Zipper puller blockage visual identification method of full-automatic zipper puller penetrating machine

Abstract

The invention relates to the technical field of image recognition, in particular to a zipper puller blockage visual recognition method for a full-automatic zipper puller penetrating machine, and the method comprises the steps: obtaining a zipper puller guide image and a zipper puller region of the zipper puller guide image; according to the structure and gray level distribution of the sliding window in the sliding windows in the two adjacent puller areas, the matching coefficient of the sliding windows in the two adjacent puller areas is obtained; obtaining a matching window of the sliding windows according to the matching coefficient and the structural features of the two sliding windows; and analyzing the consistency of the position relationship between all the sliding windows and the matching windows in the puller region and the position relationship between other adjacent puller regions in the constructed structure matching space to obtain the blockage coefficient of the puller region, and identifying the blockage of the zipper puller penetrating machine by using the blockage coefficient. According to the method, region division is carried out on the pull head, the influence of non-fixed structures is eliminated in the region matching process, the condition of pull head blockage is judged according to the distance between the matching structures, and the accuracy of pull head distance calculation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image recognition, and in particular to a zipper puller blockage visual recognition method of a full-automatic zipper puller threading machine. BACKGROUND

[0002] The full-automatic zipper puller threading machine is a core automatic equipment in the zipper processing link, and is widely used in the fields of clothing, bags, home textiles and special equipment, etc. due to its multi-material adaptation and full-process integration capability. Its normal operation is the first element of its production, and in the production process of the full-automatic zipper puller threading machine, zipper puller blockage is a core problem that restricts efficiency, which often occurs in the vibration disc feeding track, linear conveying channel and grabbing station. In order to reduce the influence of puller blockage on production efficiency, a precise puller blockage detection method is needed first.

[0003] For puller blockage recognition, some existing technologies introduce photoelectric sensors for preliminary monitoring, but such devices can only identify whether there is material, and cannot distinguish between normal arrangement and stacking blockage of pullers. Some also use visual detection, but in traditional visual detection, the edges between puller regions are often directly used to calculate the distance between pullers. Since some metal pullers have reflection, the reflection will drown some puller edges, and thus the distance between the puller edges cannot accurately reflect the actual distance between the pullers. SUMMARY

[0004] The present application provides a zipper puller blockage visual recognition method of a full-automatic zipper puller threading machine to solve the existing problems.

[0005] The zipper puller blockage visual recognition method of the full-automatic zipper puller threading machine of the present application adopts the following technical solution: One embodiment of the present application provides a zipper puller blockage visual recognition method of a full-automatic zipper puller threading machine, which comprises the following steps: Obtaining the image of the puller on the guide rail and constructing a plurality of puller regions according to the guide rail direction; For the i-th puller region on the guide rail and the j-th puller region adjacent to the i-th puller region, according to the structure and gray scale distribution of each sliding window in the i-th puller region and each sliding window in the j-th puller region, the matching coefficients of each sliding window in the i-th puller region and each sliding window in the j-th puller region are obtained; According to the matching coefficients of the two sliding windows respectively belonging to the i-th puller region and the j-th puller region, and verifying the information content and consistency of the structural features of the two sliding windows, the matching window of each sliding window in the i-th puller region in the j-th puller region is obtained; According to the position relationship of each sliding window in the i-th zipper region and the matching window thereof in the j-th zipper region in the zipper image, a structure matching space is constructed; the consistency of the position relationship of all sliding windows in each zipper region and the corresponding matching window in the adjacent zipper region with the position relationship of other adjacent zipper regions is analyzed in the structure matching space, a blocking coefficient of each zipper region is obtained, and the blocking of the zipper threading machine is identified by using the blocking coefficient.

[0006] Preferably, the obtaining of the matching coefficient of each sliding window in the i-th zipper region and each sliding window in the j-th zipper region according to the structural and grayscale distribution similarity of each sliding window in the i-th zipper region and each sliding window in the j-th zipper region comprises: The structural similarity index of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region is obtained. The absolute value of the grayscale value difference of the position corresponding pixel points in the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region is obtained, and the mean value of the absolute value of the grayscale value difference is denoted as the grayscale similarity of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region. The matching coefficient of each sliding window in the i-th zipper region and each sliding window in the j-th zipper region is obtained, and the matching coefficient is in a positive proportional relationship with the structural similarity index and in an inverse proportional relationship with the grayscale similarity.

[0007] Preferably, the obtaining of the matching coefficient of each sliding window in the i-th zipper region and each sliding window in the j-th zipper region comprises: The calculation mode of the matching coefficient of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region is as follows: wherein, is the m-th sliding window in the i-th zipper region, is the n-th sliding window in the j-th zipper region, is the structural similarity index of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region, is the grayscale similarity of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region, is an exponential function with a natural constant as the base.

[0008] Preferably, the specific obtaining steps of the matching window of each sliding window in the i-th zipper region in the j-th zipper region comprise: ​performing edge detection on the mth sliding window in the ith puller region to obtain the number of edge pixel points and the number of edges in the mth sliding window in the ith puller region; obtaining a structural feature value of the mth sliding window in the ith puller region according to the number of edge pixel points and the number of edges; correcting a matching coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region by using the structural feature value of the mth sliding window in the ith puller region and the structural feature value of the n th sliding window in the j th puller region, and obtaining a matching correction coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region; obtaining a matching window of each sliding window in the ith puller region in the j th puller region by using the matching correction coefficient.

[0009] Preferably, the step of correcting the matching coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region by using the structural feature value of the mth sliding window in the ith puller region and the structural feature value of the n th sliding window in the j th puller region, and obtaining a matching correction coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region includes: differences between the structural feature value of the mth sliding window in the ith puller region and the structural feature value of the sliding window of all pixel points in the ith puller region are recorded as the structural feature standard value of the mth sliding window in the ith puller region ; differences between the structural feature value of the n th sliding window in the j th puller region and the structural feature value of the sliding window of all pixel points in the j th puller region are recorded as the structural feature standard value of the n th sliding window in the j th puller region ; The calculation method of the matching correction coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region is as follows: wherein, is the matching coefficient of the mth sliding window in the ith puller region and the n th sliding window in the j th puller region.

[0010] Preferably, the step of obtaining a matching window of each sliding window in the ith puller region in the j th puller region by using the matching correction coefficient includes: The sliding window of the pixel point with the maximum matching correction coefficient of the mth sliding window in the ith zipper region is recorded as the matching window of each sliding window in the ith zipper region in the jth zipper region.

[0011] Preferably, the structure matching space is constructed according to the positional relationship of each sliding window in the ith zipper region and the matching window thereof in the jth zipper region and the positional relationship of the matching window in the zipper image. A plane rectangular coordinate system is constructed with any pixel point in the zipper image as the origin, wherein the horizontal axis is the row direction of the pixel points in the zipper image and the vertical axis is the column direction of the pixel points in the zipper image. For the ith zipper region and the jth zipper region adjacent to the ith zipper region on the guide rail, the center pixel points of each sliding window in the ith zipper region and the matching window thereof in the jth zipper region are connected in the zipper image, the obtained connecting line is recorded as the connecting line of each sliding window in the ith zipper region, and the slope of the connecting line in the plane rectangular coordinate system is obtained. A structure matching space is constructed, wherein the horizontal axis of the structure matching space is the length of the connecting line and the vertical axis is the slope of the connecting line in the plane rectangular coordinate system.

[0012] Preferably, the consistency of the positional relationship of each sliding window in each zipper region and the corresponding matching window in the adjacent zipper region and the positional relationship of other adjacent zipper regions is analyzed in the structure matching space, the jamming coefficient of each zipper region is obtained, and the jamming of the zipper threading machine is identified by using the jamming coefficient. The connecting lines of the sliding windows of all pixel points in the ith zipper region and the slopes thereof are projected into the structure matching space to obtain a plurality of discrete points, a K-means clustering algorithm with K=1 is used to cluster all the discrete points, and the obtained cluster is recorded as the matchable window cluster of the ith zipper region. According to the distance between the discrete point of each sliding window in the ith zipper region in the structure matching space and the matchable window cluster, and in combination with the matching correction coefficient of each sliding window in the ith zipper region and the matching window thereof in the jth zipper region, the elimination coefficient of each sliding window in the ith zipper region is obtained. According to the elimination coefficient, all the sliding windows of the ith zipper region are screened to obtain the distance judgment window of the ith zipper region. According to the difference in the length of the connecting line of all the distance judgment windows in the ith zipper region and other zipper regions, the jamming coefficient of each zipper region is obtained, and the jamming of the zipper threading machine is identified by using the jamming coefficient.

[0013] Preferably, the specific obtaining steps of the elimination coefficient include: The Euclidean distance between the discrete point of each sliding window in the i-th slider area in the structure matching space and the cluster center of the matchable window cluster of the i-th slider area in the structure matching space is denoted as the distance deviation degree of each sliding window in the i-th slider area. The elimination coefficient of the m-th sliding window in the i-th slider area is calculated as follows: wherein, is the distance deviation degree of the m-th sliding window in the i-th slider area, is the matching correction coefficient of the m-th sliding window in the i-th slider area and its matching window in the j-th slider area. is an exponential function with a natural constant as the base.

[0014] Preferably, the jam coefficient of each slider area is obtained according to the difference between the lengths of the lines connecting all distance judgment windows in the i-th slider area and other slider areas, and the jam of the zipper threading machine is identified by using the jam coefficient, which comprises: The average length of the lines connecting all distance judgment windows in the i-th slider area is denoted as the slider interval between the i-th slider area and its adjacent slider area . The slider interval between each slider area and its adjacent slider area in the slider image is obtained. The jam coefficient of the i-th slider area is calculated as follows: wherein, is the average of the slider intervals between all slider areas and their adjacent slider areas in the slider image, is an absolute value function. A preset jam judgment coefficient is provided, and if the jam coefficient of the i-th slider area is greater than or equal to 0.8, the i-th slider area is recorded as a jammed area, the full-automatic zipper threading machine issues a jam alarm and notifies the operator to stop and check, and guides the worker to check and repair.

[0015] The beneficial effects of the technical solutions of the present application are as follows: the present application acquires the slider image on the guide rail and constructs a plurality of slider regions according to the guide rail direction; according to the similarity of the structure and the gray distribution of each sliding window in the i th slider region and each sliding window in the j th slider region, the matching coefficient of each sliding window in the i th slider region and each sliding window in the j th slider region is acquired; by analyzing the structure and the gray of different sliding windows in adjacent slider regions, the similarity of the fine structure belonging to the slider between the two windows is reflected; according to the matching coefficient of the two sliding windows respectively belonging to the i th slider region and the j th slider region, and verifying the information content and consistency of the structural features of the two sliding windows, the matching window of each sliding window in the i th slider region in the j th slider region is acquired; by analyzing the information content of the structural features of the two sliding windows, the influence of the sliding window pair of non-zipper structure on matching is screened out, and then the matching coefficient difference of the sliding window pair of non-zipper structure in the sliding window matching is balanced; according to the positional relationship of each sliding window in the i th slider region and its matching window in the j th slider region in the slider image, a structure matching space is constructed; the present application constructs a structure matching space through the positional relationship of the two matched sliding windows in different slider regions, and the structure matching space can represent the positional relationship of the two matched sliding windows; the consistency of the positional relationship of all sliding windows in each slider region and the corresponding matching window in the adjacent slider region with the positional relationship of other adjacent slider regions is analyzed in the structure matching space, the blocking coefficient of each slider region is acquired, and the blocking coefficient is used to identify the blocking of the zipper slider machine; by screening out the two matched sliding windows with inconsistent positional relationship in the structure matching space, only the sliding windows with consistent positional relationship are retained, then the distance between the two slider regions is calculated by using the sliding windows with consistent positional relationship, and the blocking condition of the zipper slider machine is identified according to the distance between the slider regions, thereby improving the accuracy of the slider distance calculation. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0017] Figure 1 The step flow chart of the zipper slider blocking visual identification method of the full-automatic zipper slider machine of the present application. DETAILED DESCRIPTION

[0018] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive purpose, the specific implementation, structure, features and effects of the zipper puller blockage visual recognition method of the full-automatic zipper threading machine according to the present application are described in detail as follows in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0020] The specific scheme of the zipper puller blockage visual recognition method of the full-automatic zipper threading machine provided by the present application is described in detail below in combination with the drawings.

[0021] Please refer to Figure 1 which shows the step flowchart of the zipper puller blockage visual recognition method of the full-automatic zipper threading machine provided by one embodiment of the present application, and the method comprises the following steps: Step S001, acquiring the puller image on the guide rail and constructing a plurality of puller regions according to the guide rail direction.

[0022] It should be noted that the full-automatic zipper threading machine can realize threading the puller onto the zipper tape at fixed intervals, and then cutting the zipper to realize the production of specific specifications of the zipper. It fixes two zipper tapes through two guide rails, clamps the puller through the puller fixing seat to ensure that the two entrances of the puller are opposite to the two zipper tapes. When threading, the insert of the threading machine is first inserted into the rear entrance of the puller and penetrates into the front entrance to open the puller. The fixed zipper tape is inserted through the two entrances of the puller, and the insert is pulled out backward. At this time, the internal passage of the puller opened will restore to the original state due to the metal elasticity, so as to tightly engage with the zipper tape and complete the threading of the zipper.

[0023] However, in the actual process, the teeth of the two zipper tapes cannot be perfectly engaged, which causes the puller to be stuck, or the puller is stuck with the zipper tape when it restores the elasticity, thereby causing the puller to be stuck in the guide rail of the zipper and blocked. Therefore, it is necessary to identify the blockage of the full-automatic zipper threading machine. Therefore, it is necessary to acquire the puller image on the guide rail and construct the puller region according to the guide rail direction, so as to identify the position of the puller for analyzing the blockage.

[0024] Preferably, the specific steps of acquiring the puller image on the guide rail and constructing a plurality of puller regions according to the guide rail direction are as follows: An image sensor is installed above the plane where the two guide rails of the zipper head are located, which is used to collect the puller image on the guide rail; The image of the slider on the guide rail is collected by the image sensor; the slider image is a grayscale image; The Otsu threshold algorithm is used for threshold segmentation on the slider image, and each region highlighted after threshold segmentation is taken as an initial slider region; A minimum bounding rectangle of each initial slider region is constructed in the slider image according to the direction of the guide rail, and a plurality of slider regions are obtained.

[0025] It should be noted that the image sensor in the embodiment is installed directly above the guide rail and is 60 cm away from the guide rail. The parameters of the installed image sensor directly affect the shooting quality. The precision of the embodiment needs to be above 0.05 mm, and therefore the resolution of the image sensor is 1600*1200 pixels. The shooting interval between adjacent two slider images is taken as 0.5 seconds in the embodiment.

[0026] In step S002, for the i-th slider region on the guide rail and the j-th slider region adjacent to the i-th slider region, a matching coefficient of each sliding window in the i-th slider region and each sliding window in the j-th slider region is obtained according to the structure and grayscale distribution of each sliding window in the i-th slider region and each sliding window in the j-th slider region.

[0027] It should be noted that in the automatic zipper penetration machine, the sliders need to be conveyed to the penetration execution position through the straight guide rail running at a certain speed to realize the penetration of the zipper. The running rate of the guide rail is consistent with the penetration rate, and therefore the distance between the sliders in the guide rail remains consistent. However, when the sliders are blocked, the sliders located in the penetration execution position are not taken out of the guide rail, which leads to the decrease of the distance between the sliders in the subsequent guide rail. In the photographed slider image, all the sliders in the guide rail are included. At this time, whether the sliders are blocked can be reflected by the distance between the slider regions in the image. However, the metal sliders and the guide rail have similar colors, and the metal sliders have reflection, which leads to the fact that the edges of the sliders are submerged, so that the distance between the edges of the sliders cannot be directly determined, and the distance between the sliders cannot be determined.

[0028] It should be further noted that the sliders have some small structures, such as slider bodies, pull tabs, pull tab fixing rings, etc. These small structures form obvious feature structures in the slider regions, and all the slider structures in the same guide rail are consistent. Therefore, the distance between the sliders is calculated by the distance between the feature structures in the image in the embodiment. Therefore, in each slider region of the slider image, in order to extract the feature structures and facilitate distance calculation, a sliding window is set in each slider region in the embodiment, and the sliding window is taken as a separate structure extraction unit for extracting the feature structures.

[0029] Based on the above, the embodiment constructs a plurality of sliding windows in two adjacent puller regions on the guide rail, and then analyzes the similarity of the sliding windows in the two adjacent puller regions, so as to analyze the matching of each sliding window in each puller region with each sliding window in the adjacent puller region, and obtain the matching coefficient of each sliding window in each puller region with each sliding window in the adjacent puller region.

[0030] It should be noted that the pullers are arranged in a single column in the full-automatic zipper puller threading machine, and the reverse direction of the forward movement of the guide rail is taken as the selection direction of the adjacent puller region of each puller region, that is, if the guide rail moves in the left direction, the nearest puller region in the right direction of each puller region is taken as the adjacent puller region of each puller region.

[0031] Preferably, for the i-th puller region on the guide rail and the j-th puller region adjacent to the i-th puller region, according to the similarity of the structure and the gray scale distribution of each sliding window in the i-th puller region and each sliding window in the j-th puller region, the specific steps for obtaining the matching coefficient of each sliding window in the i-th puller region and each sliding window in the j-th puller region are as follows: Construct a sliding window, the sliding window in the embodiment is a positive direction window with each pixel point in the puller region as the center and a side length of 7*7. The shape and length of the sliding window are not limited in the embodiment, and other embodiments can select other ways. Obtain the structural similarity index of the m-th sliding window in the i-th puller region and the n-th sliding window in the j-th puller region; Obtain the absolute value of the difference between the gray scale values of the corresponding pixel points in the m-th sliding window in the i-th puller region and the n-th sliding window in the j-th puller region, and the mean value of the absolute value of the difference between the gray scale values is denoted as the gray scale similarity of the m-th sliding window in the i-th puller region and the n-th sliding window in the j-th puller region. Obtain the matching coefficient of each sliding window in the i-th puller region and each sliding window in the j-th puller region, which is in a positive proportional relationship with the structural similarity index and in an inverse proportional relationship with the gray scale similarity.

[0032] As an example, the matching coefficient of the m-th sliding window in the i-th puller region and the n-th sliding window in the j-th puller region is The calculation method is as follows: Wherein, is the m-th sliding window in the i-th puller region, is the n-th sliding window in the j-th puller region, a structural similarity index of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region; a grayscale similarity of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region; an exponential function with a natural constant as a base, used for inversely proportional normalization of the grayscale similarity.

[0033] It is to be noted that the structural similarity index is a prior art technology for evaluating the similarity of two sliding windows from the mean, standard deviation and covariance of the grayscale values, and the present embodiment uses the structural similarity index to evaluate the similarity of the zipper structures in the two sliding windows, and the greater the value, the higher the structural similarity; the present embodiment uses the difference in grayscale values of the corresponding pixels in different zipper regions as the grayscale similarity, thereby avoiding the problem of excessively large matching coefficients caused by slight deviations in two zipper structures but high overall structural similarity, and balancing the difference in matching coefficients when matching the sliding windows.

[0034] Step S003, according to the matching coefficients of the two sliding windows respectively belonging to the ith zipper region and the jth zipper region, and verifying the information content and consistency of the structural features of the two sliding windows, obtaining the matching window of each sliding window in the ith zipper region in the jth zipper region.

[0035] It is to be noted that after obtaining the matching coefficients of the two windows, since the information content contained in different regions of the zipper region is different, the information content represents the small structures in the zipper, such as the zipper body, the pull tab, the pull tab fixing ring, etc., and the information content of the planar structure in the zipper is low and prone to false matching, therefore, the present embodiment analyzes the edge condition in each sliding window in each zipper region, the edge condition represents the information content of the small structures in the zipper, and further corrects the matching coefficients as the weight of the information content, and further obtains the matching window of each sliding window in each zipper region in the adjacent zipper region.

[0036] Preferably, according to the matching coefficients of the two sliding windows respectively belonging to the ith zipper region and the jth zipper region, and verifying the information content and consistency of the structural features of the two sliding windows, the specific steps for obtaining the matching window of each sliding window in the ith zipper region in the jth zipper region are as follows: performing edge detection on the mth sliding window in the ith zipper region to obtain the number of edge pixels and the number of edges in the mth sliding window in the ith zipper region; It should be noted that the embodiment uses the Canny edge detection algorithm for edge detection, which is a known technology, and will not be described here. According to the edge pixel point number and the edge number, the structural feature value of the mth sliding window in the ith zipper region is obtained. The structural feature value of the mth sliding window in the ith zipper region and the structural feature value of the nth sliding window in the jth zipper region are used to correct the matching coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region, and obtain the matching correction coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region. The matching window of each sliding window in the ith zipper region in the jth zipper region is obtained by using the matching correction coefficient.

[0037] Specifically, the specific way of obtaining the structural feature value of the mth sliding window in the ith zipper region according to the edge pixel point number and the edge number is: The edge pixel point number of the mth sliding window in the ith zipper region is denoted as ; The edge number of the mth sliding window in the ith zipper region is denoted as ; The structural feature value of the mth sliding window in the ith zipper region is calculated as: Wherein, is a linear normalization function, and the maximum and minimum value normalization algorithm is used for normalization of the structural feature value in the embodiment.

[0038] Further, the specific way of correcting the matching coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region by using the structural feature value of the mth sliding window in the ith zipper region and the structural feature value of the nth sliding window in the jth zipper region is to obtain the matching correction coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region. The difference between the structural feature value of the mth sliding window in the ith zipper region and the structural feature value of the sliding window of all pixel points in the ith zipper region is denoted as the structural feature standard value of the mth sliding window in the ith zipper region ; The difference between the structural feature value of the nth sliding window in the jth zipper region and the structural feature value of the sliding window of all pixel points in the jth zipper region is denoted as the structural feature standard value of the nth sliding window in the jth zipper region ; The matching correction coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region The calculation method is as follows: Wherein, is the matching coefficient of the mth sliding window in the ith zipper region and the nth sliding window in the jth zipper region.

[0039] It should be noted that the value range of the structural feature standard value has positive and negative, when the value is negative, it means that the information content contained in the mth sliding window is lower than that of other sliding windows in the zipper region to which it belongs, so the correction coefficient is reduced to obtain the matching correction coefficient, thereby avoiding the interference of the sliding window without structure on the matching result; when the structural feature standard value is positive, it means that the information content contained in the mth sliding window is higher than that of other sliding windows in the zipper region to which it belongs, and it can better reflect the structure of the zipper, thereby improving the accuracy of the matching, and it is easier to be used as the basis for calculating the distance between two zippers, so the greater the value of the matching correction coefficient.

[0040] Further, the specific method for obtaining the matching window of each sliding window in the ith zipper region in the jth zipper region by using the matching correction coefficient is as follows: Among all the pixel points of the jth zipper region, the sliding window of the pixel point with the maximum matching correction coefficient of the mth sliding window in the ith zipper region is recorded as the matching window of each sliding window in the ith zipper region in the jth zipper region.

[0041] Step S004, constructing a structure matching space according to the position relationship of each sliding window in the ith zipper region and its matching window in the jth zipper region in the zipper image; analyzing the consistency of the position relationship of all sliding windows in each zipper region and the corresponding matching window in the adjacent zipper region with the position relationship of other adjacent zipper regions in the structure matching space, obtaining the blocking coefficient of each zipper region, and identifying the blocking of the zipper threading machine by using the blocking coefficient.

[0042] It should be noted that the above is the matching of the sliding window belonging to the same structure between the pull head regions, and the distance between the two matched sliding windows represents the distance between the two pull heads of the same structure. However, due to the similar edges of the pull head itself, the consistent structure may exist between different sliding windows in the same pull head region, which causes deviation of the matching accuracy of the sliding window. In addition, due to the shaking of the pull tab during the movement of the guide rail, the position of the shaking pull tab in the image cannot be consistent with that of the pull head, that is, the unstable structure of the pull head itself causes not all the distances between the matched sliding windows to accurately represent the distances between the pull heads.

[0043] Based on the above, when calculating the distance between the pull heads by using the distance between the matched sliding windows of each pull head, the influence of the matching deviation and the sliding window inconsistent with the position of the pull head needs to be avoided. In this embodiment, the position relationship between each sliding window of all pixel points in each pull head region and the matching window in the adjacent pull head region is used, and specifically, a line is constructed between each sliding window and the matching window. The length and angle of the line between the reliable sliding window and the matching window are similar, so that the sliding window is removed, and then the distance between each pull head region and its adjacent pull head region is calculated, and the consistency of the distance is analyzed to obtain the blocking coefficient of each pull head region, and then the blocking of the zipper threading machine is identified.

[0044] Preferably, a structure matching space is constructed according to the position relationship between each sliding window in the i th pull head region and the matching window in the j th pull head region in the pull head image; the consistency of the position relationship between each sliding window in each pull head region and the corresponding matching window in the adjacent pull head region and the position relationship with other adjacent pull head regions is analyzed in the structure matching space, the blocking coefficient of each pull head region is obtained, and the specific steps of identifying the blocking of the zipper threading machine by using the blocking coefficient are as follows: A plane rectangular coordinate system is constructed with any pixel point of the pull head image as the origin, wherein the horizontal axis is the pixel point row direction of the pull head image, and the vertical axis is the pixel point column direction of the pull head image; For the i th pull head region on the guide rail and the j th pull head region adjacent to the i th pull head region, the center pixel points of each sliding window in the i th pull head region and the matching window in the j th pull head region are connected in the pull head image, the obtained connecting line is recorded as the connecting line of each sliding window in the i th pull head region, and the slope of the connecting line in the plane rectangular coordinate system is obtained; A structure matching space is constructed, and the horizontal axis of the structure matching space is the length of the connecting line, and the vertical axis is the slope of the connecting line in the plane rectangular coordinate system; Projecting the connection line of the sliding window of all pixel points in the i-th slider region and the slope thereof into the structure matching space to obtain a plurality of discrete points, using a K-means clustering algorithm with K=1 to cluster all the discrete points, and recording the obtained cluster as a matchable window cluster of the i-th slider region; According to the distance between the discrete point of each sliding window in the i-th slider region in the structure matching space and the matchable window cluster, and in combination with the matching correction coefficient of each sliding window in the i-th slider region and the matching window thereof in the j-th slider region, an elimination coefficient of each sliding window in the i-th slider region is obtained; According to the elimination coefficient, all sliding windows of the i-th slider region are screened to obtain a distance judgment window of the i-th slider region; According to the difference in length of the connection line of all distance judgment windows in the i-th slider region and other slider regions, a jamming coefficient of each slider region is obtained, and the jamming coefficient is used to identify the jamming of the zipper threading machine.

[0045] Specifically, according to the distance between the discrete point of each sliding window in the i-th slider region in the structure matching space and the matchable window cluster, and in combination with the matching correction coefficient of each sliding window in the i-th slider region and the matching window thereof in the j-th slider region, the specific way of obtaining the elimination coefficient of each sliding window in the i-th slider region is: In the structure matching space, the Euclidean distance between the discrete point of each sliding window in the i-th slider region in the structure matching space and the cluster center of the matchable window cluster of the i-th slider region is recorded as the distance deviation degree of each sliding window in the i-th slider region; The elimination coefficient of each sliding window in the i-th slider region is obtained, which is inversely proportional to the distance deviation degree and proportional to the matching correction coefficient of each sliding window in the i-th slider region and the matching window thereof in the j-th slider region; As an example, the elimination coefficient of the m-th sliding window in the i-th slider region is calculated as follows: Wherein, is the distance deviation degree of the m-th sliding window in the i-th slider region, is the matching correction coefficient of the m-th sliding window in the i-th slider region and the matching window thereof in the j-th slider region; is an exponential function with a natural constant as the base.

[0046] Further, according to the elimination coefficient, all sliding windows of the i-th slider region are screened to obtain a distance judgment window of the i-th slider region in the following specific way: A preset filtering threshold is set, and in this embodiment, 0.75 is used as an example. The rejection coefficient of the m-th sliding window in the i-th zipper area is normalized by the maximum and minimum values. The sliding window whose normalized rejection coefficient in the i-th zipper area is greater than or equal to the filtering threshold is denoted as the distance judgment window of the i-th zipper area.

[0047] Furthermore, based on the difference in length between the distance judgment windows of the i-th zipper head area and all other zipper head areas, a blockage coefficient for each zipper head area is obtained. The specific method for identifying blockages in the zipper threading machine using the blockage coefficient is as follows: The average length of the line connecting all distance judgment windows in the i-th zipper area is denoted as the zipper distance between the i-th zipper area and its adjacent zipper areas. ; Obtain the distance between each slider region and its adjacent slider regions in the slider head image; The congestion coefficient of the i-th pull-head area The calculation method is as follows: in, This is the average distance between all slider regions and their adjacent slider regions in the slider image. It is an absolute value function; The preset blockage judgment coefficient is 0.8. If the blockage coefficient of the i-th pull head area is... When the value is greater than or equal to 0.8, the i-th zipper head area is marked as a blocked area. The fully automatic zipper threading machine will issue a blockage alarm and notify the operator to stop the machine for inspection, guiding the staff to carry out inspection and maintenance.

[0048] It should be noted that the embodiments used in this example The model only represents negative correlations and constraints. The model output results are in... Within the interval, This is the input to this model; in specific implementations, it can be replaced with other models that have the same purpose. This embodiment is merely an example. The description will be based on a model, without making any specific limitations.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A visual recognition method for zipper pull blockage in a fully automatic zipper threading machine, characterized in that, The method includes the following steps: Acquire images of the sliders on the guide rail and construct several slider regions according to the guide rail direction; For the i-th zipper head region on the guide rail and the j-th zipper head region adjacent to the i-th zipper head region, based on the similarity of the structure and grayscale distribution of each sliding window in the i-th zipper head region and each sliding window in the j-th zipper head region, obtain the matching coefficient between each sliding window in the i-th zipper head region and each sliding window in the j-th zipper head region; Based on the matching coefficients of two sliding windows belonging to the i-th and j-th zipper regions respectively, and verifying the information content and consistency of the structural features of the two sliding windows, obtain the matching window of each sliding window in the i-th zipper region in the j-th zipper region; A structural matching space is constructed based on the positional relationship between each sliding window in the i-th zipper head region and its matching window in the j-th zipper head region in the zipper head image. In the structural matching space, the consistency between the positional relationship of all sliding windows in each zipper head region and the corresponding matching window in the adjacent zipper head region and the positional relationship of other adjacent zipper head regions is analyzed to obtain the blockage coefficient of each zipper head region. The blockage coefficient is used to identify the blockage of the zipper threading machine.

2. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 1, characterized in that, The step of obtaining the matching coefficient between each sliding window in the i-th slider region and each sliding window in the j-th slider region based on the similarity of their structure and grayscale distribution includes: Construct a sliding window; obtain the structural similarity index between the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region; Obtain the absolute value of the difference in grayscale values ​​between the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region, and record the mean of the absolute values ​​of the grayscale differences as the grayscale similarity between the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region. Obtain the matching coefficient between each sliding window in the i-th zipper region and each sliding window in the j-th zipper region. The matching coefficient is positively proportional to the structural similarity index and inversely proportional to the grayscale similarity.

3. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 2, characterized in that, The process of obtaining the matching coefficient between each sliding window in the i-th slider region and each sliding window in the j-th slider region includes: The matching coefficient between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region. The calculation method is as follows: in, For the m-th sliding window in the i-th pull head region, For the j-th slider region, the n-th sliding window, Let be the structural similarity index between the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region; The grayscale similarity between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region; It is an exponential function with the natural constant as its base.

4. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 1, characterized in that, The specific steps for obtaining the matching window of each sliding window in the i-th slider region in the j-th slider region include: Perform edge detection on the m-th sliding window in the i-th zipper region to obtain the number of edge pixels and the number of edges in the m-th sliding window in the i-th zipper region; The structural feature value of the m-th sliding window in the i-th pull head region is obtained based on the number of edge pixels and the number of edges. Using the structural feature values ​​of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region, the matching coefficients of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region are corrected to obtain the matching correction coefficients of the m-th sliding window in the i-th zipper region and the n-th sliding window in the j-th zipper region. The matching correction coefficient is used to obtain the matching window of each sliding window in the i-th slider region in the j-th slider region.

5. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 4, characterized in that, The process of using the structural feature values ​​of the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region to correct the matching coefficient between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region, and obtaining the matching correction coefficient between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region includes: The difference between the structural feature value of the m-th sliding window in the i-th zipper region and the structural feature values ​​of the sliding windows of all pixels in the i-th zipper region is denoted as the standard value of the structural feature of the m-th sliding window in the i-th zipper region. ; The difference between the structural feature value of the nth sliding window in the j-th zipper region and the structural feature values ​​of the sliding windows of all pixels in the j-th zipper region is denoted as the standard value of the structural feature of the nth sliding window in the j-th zipper region. ; Matching correction coefficient between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region The calculation method is as follows: in, Let be the matching coefficient between the m-th sliding window in the i-th slider region and the n-th sliding window in the j-th slider region.

6. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 4, characterized in that, The step of using the matching correction coefficient to obtain the matching window of each sliding window in the i-th slider region in the j-th slider region includes: In the sliding window of all pixels in the j-th zipper region, the sliding window of the pixel with the largest matching correction coefficient with the m-th sliding window in the i-th zipper region is denoted as the matching window of each sliding window in the i-th zipper region in the j-th zipper region.

7. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 1, characterized in that, The construction of the structural matching space based on the positional relationship between each sliding window in the i-th zipper region and its matching window in the j-th zipper region in the zipper image includes: Construct a Cartesian coordinate system with any pixel in the zipper image as the origin, where the horizontal axis represents the row direction of the pixels in the zipper image and the vertical axis represents the column direction of the pixels in the zipper image. For the i-th slider region on the guide rail and the j-th slider region adjacent to the i-th slider region, connect the center pixel of each sliding window in the i-th slider region and its matching window in the j-th slider region in the slider image. Record the connection obtained as the connection line of each sliding window in the i-th slider region, and obtain the slope of the connection line in the Cartesian coordinate system. Construct a structural matching space, where the horizontal axis of the structural matching space is the length of the connecting line, and the vertical axis is the slope of the connecting line in the Cartesian coordinate system.

8. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 1, characterized in that, The step of analyzing the positional relationship between all sliding windows in each zipper pull area and the corresponding matching windows in adjacent zipper pull areas, and the consistency of the positional relationship between these windows and other adjacent zipper pull areas in the structural matching space, to obtain the blockage coefficient of each zipper pull area, and using the blockage coefficient to identify blockages in the zipper threading machine includes: Project the line connecting all pixels in the i-th zipper region and its slope onto the structure matching space to obtain several discrete points. Use the K-means clustering algorithm with K=1 to cluster all discrete points, and denote the obtained cluster as the matchable window cluster of the i-th zipper region. Based on the distance between the discrete point of each sliding window in the structural matching space in the i-th zipper region and the cluster of matchable windows, and combined with the matching correction coefficient of each sliding window in the i-th zipper region and its matching window in the j-th zipper region, the elimination coefficient of each sliding window in the i-th zipper region is obtained. Based on the elimination coefficient, all sliding windows of the i-th zipper area are filtered to obtain the distance judgment window of the i-th zipper area; Based on the difference in length between the i-th zipper head area and the lengths of the lines connecting all distance judgment windows in other zipper head areas, the blockage coefficient of each zipper head area is obtained, and the blockage coefficient is used to identify the blockage of the zipper threading machine.

9. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 8, characterized in that, The specific steps for obtaining the elimination coefficient include: The Euclidean distance between the discrete point of each sliding window in the i-th zipper region and the cluster center of the matchable window cluster in the i-th zipper region is denoted as the distance deviation of each sliding window in the i-th zipper region. The elimination coefficient of the m-th sliding window in the i-th zipper area The calculation method is as follows: in, Let m be the distance deviation of the m-th sliding window in the i-th slider region. Let be the matching correction coefficient between the m-th sliding window in the i-th slider region and its matching window in the j-th slider region; It is an exponential function with the natural constant as its base.

10. The visual recognition method for zipper pull blockage in a fully automatic zipper threading machine according to claim 1, characterized in that, The step of obtaining the blockage coefficient of each zipper pull area based on the difference in the length of the line connecting all distance judgment windows in the i-th zipper pull area and other zipper pull areas, and using the blockage coefficient to identify the blockage of the zipper threading machine includes: The average length of the line connecting all distance judgment windows in the i-th zipper area is denoted as the zipper distance between the i-th zipper area and its adjacent zipper areas. ; Obtain the distance between each slider region and its adjacent slider regions in the slider head image; The congestion coefficient of the i-th pull-head area The calculation method is as follows: in, This is the average distance between all slider regions and their adjacent slider regions in the slider image. It is an absolute value function; A preset congestion judgment coefficient is set; if the congestion coefficient of the i-th pull-head area is... When the value is greater than or equal to 0.8, the i-th zipper head area is marked as a blocked area. The fully automatic zipper threading machine will issue a blockage alarm and notify the operator to stop the machine for inspection, guiding the staff to carry out inspection and maintenance.

Images