton extraction processing on a cross-section image of a multi-layer tab to obtain a skeleton image of the multi-layer tab; the fractured connected domains in the skeleton image are merged to obtain merged connected domains, and the fractured connected domains are fractured connected domains in the same tab cross section; counting the target number of the multiple layers of tabs according to the combined connected domains and the unbroken connected domains; and according to the target number and the preset number, detecting whether there are tabs in the multiple layers of tabs in a folded state or not. Performing merging processing on the fractured connected domain to obtain a merged connected domain; according to the combined connected domains and the unbroken connected domains, the counted target number of the multiple layers of tabs is more accurate, and then the turnover detection of the tabs is more accurate.

Description

Tab fold detection method, device, electronic device and storage medium Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a tab fold detection method, device, electronic device, and storage medium. Background Art

[0002] With the rapid development of new energy vehicles, power batteries have also gained widespread application. The manufacturing method for bare power battery cells can be winding. During winding, only the portion of the cell electrode sheet that needs to pass current is retained. This portion of the metal foil is the tab. Due to the extremely thin thickness of the metal foil, the tab is prone to folding during the winding process. Therefore, detecting tab folding has become a hot topic of research.

[0003] In related technologies, when performing folding detection on the tabs, a line graph corresponding to the tab area is obtained, the number of lines on the vertical cross section of the image corresponding to each sampling point is counted, and the maximum line value is taken as the actual number of tabs.

[0004] However, in the related art, the problem of inaccurate tab count may occur, which may lead to inaccurate tab folding detection.

[0005] Summary of the Invention

[0006] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, one purpose of the present application is to provide a tab fold detection method, device, electronic device and storage medium to solve the problem of inaccurate tab fold detection.

[0007] An embodiment of the first aspect of the present application provides a tab fold detection method, comprising:

[0008] A skeleton extraction process is performed on a cross-sectional image of a multi-layer tab to obtain a skeleton image of the multi-layer tab. The broken connected domains in the skeleton image are merged to obtain a merged connected domain, where a broken connected domain is a connected domain that is broken within the same tab cross-section. The target number of multi-layer tabs is counted based on the merged connected domains and the unbroken connected domains. Based on the target number and a preset number, whether any tabs in the multi-layer tab are in a folded state is detected. The count of the target number of multi-layer tabs based on the merged connected domains and the unbroken connected domains is more accurate, thereby making tab fold detection more accurate.

[0009] In some embodiments, merging broken connected domains in a skeleton image to obtain a processed connected domain further includes: if an endpoint of the connected domain is within a preset region of the skeleton image, determining a first foreground point and a second foreground point adjacent to the endpoint based on the endpoint, wherein the endpoint, the first foreground point, and the second foreground point are located on different connected domains; and merging the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain the processed connected domain. If the endpoint of the connected domain is within the preset region of the skeleton image, merging is performed based on the endpoint and the first foreground point and the second foreground point adjacent to the endpoint, thereby making the merging result more reasonable and accurate.

[0010] In some embodiments, merging the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain a processed connected domain includes: determining a first distance between the endpoint and the first foreground point, and a second distance between the endpoint and the second foreground point; if the first distance is less than the second distance, merging the first connected domain where the first foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain; if the second distance is less than the first distance, merging the second connected domain where the second foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain. This allows accurate determination of the first connected domain and the second connected domain to be merged with the connected domain where the endpoint is located, thereby enabling accurate merging of connected domains.

[0011] In some embodiments, counting a target number of multi-layer tabs based on the merged connected domain and the unbroken connected domain includes: traversing each third connected domain in the merged connected domain and the unbroken connected domain, counting the number of tabs in each third connected domain; summing the number of tabs in each third connected domain to obtain a first target number; and determining the target number of multi-layer tabs based on the first target number and the number of endpoints in the preset region in the merged connected domain and the unbroken connected domain. The target number is determined based on the first target number and further combined with the number of endpoints in the preset region in the merged connected domain and the unbroken connected domain, thereby making the determined target number more accurate.

[0012] In some embodiments, determining a target number of multi-layer tabs based on a first target number, a number of endpoints in a preset region of a merged connected domain, and an unbroken connected domain includes: if the number of endpoints in the preset region is the same as the preset number, using the number of endpoints in the preset region as the target number; if the number of endpoints in the preset region is different from the preset number, determining a maximum between the number of endpoints in the preset region and the first target number; and determining the target number based on the maximum value and the preset number. Determining the target number based on the maximum value between the number of endpoints in the preset region and the first target number, together with the preset number, provides a more accurate determination of the target number, thereby further improving the detection of tab folding.

[0013] In some embodiments, determining a target quantity based on a maximum value and a preset quantity includes: if the maximum value is less than or equal to the preset quantity, using the maximum value as the target quantity; if the maximum value is greater than the preset quantity, traversing the broken connected domain and each fourth connected domain in the unbroken connected domain, counting the number of tabs in each fourth connected domain; adding the number of tabs in each fourth connected domain to obtain a second target quantity; and using the second target quantity as the target quantity. Using the maximum value as the target quantity, or using the second target quantity obtained based on the fourth connected domain as the target quantity, makes determining the target quantity more reasonable and accurate.

[0014] In some embodiments, counting the number of tabs in each third connected domain includes: determining sampling points in each third connected domain; sorting the sampling points in each third connected domain in a preset horizontal direction according to the position of each third connected domain to obtain a sorting result; and determining the number of tabs in each third connected domain based on the sorting result and a preset threshold. Determining the number of tabs in each third connected domain based on the sorting result and the preset threshold makes the determination of the number of tabs in each third connected domain more accurate.

[0015] In some embodiments, determining the number of tabs in each third connected domain based on the sorting results and a preset threshold includes: determining whether the distance between two adjacent sampling points is greater than the preset threshold based on the sorting results; if so, determining the number of tabs on a vertical cross-section between the two adjacent sampling points; and determining the number of tabs in each third connected domain based on the number of tabs on the vertical cross-section between the two adjacent sampling points. Fully considering the distance between the sampling points makes determining the number of tabs in the third connected domain more reasonable.

[0016] In some embodiments, determining sampling points for each third connected domain includes: determining intersections, first-class endpoints, and second-class endpoints in each third connected domain; removing burrs from the first-class endpoints and the second-class endpoints to obtain processed endpoints; and using the processed endpoints and intersections as sampling points. Removing burrs from the first-class endpoints and the second-class endpoints can make the determined endpoints more accurate and avoid inaccurate tab counting caused by burrs.

[0017] An embodiment of a second aspect of the present application provides a tab fold detection device, comprising:

[0018] An extraction processing module is used to perform skeleton extraction processing on the cross-sectional image of the multi-layer tab to obtain a skeleton image of the multi-layer tab;

[0019] A merging processing module is used to merge the broken connected domains in the skeleton image to obtain a merged connected domain, where the broken connected domains are multiple connected domains belonging to the same tab cross section;

[0020] A statistics module is used to count the target number of multi-layer tabs based on the merged connected domains and the unbroken connected domains;

[0021] The detection module is used to detect whether there are any tabs in the multi-layer tabs in a folded state according to the target number and the preset number.

[0022] In some embodiments, the merging processing module is specifically used to determine the first foreground point and the second foreground point adjacent to the endpoint based on the endpoint if the endpoint of the connected domain is within a preset area of ​​the skeleton image, and the endpoint, the first foreground point, and the second foreground point are on different connected domains; and perform merging processing based on the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain a processed connected domain.

[0023] In some embodiments, the merging processing module is specifically used to determine a first distance between the endpoint and the first foreground point, and a second distance between the endpoint and the second foreground point; if the first distance is less than the second distance, the first connected domain where the first foreground point is located and the connected domain where the endpoint is located are merged to obtain a merged connected domain; if the second distance is less than the first distance, the second connected domain where the second foreground point is located and the connected domain where the endpoint is located are merged to obtain a merged connected domain.

[0024] In some embodiments, the statistical module is specifically used to traverse the merged connected domain and each third connected domain in the unbroken connected domain, and count the number of tabs in each third connected domain; add the number of tabs in each third connected domain to obtain a first target number; and determine the target number of multi-layer tabs based on the first target number, the number of endpoints in the preset area in the merged connected domain and the unbroken connected domain.

[0025] In some embodiments, the statistical module is specifically used to, if the number of endpoints in the preset area is the same as the preset number, use the number of endpoints in the preset area as the target number; if the number of endpoints in the preset area is different from the preset number, determine the maximum value between the number of endpoints in the preset area and the first target number; and determine the target number based on the maximum value and the preset number.

[0026] In some embodiments, the statistical module is specifically used to use the maximum value as the target number if the maximum value is less than or equal to a preset number; if the maximum value is greater than the preset number, traverse the broken connected domain and each fourth connected domain in the unbroken connected domain, and count the number of tabs in each fourth connected domain; add the number of tabs in each fourth connected domain to obtain a second target number; and use the second target number as the target number.

[0027] In some embodiments, the statistical module is specifically used to determine the sampling points of each third connected domain; sort the sampling points of each third connected domain according to the position of each third connected domain in a preset horizontal direction to obtain a sorting result; and determine the number of tabs in each third connected domain based on the sorting result and a preset threshold.

[0028] In some embodiments, the statistical module is specifically used to determine whether the distance between two adjacent sampling points is greater than a preset threshold based on the sorting result; if so, determine the number of tabs on the vertical section between the two adjacent sampling points; and determine the number of tabs in each third connected domain based on the number of tabs on the vertical section between the two adjacent sampling points.

[0029] In some embodiments, the statistical module is specifically used to determine the intersection points, first-class endpoints, and second-class endpoints in each third connected domain; remove the burr points in the first-class endpoints and the second-class endpoints to obtain processed endpoints; and use the processed endpoints and intersection points as sampling points.

[0030] An embodiment of the third aspect of the present application provides an electronic device, which includes: a memory and a processor, the memory stores a computer program executable by the processor, and the processor implements any one of the methods of the first aspect when executing the computer program.

[0031] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, wherein a computer program is stored on the storage medium, and when the computer program is read and executed, any method of the above-mentioned first aspect is implemented.

[0032] An embodiment of the fifth aspect of the present application provides a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, it is used to implement any one of the methods in the first aspect.

[0033] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0035] FIG1 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0036] FIG2 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0037] FIG3 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0038] FIG4 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0039] FIG5 is a schematic diagram of a tab connection region rupture provided in an embodiment of the present application;

[0040] FIG6 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0041] FIG7 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0042] FIG8 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0043] FIG9 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0044] FIG10 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0045] FIG11 is a schematic flow chart of a tab fold detection method provided in an embodiment of the present application;

[0046] FIG12 is a schematic structural diagram of a tab folding detection device provided in an embodiment of the present application;

[0047] FIG13 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are for the purpose of describing specific embodiments only and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0050] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0051] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0053] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0054] In the description of the embodiments of the present application, the technical terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they should not be understood as limiting the embodiments of the present application.

[0055] In the description of the embodiments of the present application, unless otherwise expressly specified or limited, technical terms such as "installed," "connected," "connect," and "fixed" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; internal connections between two components or interactions between two components. Those skilled in the art can understand the specific meanings of the above terms in the embodiments of the present application based on specific circumstances.

[0056] With the rapid development of new energy vehicles, power batteries have also gained widespread application. Bare power battery cells can be manufactured using winding methods. Winding involves retaining only the portion of the cell's metal foil needed to carry the current. This portion of the metal foil is known as the tab. Due to the extremely thin thickness of the metal foil, the tab is prone to folding during the winding process. Therefore, detecting tab folding has become a hot topic of research.

[0057] In related technologies, when performing folding detection on the tabs, a line graph corresponding to the tab area is obtained, the number of lines on the vertical cross section of the image corresponding to each sampling point is counted, and the maximum line value is taken as the actual number of tabs.

[0058] However, in the related art, the number of lines on the vertical cross-section of the image corresponding to each sampling point is independently counted. The statistical process is relatively isolated, which easily leads to the problem of inaccurate number of tabs counted, thereby causing inaccurate detection of tab folding.

[0059] In order to solve at least one of the above problems, an embodiment of the present application provides a method for detecting the folding of the tab, which merges the broken connected domains to obtain a merged connected domain; based on the merged connected domains and the unbroken connected domains, the target number of multi-layer tabs is counted based on these connected domains, which can fully consider the correlation between the multi-layer tabs, so that the calculated target number is more accurate, and then the folding detection of the tab is more accurate.

[0060] The tab folding detection method disclosed in the embodiment of the present application can capture cross-sectional images of the sides of multiple tabs through an image acquisition device, and the image acquisition device can be set on the side of a multi-layer tab; the image acquisition device is communicatively connected to an electronic device, and the image acquisition device can send cross-sectional images of the multi-layer tabs to the electronic device, and the electronic device can receive the cross-sectional images of the multi-layer tabs and execute the tab folding detection method provided in the embodiment of the present application to determine whether there are any tabs in the multi-layer tabs that are in a folded state.

[0061] The communication connection mode may be a wired communication connection or a wireless communication connection.

[0062] It should be noted that the image acquisition device can be a camera, a still camera, or other devices with image acquisition functions, and the present application does not specifically limit this. The electronic device can be a terminal or a server, and the terminal can be any of the following: a desktop computer, a laptop computer, a tablet computer, a smartphone, etc.

[0063] According to some embodiments of the present application, FIG1 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG1 , the tab fold detection method may include:

[0064] S101 , performing skeleton extraction processing on a cross-sectional image of a multi-layer tab to obtain a skeleton image of the multi-layer tab.

[0065] S102 , merging the broken connected domains in the skeleton image to obtain merged connected domains, where the broken connected domains are connected domains that are broken in the same tab cross section.

[0066] S103 , counting the target number of multi-layer tabs based on the merged connected domains and the unbroken connected domains.

[0067] S104: Detect whether there is any tab in the multi-layer tab in a folded state according to the target number and the preset number.

[0068] The cross-sectional image of the multi-layer tab may be a segmented image of the cross-sectional area of ​​the multi-layer tab.

[0069] In some embodiments, the cross-sectional image of the multi-layer tab is preprocessed to obtain a preprocessed image, and skeleton extraction is performed on the preprocessed image to obtain a skeleton image of the multi-layer tab. The skeleton image is a single-pixel width skeleton image.

[0070] Optionally, the process of preprocessing the cross-sectional image of the multi-layer tab may include: binarizing the cross-sectional image of the multi-layer tab to obtain a binarized image, detecting holes in the binarized image, and filling the holes if the size of the holes meets a preset condition.

[0071] It should be noted that the background pixels and foreground pixels in the binarized image have different pixel values. For example, the pixel value of the background pixel may be 0, and the pixel value of the foreground pixel may be 1.

[0072] In addition, the broken connected domains in the skeleton image can be determined, and then the broken connected domains can be merged to obtain the merged connected domains. Based on the merged connected domains and the unbroken connected domains, the target number of multi-layer tabs can be counted. For example, the sum of each connected domain can be used as the target number of multi-layer tabs.

[0073] In an embodiment of the present application, if the target number is less than the preset number, it is determined that there is a tab in the multi-layer tab in a folded state; if the target number is less than the preset number, it is determined that no tab in the multi-layer tab is in a folded state.

[0074] The broken connected domains are merged to obtain a merged connected domain; based on the merged connected domain and the unbroken connected domain, the target number of multi-layer tabs is counted more accurately, thereby making the tab folding detection more accurate.

[0075] According to some embodiments of the present application, FIG2 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG2 , the process of merging the broken connected domains in the skeleton image to obtain the processed connected domains in S102 includes:

[0076] S201: If the endpoint of the connected domain is within a preset area of ​​the skeleton image, determine a first foreground point and a second foreground point adjacent to the endpoint according to the endpoint;

[0077] S202 , performing merging processing on the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain a processed connected domain.

[0078] It is worth noting that if the endpoint of a connected domain is within a preset area of ​​the skeleton image, the connected domain is determined to be a suspected broken connected domain, the endpoint is determined as break point A, and a vertical cross-section of the endpoint is determined. The first foreground point and the second foreground point are determined based on the connected domain on the vertical cross-section. The first foreground point can be referred to as the uppermost foreground point A1, and the second foreground point A2 can be referred to as the lowermost foreground point.

[0079] It should be noted that if there is only one branch in the broken connected domain, the first foreground, the second foreground point and the breaking point are the same point, and the first foreground and the second foreground point are both breaking point A.

[0080] In an embodiment of the present application, the first connected domain where the first foreground point is located and the connected domain to be merged in the second connected domain where the second foreground point is located can be determined, and the connected domain where the endpoint is located and the connected domain to be merged are merged to obtain the processed connected domain.

[0081] If the endpoints of the connected domain are within the preset area of ​​the skeleton image, merging is performed based on the endpoints and the first and second foreground points adjacent to the endpoints, so that the result of the merging is more reasonable and accurate.

[0082] According to some embodiments of the present application, FIG3 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG3 , the process of merging the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located in the above S202 to obtain the processed connected domain may include:

[0083] S301, determining a first distance between an endpoint and a first foreground point, and a second distance between an endpoint and a second foreground point;

[0084] S302: If the first distance is less than the second distance, merge the first connected domain where the first foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain;

[0085] S303: If the second distance is smaller than the first distance, merge the second connected domain where the second foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain.

[0086] The first foreground point is the uppermost foreground point closest to the endpoint, and the second foreground point is the lowermost foreground point closest to the endpoint. The first connected domain where the first foreground point is located may be the upper adjacent connected domain, and the second connected domain where the second foreground point is located may be the lower adjacent connected domain.

[0087] In an embodiment of the present application, the connected domain where the endpoint is located is merged with the first connected domain where the first foreground point is located or the second connected domain where the second foreground point is located to obtain a merged connected domain. In addition, the independent connected domains before the merge need to be deleted. If the first connected domain and the connected domain where the endpoint are located are merged, the independent first connected domain and the connected domain where the endpoint are located are deleted, and the second connected domain is retained; if the second connected domain and the connected domain where the endpoint are located are merged, the independent second connected domain and the connected domain where the endpoint are located are deleted, and the first connected domain is retained.

[0088] FIG4 is a flow chart of a tab fold detection method provided by an embodiment of the present application. As shown in FIG4 , if endpoint A of connected domain 2 is within a preset area of ​​the skeleton image, connected domain 2 is considered to be a suspected broken connected domain. The upper foreground point B of the remaining connected domains closest to point A and the lower foreground point C of the remaining connected domains closest to point A are determined, thereby finding the upper adjacent connected domain 1 and the lower adjacent connected domain 3. The upper adjacent connected domain 1 is closest to the connected domain 2. The broken connected domain 1 and the broken connected domain 2 are merged, and the original independent broken connected domains 1 and 2 are deleted.

[0089] Among them, the merged connected domain is counted according to the previous multi-section counting method of the connected domain sampling points, and three tabs will be counted, which is correct; however, if it is divided into three independent connected domains and counted separately, four tabs will be detected, and one tab will be counted too many.

[0090] In addition, Figure 5 is a schematic diagram of a tab connected domain rupture provided in an embodiment of the present application. As shown in Figure 5 , (a), (b) and (c) in Figure 5 show three different situations of tab connected domain rupture.

[0091] The first distance between the endpoint and the first foreground point, and the second distance between the endpoint and the second foreground point, can accurately determine the first connected domain and the second connected domain that need to be merged with the connected domain where the endpoint is located, thereby achieving accurate merging of the connected domains.

[0092] According to some embodiments of the present application, FIG6 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG6 , the process of counting the target number of multi-layer tabs based on the merged connected domains and the unbroken connected domains in the above S103 may include:

[0093] S601, traverse the merged connected domain and each third connected domain in the unbroken connected domain, and count the number of tabs in each third connected domain;

[0094] S602, adding the number of tabs in each third connected domain to obtain a first target number;

[0095] S603: Determine the target number of multi-layer tabs according to the first target number, the number of endpoints in the merged connected domain and the preset area in the unbroken connected domain.

[0096] The third connected domain may be any one of the merged connected domains and the unbroken connected domains. The number of tabs in each third connected domain may be calculated separately, and the number of tabs in each third connected domain may be added together to obtain the first target number.

[0097] It should be noted that the preset area may be the left area, the number of endpoints in the preset area may be the number of left endpoints in the left area, the number of endpoints in the preset area may be b, and the first target number may be a.

[0098] By fully utilizing skeleton endpoint information and taking into account the horizontal expansion of the tab cross-section skeleton image, a strategy for distinguishing left and right endpoints was devised. Furthermore, because the leftmost endpoint of each connected domain skeleton is typically located at the base of the tab, this left region is typically imaged clearly. Therefore, the number of left-side endpoints within a certain range on the left side of the image often accurately reflects the actual number of tabs in the image.

[0099] For example, the target point P1 and its 8 neighboring pixels are defined as follows:

[0100] P9P2P3P8P1P4P7P6P5

[0101] Left endpoint: Pixels P2, P9, P8, P7, and P6 have a value of 0, meaning they are background pixels. Among pixels P3, P4, and P5, only one has a value of 1, and the other two are background pixels. Right endpoint: Pixels P2, P3, P4, P5, and P6 have a value of 0, meaning they are background pixels. Among pixels P9, P8, and P7, only one has a value of 1, and the other two are background pixels.

[0102] The first target number is obtained based on the count of the connected domain after the merger and the connected domain that is not broken. On the basis of the first target number, the target number is determined in combination with the number of endpoints in the preset area in the connected domain after the merger and the connected domain that is not broken, so that the determined target number is more accurate.

[0103] According to some embodiments of the present application, FIG7 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG7 , the process of determining the target number of multi-layer tabs in the above S603 based on the first target number, the merged connected domain, and the number of endpoints in the preset area of ​​the unbroken connected domain may include:

[0104] S701. If the number of endpoints in the preset area is the same as the preset number, the number of endpoints in the preset area is used as the target number;

[0105] S702: If the number of endpoints in the preset area is different from the preset number, determine the maximum value between the number of endpoints in the preset area and the first target number;

[0106] S703: Determine the target quantity according to the maximum value and the preset quantity.

[0107] Among them, when the number of endpoints in the preset area is different from the preset number, if the number of endpoints in the preset area is greater than the first target number, the maximum value is the number of endpoints in the preset area; if the number of endpoints in the preset area is less than the first target number, the maximum value is the first target number.

[0108] The target number can be called checkNum. If the number of endpoints b in the preset area is equal to the preset number normalNum, then checkNum = b. If the number of endpoints b in the preset area is not equal to the preset number normalNum, then the maximum value between the number of endpoints b in the preset area and the first target number a is determined. This process is expressed as: max(a,b).

[0109] The target quantity is determined based on the maximum value of the number of endpoints in the preset area and the first target quantity and the preset quantity. The determined target quantity is more accurate, thereby making the detection of the tab folding more accurate.

[0110] According to some embodiments of the present application, FIG8 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG8 , the process of determining the target number based on the maximum value and the preset number in the above S703 may include:

[0111] S801: If the maximum value is less than or equal to the preset number, the maximum value is used as the target number.

[0112] S802: If the maximum value is greater than a preset number, traverse the broken connected domain and each fourth connected domain in the unbroken connected domain, and count the number of tabs in each fourth connected domain.

[0113] S803, adding the number of tabs in each fourth connected domain to obtain a second target number;

[0114] S804: Set the second target quantity as the target quantity.

[0115] Among them, if the maximum value max(a,b) between the number of endpoints in the preset area and the first target number is less than or equal to the preset number normalNum, then the target number checkNum = the maximum value max(a,b); if max(a,b) is greater than the preset number normalNum, then the target number checkNum = the second target number c.

[0116] In addition, the fourth connected domain can be any one of the broken connected domain and the unbroken connected domain. The number of tabs in each fourth connected domain is determined sequentially or simultaneously, and the number of tabs in each fourth connected domain is added to obtain the second target number c.

[0117] The maximum value is used as the target number, or the second target number obtained based on the fourth connected domain is used as the target number, so that the target number can be determined more reasonably and accurately.

[0118] According to some embodiments of the present application, FIG9 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG9 , the process of counting the number of tabs in each third connected domain in S601 may include:

[0119] S901, determining sampling points of each third connected domain;

[0120] S902: sorting the sampling points of each third connected component according to the position of each third connected component in a preset horizontal direction to obtain a sorting result;

[0121] S903 : Determine the number of tabs in each third connected domain according to the sorting result and a preset threshold.

[0122] The preset horizontal direction may be the X-axis direction in the coordinate axis.

[0123] In some embodiments, in the X-axis direction, for each third connected domain, the coordinate values ​​of the sampling points in each third connected domain are sorted to obtain a sorting result. The sorting can be from small to large or from large to small, and this embodiment of the application does not specifically limit this.

[0124] In addition, the preset threshold value can be an empirical value or can be set according to actual needs, and the embodiments of the present application do not impose specific restrictions on this.

[0125] The number of tabs in each third connected domain is determined according to the sorting result and the preset threshold, so that the determined number of tabs in each third connected domain is more accurate.

[0126] According to some embodiments of the present application, FIG. 10 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG. 10 , the process of determining the number of tabs in each third connected domain based on the sorting result and the preset threshold in S903 may include:

[0127] S1001: Determine, based on the sorting result, whether the distance between two adjacent sampling points is greater than a preset threshold;

[0128] S1002: If yes, determine the number of tabs on the vertical section between two adjacent sampling points;

[0129] S1003 : Determine the number of tabs in each third connected domain according to the number of tabs on the vertical section between two adjacent sampling points.

[0130] In an embodiment of the present application, if the distance between two adjacent sampling points is greater than a preset threshold, the number of tabs on the vertical section between the two adjacent sampling points is determined; based on the number of tabs on the vertical section between the two adjacent sampling points, the maximum value thereof is taken as the number of tabs in each third connected domain.

[0131] The number of tabs in each third connected domain is determined based on the number of tabs on the vertical section between two adjacent sampling points. The distance between the sampling points is fully considered, making the determination of the number of tabs in the third connected domain more reasonable.

[0132] According to some embodiments of the present application, FIG11 is a flow chart of a tab fold detection method provided in an embodiment of the present application. As shown in FIG11 , the process of determining the sampling points of each third connected domain in the above S901 may include:

[0133] S1101, determining the intersection, first-type endpoints, and second-type endpoints in each third connected domain;

[0134] S1102, removing burr points in the first type of endpoints and the second type of endpoints to obtain processed endpoints;

[0135] S1103: Use the processed endpoints and intersections as sampling points.

[0136] The first type of endpoint may be a left endpoint, and the second type of endpoint may be a right endpoint.

[0137] In some embodiments, the intersection points and endpoints of each connected domain are extracted, and the endpoints are classified as left endpoints and right endpoints, and the burrs of the skeleton are removed, that is, the burrs in the first type of endpoints and the second type of endpoints are removed to obtain processed endpoints. The sampling points may include: processed endpoints and intersection points.

[0138] Removing the burr points in the first type of endpoints and the second type of endpoints can make the determined endpoints more accurate and avoid the problem of inaccurate tab counting caused by the burrs.

[0139] A schematic flow chart of a tab fold detection method provided in an embodiment of the present application may include:

[0140] S1001, performing skeleton extraction processing on the cross-sectional image of the multi-layer tab to obtain a skeleton image of the multi-layer tab;

[0141] S1002: If the endpoint of the connected domain is within a preset area of ​​the skeleton image, determine a first foreground point and a second foreground point adjacent to the endpoint based on the endpoint, and the endpoint, the first foreground point, and the second foreground point are on different connected domains;

[0142] S1003, determining a first distance between the endpoint and the first foreground point, and a second distance between the endpoint and the second foreground point;

[0143] S1004: If the first distance is less than the second distance, merge the first connected domain where the first foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain;

[0144] S1005: If the second distance is smaller than the first distance, merge the second connected domain where the second foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain.

[0145] S1006, traversing the connected domain after the merger and each third connected domain in the unbroken connected domain, and determining the intersection, the first type endpoint, and the second type endpoint in each third connected domain;

[0146] S1007, removing burrs from the first-type endpoints and the second-type endpoints to obtain processed endpoints;

[0147] S1008: Use the processed endpoints and intersections as sampling points.

[0148] S1009. Sort the sampling points of each third connected component according to the position of each third connected component in a preset horizontal direction to obtain a sorting result;

[0149] S1010: Determine, based on the sorting result, whether the distance between two adjacent sampling points is greater than a preset threshold;

[0150] S1011. If yes, determine the number of tabs on the vertical section between two adjacent sampling points;

[0151] S1012, determining the number of tabs in each third connected domain according to the number of tabs on the vertical cross section between two adjacent sampling points;

[0152] S1013, adding the number of tabs in each third connected domain to obtain a first target number;

[0153] S1014. If the number of endpoints in the preset area is the same as the preset number, the number of endpoints in the preset area is used as the target number;

[0154] S1015: If the number of endpoints in the preset area is different from the preset number, determining a maximum value between the number of endpoints in the preset area and the first target number;

[0155] S1016. If the maximum value is less than or equal to the preset number, the maximum value is used as the target number;

[0156] S1017: If the maximum value is greater than a preset number, traverse the broken connected domain and each fourth connected domain in the unbroken connected domain, and count the number of tabs in each fourth connected domain;

[0157] S1018, adding the number of tabs in each fourth connected domain to obtain a second target number;

[0158] S1019: Set the second target quantity as the target quantity.

[0159] FIG12 is a schematic structural diagram of a tab fold detection device provided in an embodiment of the present application. As shown in FIG12 , the device may include:

[0160] An extraction processing module 1201 is used to perform skeleton extraction processing on the cross-sectional image of the multi-layer tab to obtain a skeleton image of the multi-layer tab;

[0161] A merging processing module 1202 is used to merge the broken connected domains in the skeleton image to obtain a merged connected domain, where the broken connected domains are connected domains that are broken in the same tab cross section;

[0162] A statistics module 1203 is configured to count the target number of multi-layer tabs based on the merged connected domains and the unbroken connected domains;

[0163] The detection module 1204 is used to detect whether there is a tab in the multi-layer tab that is in a folded state according to the target number and the preset number.

[0164] In some embodiments, the merging processing module 1202 is specifically configured to determine, based on the endpoint, a first foreground point and a second foreground point adjacent to the endpoint if the endpoint of the connected domain is within a preset area of ​​the skeleton image, and the endpoint, the first foreground point, and the second foreground point are on different connected domains; and perform merging processing based on the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain a processed connected domain.

[0165] In some embodiments, the merging processing module 1202 is specifically used to determine a first distance between the endpoint and the first foreground point, and a second distance between the endpoint and the second foreground point; if the first distance is less than the second distance, the first connected domain where the first foreground point is located and the connected domain where the endpoint is located are merged to obtain a merged connected domain; if the second distance is less than the first distance, the second connected domain where the second foreground point is located and the connected domain where the endpoint is located are merged to obtain a merged connected domain.

[0166] In some embodiments, the statistical module 1203 is specifically used to traverse the merged connected domain and each third connected domain in the unbroken connected domain, and count the number of tabs in each third connected domain; add the number of tabs in each third connected domain to obtain a first target number; and determine the target number of multi-layer tabs based on the first target number, the number of endpoints in the preset area in the merged connected domain and the unbroken connected domain.

[0167] In some embodiments, the statistical module 1203 is specifically used to, if the number of endpoints in the preset area is the same as the preset number, use the number of endpoints in the preset area as the target number; if the number of endpoints in the preset area is different from the preset number, determine the maximum value between the number of endpoints in the preset area and the first target number; and determine the target number based on the maximum value and the preset number.

[0168] In some embodiments, the statistical module 1203 is specifically used to use the maximum value as the target number if the maximum value is less than or equal to a preset number; if the maximum value is greater than the preset number, traverse the broken connected domain and each fourth connected domain in the unbroken connected domain, and count the number of tabs in each fourth connected domain; add the number of tabs in each fourth connected domain to obtain a second target number; and use the second target number as the target number.

[0169] In some embodiments, the statistical module 1203 is specifically used to determine the sampling points of each third connected domain; sort the sampling points of each third connected domain according to the position of each third connected domain in a preset horizontal direction to obtain a sorting result; and determine the number of tabs in each third connected domain based on the sorting result and a preset threshold.

[0170] In some embodiments, the statistical module 1203 is specifically used to determine whether the distance between two adjacent sampling points is greater than a preset threshold based on the sorting result; if so, determine the number of tabs on the vertical section between the two adjacent sampling points; and determine the number of tabs in each third connected domain based on the number of tabs on the vertical section between the two adjacent sampling points.

[0171] In some embodiments, the statistical module 1203 is specifically used to determine the intersection points, first-class endpoints, and second-class endpoints in each third connected domain; remove the burr points in the first-class endpoints and the second-class endpoints to obtain processed endpoints; and use the processed endpoints and intersection points as sampling points.

[0172] Figure 13 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in Figure 13, the electronic device may include: a processor 1301 and a memory 1302. Memory 1302 is used to store programs, and processor 1301 calls the programs stored in memory 1302 to execute the above method embodiment. The specific implementation methods and technical effects are similar and will not be repeated here.

[0173] The electronic device can be a variety of different types of devices, such as a server of a service provider, a device associated with a client (e.g., a client device), a system on a chip, and / or any other suitable electronic device. Examples of electronic devices include, but are not limited to, desktop computers, server computers, laptop or netbook computers, mobile devices (e.g., tablet computers, cellular or other wireless phones (e.g., smartphones), notepad computers, mobile stations), wearable devices (e.g., glasses, watches), entertainment devices (e.g., entertainment appliances, set-top boxes communicatively coupled to a display device, game consoles), televisions or other display devices, automotive computers, and the like.

[0174] Among other things, the processor 1301 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuits, and / or any device that manipulates signals based on operational instructions.

[0175] The present application also provides a computer-readable storage medium having a computer program stored therein. When the computer program is read and executed, the above method embodiments are implemented. The computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0176] The present application also provides a computer program product, such as a computer-readable storage medium, comprising a computer program, which is used to perform the above method embodiments when executed by a processor.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A tab fold detection method, comprising: Performing skeleton extraction processing on the cross-sectional image of the multi-layer tab to obtain a skeleton image of the multi-layer tab; Merging the broken connected domains in the skeleton image to obtain merged connected domains, wherein the broken connected domains are connected domains that are broken in the same tab cross section; Counting the target number of the multi-layer tabs according to the merged connected domains and the unbroken connected domains; According to the target number and the preset number, it is detected whether there is a tab in the multi-layer tab that is in a folded state.

2. The method according to claim 1, wherein The merging of the broken connected domains in the skeleton image to obtain the processed connected domains further includes: If an endpoint of the connected domain is within a preset area of ​​the skeleton image, determining a first foreground point and a second foreground point adjacent to the endpoint based on the endpoint, wherein the endpoint, the first foreground point, and the second foreground point are on different connected domains; A merging process is performed on the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain the processed connected domain.

3. The method according to claim 2, wherein: The merging process is performed according to the connected domain where the endpoint is located, the first connected domain where the first foreground point is located, and the second connected domain where the second foreground point is located to obtain the processed connected domain, including: determining a first distance between the endpoint and the first foreground point, and a second distance between the endpoint and the second foreground point; If the first distance is smaller than the second distance, merging the first connected domain where the first foreground point is located and the connected domain where the endpoint is located to obtain a merged connected domain; If the second distance is smaller than the first distance, the second connected domain where the second foreground point is located and the connected domain where the endpoint is located are merged to obtain a merged connected domain.

4. The method according to claim 1, wherein The counting of the target number of the multi-layer tabs according to the merged connected domains and the unbroken connected domains includes: Traversing the merged connected domain and each third connected domain in the unbroken connected domain, and counting the number of tabs in each third connected domain; Adding the number of tabs in each third connected domain to obtain a first target number; The target number of the multi-layer tabs is determined according to the first target number, the merged connected domain, and the number of endpoints in the preset area in the unbroken connected domain.

5. The method according to claim 4, wherein Determining the target number of the multi-layer tabs according to the first target number, the merged connected domain, and the number of endpoints in the preset area in the unbroken connected domain includes: If the number of endpoints in the preset area is the same as the preset number, the number of endpoints in the preset area is used as the target number; If the number of endpoints in the preset area is different from the preset number, determining the maximum value between the number of endpoints in the preset area and the first target number; The target quantity is determined according to the maximum value and the preset quantity.

6. The method according to claim 5, wherein: The determining the target quantity according to the maximum value and the preset quantity includes: If the maximum value is less than or equal to the preset number, the maximum value is used as the target number; If the maximum value is greater than the preset number, traversing the broken connected domain and each fourth connected domain in the unbroken connected domain, and counting the number of tabs in each fourth connected domain; Adding the number of tabs in each fourth connected domain to obtain a second target number; The second target quantity is used as the target quantity.

7. The method according to claim 4, wherein: The counting of the number of tabs in each third connected domain includes: Determining sampling points of each third connected domain; In a preset horizontal direction, sorting the sampling points of each third connected domain according to the position of each third connected domain to obtain a sorting result; The number of tabs in each third connected domain is determined according to the sorting result and a preset threshold.

8. The method according to claim 7, wherein: The step of determining the number of tabs in each third connected domain according to the sorting result and a preset threshold comprises: Determine, based on the sorting result, whether the distance between two adjacent sampling points is greater than the preset threshold; If yes, then determine the number of tabs on the vertical section between the two adjacent sampling points; The number of tabs in each third connected domain is determined according to the number of tabs on the vertical cross section between the two adjacent sampling points.

9. The method according to claim 4, wherein: The determining of the sampling points of each third connected domain includes: Determine an intersection point, a first-category endpoint, and a second-category endpoint in each of the third connected domains; removing burr points from the first-type endpoints and the second-type endpoints to obtain processed endpoints; The processed endpoints and the intersection points are used as the sampling points.

10. A tab fold detection device, wherein: include: An extraction processing module, configured to perform skeleton extraction processing on a cross-sectional image of a multi-layer tab to obtain a skeleton image of the multi-layer tab; a merging processing module, configured to merge the broken connected domains in the skeleton image to obtain merged connected domains, wherein the broken connected domains are multiple connected domains belonging to the same tab cross section; a statistical module, configured to count the target number of the multi-layer tabs based on the merged connected domains and the unbroken connected domains; The detection module is used to detect whether there is a tab in the multi-layer tab in a folded state according to the target number and the preset number.

11. An electronic device, wherein: include: A memory and a processor, wherein the memory stores a computer program executable by the processor, and when the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, wherein: The storage medium stores a computer program, which, when read and executed, implements the method according to any one of claims 1 to 9.

13. A computer program product, wherein: The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program is used to implement the method according to any one of claims 1 to 9.

Images