An intelligent warehousing management method and system for packaging bags based on two-dimensional codes

Abstract

The present invention relates to the field of image data processing, and particularly to an intelligent warehouse management method and system for packaging bags based on two-dimensional codes. The method of the present invention includes: preprocessing a packaging bag image that cannot recognize the two-dimensional code to obtain a grayscale image containing only the two-dimensional code area; determining the first abnormal degree of pixel points in the grayscale image; performing edge detection on the grayscale image, and calculating the second abnormal degree of the obtained target edge, wherein the second abnormal degree is positively correlated with the average curvature of pixel points on the target edge and the mean value of the first abnormal degree respectively; when the second abnormal value is greater than a preset threshold, filtering the target edge; performing two-dimensional code recognition according to the image obtained after filtering, and performing warehouse management according to the recognized information. The present invention can improve the recognition rate of two-dimensional codes, thereby improving the warehouse management efficiency of goods.

Description

Technical Field

[0001] The present invention relates to the field of image data processing. More specifically, the present invention relates to an intelligent warehouse management method and system for packaging bags based on two-dimensional codes. Background Art

[0002] Intelligent warehouse management systems are widely used in the logistics industry. By introducing advanced technologies such as the Internet of Things, big data, and artificial intelligence, these systems make warehouse management more intelligent and automated. For example, an intelligent warehouse management system collects information such as the quantity, location, and status of items in the warehouse in real time, and then optimizes operations such as goods storage and retrieval and personnel scheduling based on technologies such as artificial intelligence. Among them, by identifying the two-dimensional code on the goods, rapid identification, tracking and positioning of the goods can be achieved, so that operations such as automatic sorting and scheduling of the goods can be carried out. The two-dimensional code technology increases the visibility of the logistics process and helps the warehouse management system manage the goods.

[0003] When identifying a two-dimensional code image, if the two-dimensional code image has problems such as low contrast, blurriness, background interference, or damage, it is not easy to be recognized. For the problem of poor quality of the two-dimensional code image, generally, image enhancement is performed on the two-dimensional code image to improve the success rate of two-dimensional code recognition. For example, a Chinese patent application document with the publication number CN112580383A discloses a two-dimensional code recognition method, device, electronic device, and storage medium. This method performs image enhancement on the unrecognizable two-dimensional code by using the image enhancement method adopted by the successfully recognizable two-dimensional code to improve the success rate of two-dimensional code recognition. However, the above method performs image enhancement on the entire two-dimensional code image without discrimination, and does not selectively perform image enhancement on the two-dimensional code according to the image characteristics of the two-dimensional code itself. Therefore, the effect of two-dimensional code image enhancement is general, resulting in a low recognition rate of the two-dimensional code. Summary of the Invention

[0004] To solve the technical problem of low recognition rate of two-dimensional codes caused by poor two-dimensional code image enhancement effect, the present invention provides solutions in the following aspects.

[0005] In a first aspect, the present invention provides an intelligent warehouse management method for packaging bags based on two-dimensional codes, including: preprocessing a packaging bag image with an unrecognizable two-dimensional code to obtain a grayscale image containing only the two-dimensional code area; determining a first abnormal degree of pixel points in the grayscale image, and the calculation expression of the first abnormal degree is:

[0006] ;

[0007] In the formula, represents the first abnormal value of the pixel point, , , respectively represent the gray value, gradient value, and gradient direction of the pixel point, , , respectively represent the reference gray value, reference gradient value, and reference gradient direction of the pixel point; perform edge detection on the grayscale image, and calculate the second abnormality degree of the obtained target edge, where the second abnormality degree is positively correlated with the average curvature of the pixel points on the target edge and the mean value of the first abnormality degree; when the second abnormal value is greater than a preset threshold, filter the target edge; perform two-dimensional code recognition based on the filtered image, and perform warehouse management based on the recognized information.

[0008] Beneficial effects: By filtering abnormal edges according to the characteristics of the two-dimensional code, the quality of the two-dimensional code image is improved, thereby improving the recognition rate of the two-dimensional code, and further improving the efficiency of warehouse management.

[0009] Furthermore, preprocess the packaging bag image that cannot recognize the two-dimensional code, including: converting the packaging bag image that cannot recognize the two-dimensional code into a grayscale image, and segmenting the grayscale image according to the semantic segmentation network.

[0010] Beneficial effects: By segmenting the grayscale image that only contains the two-dimensional code area, the interference of the background area during two-dimensional code recognition is avoided, thereby improving the success rate of two-dimensional code recognition.

[0011] Furthermore, perform edge detection on the grayscale image, and calculate the second abnormality degree of the obtained target edge, including: performing abnormality detection on the first abnormality degree of the pixel points on the target edge, and marking the obtained abnormal pixel points; obtaining the curvature of the unmarked pixel points, and determining the second abnormality degree according to the mean value of the curvature of the unmarked pixel points and the mean value of the first abnormality degree.

[0012] Beneficial effects: By not involving abnormal pixel points when calculating the second abnormality degree, the accuracy of calculating the second abnormality degree is improved, and further the accuracy of determining abnormal edges is improved.

[0013] Furthermore, the calculation expression of the second abnormality degree is as follows:

[0014] ;

[0015] In the formula, represents the second abnormality degree of the target edge, represents the total number of unmarked pixel points on the target edge, represents the th unmarked pixel point on the target edge, Indicates the first degree of abnormality of the unmarked pixel point on the target edge.

[0016] Further, filtering the target edge includes: taking the perpendicular line of the connection line of the two pixel points farthest apart on the target edge as the search direction; starting from the target pixel point on the target edge, searching on both sides according to the search direction, and stopping the search when an edge pixel point is encountered or the search distance is greater than a preset distance; forming a filtering window of the target pixel point with all the searched pixel points, and performing mean filtering on the target pixel point.

[0017] Beneficial effect: By performing mean filtering on the abnormal edge, the quality of the QR code image is improved, and thus the success rate of QR code recognition is increased.

[0018] Further, it further includes: jointly forming a region covering the target edge with all the pixel points serving as the filtering window, and performing mean filtering on the region according to a preset window.

[0019] Beneficial effect: By performing mean filtering on the region where the abnormal edge is located, the problem that the abnormal edge is not smoothly connected to other surrounding pixel points caused by the first mean filtering is avoided, thereby improving the quality of the QR code image, and further increasing the success rate of QR code recognition.

[0020] Further, before performing QR code recognition, it further includes: enhancing the contrast of the filtered image.

[0021] Further, enhancing the contrast of the filtered image includes: performing gamma transformation on the filtered image:

[0022] ;

[0023] In the formula, represents the gray value before enhancing the gray image, represents the gray value after enhancing the gray image, and respectively represent the two gray values with the largest proportion among all the gray values of the gray image before filtering, where .

[0024] Beneficial effect: By specifically enhancing the contrast of the QR code image, the quality of the QR code image is improved, and thus the success rate of QR code recognition is increased.

[0025] In a second aspect, the present invention provides a smart warehouse management system for packaging bags based on two-dimensional codes, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the smart warehouse management method for packaging bags based on two-dimensional codes according to any one of the first aspect is implemented.

[0026] The beneficial effects of the present invention are as follows: by performing mean filtering on the abnormal edges in the two-dimensional code image, the quality of the two-dimensional code image is improved, thereby increasing the success rate of two-dimensional code recognition. In addition, by enhancing the contrast of the two-dimensional code image, the quality of the two-dimensional code image is further improved, thereby increasing the recognition rate of the two-dimensional code, and further improving the efficiency of warehouse management. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of illustration and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:

[0028] Figure 1 is a flowchart schematically showing a smart warehouse management method for packaging bags according to an embodiment of the present invention;

[0029] Figure 2 is a block diagram schematically showing the structure of a smart warehouse management system for packaging bags according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0031] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings.

[0032] Figure 1 is a flowchart schematically showing a smart warehouse management method for packaging bags according to an embodiment of the present invention.

[0033] In a first aspect, the present invention provides a smart warehouse management method for packaging bags based on two-dimensional codes. As Figure 1 shown, the method of the present invention includes:

[0034] S101. Preprocess the packaging bag image that cannot recognize the two-dimensional code to obtain a grayscale image containing only the two-dimensional code area.

[0035] In one embodiment, the goods in the warehouse can be arranged in a consistent manner, with the two-dimensional code on the goods packaging bag facing outward, thereby improving the efficiency of simultaneously photographing multiple goods, and further improving the efficiency of obtaining the two-dimensional code image on the goods packaging bag.

[0036] Further, the obtained two-dimensional code image is recognized. For the packaging bag image of the two-dimensional code that cannot be recognized, by preprocessing it, a grayscale image containing only the two-dimensional code area is obtained. Specifically, the packaging bag image of the unrecognizable two-dimensional code is grayscaled to obtain the grayscale image of the two-dimensional code, and then the grayscale image is input into the trained semantic segmentation network. The semantic segmentation network outputs a binary image of the grayscale image. Among them, in this binary image, the pixel points belonging to the two-dimensional code area are set to 1, and the pixel points belonging to the background area are set to 0. Further, the binary image is multiplied by its corresponding grayscale image to obtain a grayscale image containing only the two-dimensional code area.

[0037] By grayscaling the packaging bag image, the contrast and brightness of the unrecognizable packaging bag image are initially adjusted, which can improve the recognition rate of the two-dimensional code. Further, by segmenting out the grayscale image containing only the two-dimensional code area, the interference of the background area on the two-dimensional code recognition is avoided, thereby improving the recognition rate of the two-dimensional code and further improving the efficiency of warehouse management.

[0038] In one embodiment, the loss function of the semantic segmentation network is the cross-entropy loss function.

[0039] S102. Determine the first abnormal degree of the pixel points in the grayscale image.

[0040] In an ideal situation, only black and white exist in the two-dimensional code, corresponding to the two grayscale values of 0 and 255 respectively. However, during the actual photographing process, due to the existence of light, shadows, creases, etc., there may be other grayscale values in the photographed two-dimensional code image, thus causing certain interference to the recognition of the two-dimensional code. In addition, in an ideal situation, there are four gradient directions in the two-dimensional code image, that is, four mutually perpendicular directions, namely horizontally to the right (i.e., 0°), horizontally to the left (i.e., 180°), vertically upward (i.e., 90°), and vertically downward (i.e., 270°). However, in the actually obtained two-dimensional code image, these four gradient directions may not be completely perpendicular, thus also causing certain interference to the recognition of the two-dimensional code.

[0041] It should be noted that the gradient direction of the pixel points described in the present invention is represented by the angle with the horizontal to the right.

[0042] In view of the characteristic that in an ideal situation, a two-dimensional code has only two grayscale values, the grayscale value of each pixel point in the two-dimensional code is counted to obtain the grayscale histogram of the grayscale image. The two peaks with the largest values in the grayscale histogram are marked, and at the same time, the grayscale values where these two peaks are located are used as the main grayscale values. It can be understood that in an ideal situation, the two main grayscale values of the two-dimensional code image should be 0 and 255, that is, among all the grayscale values of the grayscale image, the two grayscale values with the largest proportions are 0 and 255.

[0043] It can be understood that in the grayscale histogram, the abscissa represents the grayscale value, and the ordinate represents the probability or frequency. Therefore, the difference between the two main grayscale values reflects the contrast of the grayscale image. Specifically, if the difference between the two main grayscale values is large, it indicates that there are obvious bright and dark parts in the grayscale image, that is, the contrast of the grayscale image is high. Then, when enhancing the contrast of the image subsequently, the degree of enhancement required is lower; if the difference between the two main grayscale values is small, it indicates that the difference between the bright and dark parts in the grayscale image is not obvious, that is, the contrast of the grayscale image is low. Then, when enhancing the contrast of the image subsequently, the degree of enhancement required is higher.

[0044] In one embodiment, according to the sobel operator, the gradient value and gradient direction of each pixel point in the grayscale image are obtained, and the gradient value histogram and gradient direction histogram are respectively drawn. Among them, in the gradient value histogram, the abscissa is the gradient value of the pixel point, and the ordinate is the frequency or probability; in the gradient direction histogram, the abscissa is the gradient direction of the pixel point, and the ordinate is the frequency or probability. Further, the gradient values corresponding to the two peaks with the largest values in the gradient value histogram are used as the main gradient values; the gradient directions corresponding to the four peaks with the largest values in the gradient direction histogram are used as the main gradient directions. It can be understood that in a grayscale image, there should be two main grayscale values, two main gradient values, and four main gradient directions.

[0045] Further, the grayscale value of any pixel point is obtained, and then the differences between the grayscale value of this pixel point and the two main grayscale values are calculated respectively. The main grayscale value with the smallest difference is used as the reference grayscale value of this pixel point; the gradient value of this pixel point is obtained, and then the differences between the gradient value of this pixel point and the two main gradient values are calculated respectively. The main gradient value with the smallest difference is used as the reference gradient value of this pixel point; the gradient direction of this pixel point is obtained, and then the differences between the gradient direction of this pixel point and the four main gradient directions are calculated respectively. The main gradient direction with the smallest difference is used as the reference gradient direction of this pixel point. For example, if the gradient direction of a pixel point is 3°, and the four main gradient directions are 0°, 91°, 178°, and 270° respectively, since the difference between the main gradient direction 0° and the gradient direction 3° of this pixel point is the smallest, therefore, the reference gradient direction of this pixel point is 0°.

[0046] Further, according to the grayscale value, gradient value, gradient direction, reference grayscale value, reference gradient value, and reference gradient direction of the pixel, calculate the first degree of abnormality of the pixel. Specifically, the calculation expression of the first degree of abnormality is as follows:

[0047] ;

[0048] In the formula, represents the first degree of abnormality of the pixel, , , respectively represent the grayscale value, gradient value, and gradient direction of the pixel. , , respectively represent the reference grayscale value, reference gradient value, and reference gradient direction of the pixel.

[0049] It can be seen from the above expression that when the differences between the grayscale value, gradient value, and gradient direction of the pixel and the reference grayscale value, reference gradient value, and reference gradient direction are larger, that is, , , are larger, the first degree of abnormality of the pixel is larger.

[0050] It should be noted here that ranges from 0 to 90°. This is because in an ideal situation, the four main gradient directions should be 0°, 90°, 180°, and 270°, and the angle between two adjacent main gradient directions is 90°. Therefore, the angle between the gradient direction of the pixel and its reference gradient direction ranges from 0 to 45°. However, due to the influence of the shooting angle, the angle between two adjacent main gradient directions may be greater than or less than 90°. When this angle is greater than 90°, its maximum will not reach 180°. Therefore, the angle between the gradient direction of the pixel and its reference gradient direction ranges from 0 to 90°.

[0051] Similarly, according to the above calculation expression of the first degree of abnormality, obtain the first degree of abnormality of all pixels in the grayscale image.

[0052] S103. Perform edge detection on the grayscale image and calculate the second degree of abnormality of the obtained target edge.

[0053] In one embodiment, use the canny edge detection algorithm to perform edge detection on the grayscale image, analyze each detected edge, and call the edge being analyzed the target edge. Perform anomaly detection on the first degree of abnormality of all pixels on the target edge through the isolation forest algorithm, and mark the abnormal pixels obtained.

[0054] Further, obtain the curvature of the unlabeled pixel points on the target edge, and record the case where the curvature does not exist as 0; determine the second abnormality degree of the target edge according to the mean value of the curvature of the unlabeled pixel points on the target edge and the mean value of the first abnormality degree, wherein the second abnormality degree is positively correlated with the average curvature of the pixel points on the target edge and the mean value of the first abnormality degree respectively. Specifically, the calculation expression of the second abnormality degree is as follows:

[0055] ;

[0056] In the formula, represents the second abnormality degree of the target edge, represents the total number of unlabeled pixel points on the target edge, represents the curvature of the th unlabeled pixel point on the target edge, represents the first abnormality degree of the th unlabeled pixel point on the target edge.

[0057] Among them, represents the average curvature of the target edge. If the average curvature of the target edge is small and close to 0, it indicates that the target edge is a straight line or the edge where the black and white areas of the QR code itself meet. This is because the edges of the QR code are regular, generally rectangular. Therefore, except for the turning points on the edge, the curvature of the remaining pixel points should be 0. In addition, the larger, the second abnormality degree of the target edge is larger, indicating that the target edge is more curved and less in line with the characteristics of the QR code edge.

[0058] Further, represents the mean value of the first abnormality degrees of all unlabeled pixel points on the target edge. The larger this value is, the second abnormality degree of the target edge is larger.

[0059] Since the pixel points on the same edge have the same or similar features, when the first abnormal degrees of most pixel points on the edge are relatively large, the few pixel points with relatively small first abnormal degrees may be caused by noise or coincidence; in addition, when the first abnormal degrees of most pixel points on the edge are relatively small, the few pixel points with relatively large first abnormal degrees may be caused by noise or corner points on the edge. These abnormal pixel points do not represent the edge features and will affect the accuracy of the subsequent calculation of the second abnormal degree. Therefore, when calculating the second abnormal degree of the target edge, by only involving normal pixel points, that is, unmarked pixel points, the accuracy of calculating the second abnormal degree of the target edge is improved, thereby improving the accuracy of subsequent determination of abnormal edges and further improving the recognition rate of the two-dimensional code.

[0060] S104. When the second abnormal value is greater than a preset threshold, filter the target edge.

[0061] Since shadows, foreign object occlusion, light spots, etc. can cause abnormalities in the edge, thereby affecting the recognition of the two-dimensional code, abnormal edges and their regions can be filtered to eliminate the abnormal edges, thereby improving the quality of the two-dimensional code image. Specifically, it can be determined whether the second abnormal value of the target edge is greater than a preset threshold. If so, it indicates that the target edge is an abnormal edge, and then the target edge is filtered. If not, it indicates that the target edge is a normal edge, and then the target edge is not filtered.

[0062] In one embodiment, the preset threshold can be 0.6. In other alternative embodiments, the preset threshold can also be 0.7.

[0063] Specifically, the abnormal edge can be filtered by means of mean filtering, median filtering, Gaussian filtering, etc. In one embodiment, the abnormal edge is subjected to mean filtering twice to achieve the purpose of eliminating the abnormal edge, that is, converting the abnormal edge into a normal edge. By converting the abnormal edge into a normal edge, the quality of the two-dimensional code image is improved, thereby improving the recognition rate of the two-dimensional code.

[0064] In one embodiment, during the first mean filtering, the perpendicular line of the connection line of the two pixel points with the farthest distance on the abnormal edge is used as the search direction; any pixel point on the abnormal edge is used as the target pixel point. Starting from the target pixel point, search on both sides according to the search direction. When an edge pixel point is encountered or the search distance is greater than a preset distance, stop the search; all the pixel points searched are formed into a filtering window of the target pixel point (excluding the searched edge pixel points), and then the target pixel point is subjected to mean filtering.

[0065] In the first mean filtering, by using the pixel points on the non-edge to filter the pixel points on the abnormal edge, the abnormal edge can be eliminated, thereby improving the quality of the grayscale image and further improving the recognition rate of the QR code. In one embodiment, the preset distance can be set to 20.

[0066] According to the above process, mean filtering is performed on each pixel point on the abnormal edge.

[0067] After the first mean filtering is completed, all the previous pixel points used as the filtering window jointly form a region covering the abnormal edge, and mean filtering is performed on this region according to the preset window. In one embodiment, the preset window can be set to a 3×3 window or a 5×5 window.

[0068] Through the second mean filtering operation, the problem of uneven connection between the abnormal edge and its surrounding pixel points that appears after the first mean filtering is solved, making the local area of the QR code relatively smooth, and at the same time not affecting the edge features existing in the QR code itself. Therefore, through two mean filterings, both the abnormal edge is eliminated and the unevenness problem caused by eliminating the abnormal edge is avoided, ensuring the elimination of the abnormal edge while the grayscale image is complete, improving the quality of the QR code image, and thus improving the recognition rate of the QR code.

[0069] S105. Enhance the contrast of the filtered image.

[0070] In an alternative embodiment, the success rate of QR code recognition can be improved by enhancing the contrast of the filtered image. Specifically, in this embodiment, the contrast of the filtered image can be improved by performing gamma transformation on the filtered image.

[0071] In one embodiment, the expression of gamma transformation is as follows:

[0072] ;

[0073] In the formula, represents the gray value of the grayscale image before enhancement, represents the gray value of the grayscale image after enhancement, and respectively represent the two main gray values of the grayscale image, where .

[0074] It should be noted that is the result of normalization, is the result of normalization.

[0075] In addition, when the difference between the two main gray values The smaller it is, the lower the contrast of the QR code area, and the higher the degree of enhancement required. Therefore, the smaller it is, the greater the degree of enhancement. When the difference between the two main gray values is greater, it indicates that the contrast of the QR code area is higher and the degree of enhancement required is lower. Therefore, the greater it is, the smaller the degree of enhancement. When the distance between the gray value and the nearest main gray value is farther, it indicates that the abnormality degree of this gray value is greater, because in the ideal state, this gray value should be equal to the nearest main gray value.

[0076] When the gray value is greater than , it indicates that this gray value is larger and the main gray value closest to this gray value is . At this time, the gamma coefficient is less than 1, which can increase this gray value, thereby enhancing the contrast of the image. Further, from the above expression, it can be seen that the greater it is, the greater the degree of increase for this gray value, so that the distance between this gray value and the main gray value H2 is closer, and the better the enhancement effect on the filtered image.

[0077] When the gray value is less than , it indicates that this gray value is smaller and the main gray value closest to this gray value is . If it is necessary to enhance the contrast of this gray image, then this gray value needs to be reduced. At this time, the gamma coefficient is greater than 1, which can reduce this gray value, thereby enhancing the contrast of the image. Further, from the above expression, it can be seen that the greater it is, the greater the degree of reduction for this gray value, so that the distance between this gray value and the main gray value is reduced more, and the better the enhancement effect on the filtered image.

[0078] Through the above gamma transformation, the contrast of the filtered image can be effectively enhanced, so that the image can be clearer, and then the QR code in the image can be recognized better, thus improving the recognition rate of the QR code.

[0079] S106. Perform QR code recognition based on the enhanced image, and perform warehousing management according to the recognized information.

[0080] After the QR code on the image of the goods packaging bag is recognized, the information of the goods can be obtained, and then the goods can be tracked and scheduled in real time, etc., ensuring high transparency of logistics and improving the efficiency of warehouse management. Specifically, the information obtained by recognizing the QR code clarifies the situation of goods inbound and outbound, realizes automated inventory management, reduces human errors, and lowers operating costs; the information obtained by recognition guides the storage of goods, etc., optimizes the warehouse operation process, and strengthens the security control of goods in combination with the anti-counterfeiting function. In addition, whether it is inbound, outbound or goods movement, it can quickly respond and update information, support real-time inventory checking, generate detailed data analysis and reports, optimize the inventory structure and inbound and outbound strategies, and comprehensively improve the efficiency and accuracy of warehouse management.

[0081] Figure 2 It schematically shows a structural block diagram of an intelligent warehouse management system for packaging bags based on QR codes according to this embodiment.

[0082] The present invention also provides an intelligent warehouse management system for packaging bags based on QR codes. As Figure 2 shown, the system includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, it realizes an intelligent warehouse management method for packaging bags based on QR codes according to the first aspect of the present invention.

[0083] The system also includes other components well known to those skilled in the art such as a communication interface, and its settings and functions are known in the art, so they will not be described in detail here.

[0084] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as, resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that can be stored or otherwise held by such a computer-readable medium.

[0085] Although this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many changes, variations, and alternative ways will occur to those skilled in the art without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. An intelligent warehousing management method for packaging bags based on two-dimensional codes, characterized in that, Including: Preprocess the packaging bag image that cannot recognize the QR code to obtain a grayscale image containing only the QR code area; Determine the first abnormal degree of the pixel points in the grayscale image, and the calculation expression of the first abnormal degree is: ； Wherein, represents the first outlier of the pixel point, , , respectively represent the gray value, gradient value, and gradient direction of the pixel point, , , respectively represent the reference gray value, reference gradient value, and reference gradient direction of the pixel point; Perform edge detection on the grayscale image and calculate the second abnormal degree of the target edge. Among them, the second abnormal degree is positively correlated with the average curvature of the pixel points on the target edge and is also positively correlated with the mean value of the first abnormal degree; When the second abnormal degree is greater than the preset threshold, filter the target edge; Perform QR code recognition based on the image obtained after filtering, and perform warehouse management according to the recognized information.

2. The intelligent warehousing management method for packaging bags based on two-dimensional codes according to claim 1, wherein, Preprocess the packaging bag image that cannot recognize the QR code, including: converting the packaging bag image that cannot recognize the QR code into a grayscale image, and segmenting the grayscale image according to the semantic segmentation network.

3. The intelligent warehousing management method for packaging bags based on two-dimensional codes according to claim 1, characterized in that, Perform edge detection on the grayscale image and calculate the second abnormal degree of the target edge, including: Perform abnormal detection on the first abnormal degree of the pixel points on the target edge, and mark the obtained abnormal pixel points; Obtain the curvature of the unmarked pixel points, and determine the second abnormal degree according to the mean value of the curvature of the unmarked pixel points and the mean value of the first abnormal degree.

4. The intelligent warehousing management method for packaging bags based on two-dimensional codes according to claim 3, characterized in that The calculation expression of the second abnormal degree is as follows: ； In the formula, represents the second abnormal degree of the target edge, represents the total number of unmarked pixel points on the target edge, represents the curvature of the th unmarked pixel point on the target edge, and represents the first abnormal degree of the th unmarked pixel point on the target edge.

5. The intelligent warehousing management method for packaging bags based on two-dimensional codes according to claim 1, wherein, Filter the target edge, including: Use the perpendicular line of the connection line between the two pixel points with the farthest distance on the target edge as the search direction; Starting from the target pixel point on the target edge, search to both sides according to the search direction, and stop searching when encountering edge pixel points or the search distance is greater than the preset distance; Form the filtering window of the target pixel point with all the pixel points searched, and perform mean filtering on the target pixel point.

6. The method for intelligent warehousing management of packaging bags based on two-dimensional codes according to claim 5, wherein, Also including: Form a region covering the target edge with all the pixel points serving as the filtering window, and perform mean filtering on the region according to the preset window.

7. The intelligent warehousing management method for packaging bags based on two-dimensional codes according to claim 1, wherein, Before performing QR code recognition, it also includes: enhancing the contrast of the image after filtering.

8. The method for intelligent warehouse management of packaging bags based on two-dimensional codes according to claim 7, wherein Enhance the contrast of the image after filtering, including: performing gamma transformation on the image after filtering: ； In the formula, represents the gray value before the enhancement of the grayscale image, represents the gray value after the enhancement of the grayscale image, and respectively represent the two gray values with the largest proportions among all the gray values of the grayscale image before filtering, where .

9. An intelligent warehousing management system for packaging bags based on two-dimensional codes, characterized in that, Including: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent warehouse management method for packaging bags based on QR codes according to any one of claims 1-8 is implemented.

Images