Finished shoe tax calculation method, device and equipment and storage medium

Abstract

The embodiment of the invention provides a finished shoe tax calculation method and device, equipment and a storage medium, and the method specifically comprises the steps: obtaining the vamp picture data of a finished shoe, and carrying out the extraction according to the vamp picture data of the finished shoe, and obtaining a convolution input feature map of a specific region; wherein the vamp picture data of the finished shoe is obtained by paving and shooting a cut vamp through a box body with the inner wall being a reflective surface and the outer part being a shading material; obtaining a vamp material area proportion according to the convolution input feature map of the specific region; and obtaining the shoe export tax according to the area ratio of the vamp material. By automatically calculating the area ratio of each material, the problems of long time consumption and low efficiency in the prior art are solved, and the effects of being simple to operate, improving the working efficiency, saving the time and improving the accuracy are achieved. And the vamp material and occupied surface area AI identification software realizes automatic identification and segmentation of the vamp material and the occupied surface area by combining image features and prompt information.

Description

Technical Field

[0001] The present invention relates to the field of calculation, and in particular to a method, device, equipment and storage medium for calculating tariffs on finished shoes. Background Art

[0002] As international trade becomes more and more developed, as an industrial power, my country's annual export volume of various products is also very considerable, and footwear products have maintained a stable output. The calculation of export tariffs on footwear products is closely related to the shoe type and the proportion of various materials in the finished shoe, so the calculation of the area percentage of various materials in the upper and outsole of each shoe type is particularly important.

[0003] The prior art is to use a printer and Photoshop image processing software in combination. The specific usage is: first cut the entire shoe upper along the adhesive line, then scan it into a picture format, and then import it into Photoshop image processing software, draw lines along the edges of different materials and distinguish them, and then use Photoshop image processing software to calculate the area of ​​each material, and then calculate the percentage of each material in the total area.

[0004] However, the existing technology requires a lot of manual work, takes a lot of time, and is difficult to improve work efficiency; when there is a deviation from the actual shape of the finished shoe and the curvature of the sample is relatively large, the deviation will be large and the accuracy will be low. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a method, device, equipment and storage medium for calculating tariffs on finished shoes that overcome the above problems or at least partially solve the above problems, including:

[0006] A method for calculating tariffs on finished shoes, the method being used to calculate export tariffs on shoes by calculating the proportion of upper materials, comprising:

[0007] Acquire the upper image data of the finished shoe, and extract the convolution input feature map of the specific area according to the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material;

[0008] Obtaining the proportion of the upper material area according to the convolution input feature map of the specific area;

[0009] The export tariff of shoes is obtained based on the proportion of the upper material area.

[0010] Preferably, the step of extracting a convolution input feature map of a specific area based on the finished shoe upper image data comprises:

[0011] Extracting features based on the finished shoe upper image data to obtain image features;

[0012] Mask conversion is performed based on the image features to obtain a convolution input feature map of a specific area.

[0013] Preferably, the step of extracting features based on the finished shoe upper image data to obtain image features includes:

[0014] Formatting the finished upper image data to obtain formatted upper data;

[0015] Feature extraction is performed based on the formatted upper data to obtain image features.

[0016] Preferably, the step of obtaining the proportion of the upper material area according to the convolution input feature map of the specific area includes:

[0017] Encoding the convolution input feature map of the specific area to obtain a square area;

[0018] Cutting the square area to obtain a segmented image;

[0019] The proportion of the upper material area is obtained according to the segmented image.

[0020] Preferably, the step of obtaining a segmented image by cutting the square area comprises:

[0021] Performing dynamic mask prediction according to the square area to obtain a pre-segmented image;

[0022] Adjustment is performed according to the pre-segmented image to obtain a segmented image.

[0023] Preferably, the step of performing dynamic mask prediction based on the square area to obtain a pre-segmented image comprises:

[0024] According to the square area, points and boxes are encoded by position encoding to obtain a mask;

[0025] A pre-segmented image is obtained according to the mask.

[0026] To implement this application, a device for calculating tariffs on finished shoes is also provided. The device is used to calculate export tariffs on shoes by calculating the proportion of upper materials, including:

[0027] A convolution input feature map module is used to obtain the upper image data of the finished shoe, and extract the convolution input feature map of a specific area according to the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material;

[0028] A shoe upper material area ratio module, used to obtain the shoe upper material area ratio according to the convolution input feature map of the specific area;

[0029] The shoe export tariff module is used to obtain the shoe export tariff according to the proportion of the upper material area.

[0030] Preferably, the convolution input feature map module comprises:

[0031] An image feature submodule, used for extracting features based on the finished shoe upper image data to obtain image features;

[0032] The specific area submodule is used to perform mask conversion according to the image features to obtain a convolution input feature map of the specific area.

[0033] To implement the present application, an electronic device is also included, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the steps of the method for calculating tariffs based on finished shoes are implemented.

[0034] To implement the present application, a computer-readable storage medium is also included, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for calculating tariffs based on finished shoes are implemented.

[0035] This application has the following advantages:

[0036] In the embodiments of the present application, in view of the "long time and low efficiency" in the prior art, the present application provides a solution for automatically calculating the area ratio of each material, specifically: obtaining the upper image data of the finished shoe, and extracting the convolution input feature map of the specific area based on the finished shoe upper image data; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper through a box body made of a reflective surface on the inner wall and a light-shielding material on the outer wall; obtaining the upper material area ratio based on the convolution input feature map of the specific area; obtaining the shoe export tariff based on the upper material area ratio. The problem of long time and low efficiency in the prior art is solved by automatically calculating the area ratio of each material, achieving the effect of simple operation, improving work efficiency, saving time and improving accuracy. The AI ​​recognition software for upper materials and surface area realizes the automatic recognition and segmentation of upper materials and surface area by combining image features and prompt information. The Transformer-based model has strong generalization ability and flexibility, and can adapt to various segmentation tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 It is a flow chart of a method for calculating tariffs on finished shoes provided in one embodiment of the present application;

[0039] Figure 2 It is a structural block diagram of a finished shoe tariff calculation device provided by an embodiment of the present application;

[0040] Figure 3 It is a schematic diagram of a device for calculating tariffs on finished shoes provided in one embodiment of the present application;

[0041] Figure 4 This is a tariff calculation chart for finished shoes provided in one embodiment of the present application;

[0042] Figure 5 It is a tariff calculation chart for calculating tariffs on finished shoes provided in one embodiment of the present application;

[0043] Figure 6 is a structural schematic diagram of a computer device provided by an embodiment of the present invention;

[0044] Figure 7 This is a calculation principle diagram of tariff calculation for finished shoes provided in one embodiment of the present application;

[0045] 1. Camera; 2. Box; 3. Sample; 12. Computer equipment; 14. External device; 16. Processing unit; 18. Bus; 20. Network adapter; 22. I / O interface; 24. Display; 28. Memory; 30. Random access memory; 32. Cache memory; 34. Storage system; 40. Program / utility; 42. Program module. DETAILED DESCRIPTION

[0046] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0047] The inventors found through analyzing the prior art that the prior art is to use a printer and Photoshop (image processing software) in combination. The specific usage is: first cut the entire shoe upper along the adhesive line, then scan it into a picture format, and then import it into Photoshop, draw lines along the edges of different materials and distinguish them, and then use Photoshop to calculate the area of ​​each material. The tester then calculates the percentage of each material in the total area based on the calculation results.

[0048] The existing technology has the following disadvantages:

[0049] Outlining is done in different areas according to different materials. Especially when encountering densely distributed diamond decorations, each decoration needs to be outlined and separated to calculate the area. The workload is very large and time-consuming, and it is difficult to improve work efficiency;

[0050] The upper of a finished shoe will have a certain curvature, and the outsole will have a certain thickness, but ordinary printers can only perform flat scanning, which will deviate from the actual shape of the finished shoe. For samples with thinner uppers and soles, the accuracy of the final calculation results of the existing method will be very close, but for samples with thicker uppers and soles and larger curvatures, the deviation may be slightly larger, and there is still room for improvement in accuracy.

[0051] This application provides a solution to solve the problems of the prior art. The software of this application has a set of mature algorithms that can quickly analyze and calculate the area of ​​each region;

[0052] AI capabilities can quickly collect sample data for various upper materials and mark targets for static data sets. Through continuous learning and training in the later stage, it can more accurately analyze different materials and areas, and perform more precise calculations. There is a professional camera that can quickly scan the entire upper or sole. There is a box environment specifically used for scanning. The inner wall of the box is a reflective surface, the whole is made of light-shielding material, and there is a professional light source inside the box.

[0053] The purpose of the present invention is to solve the problem of long time and low efficiency while greatly improving the accuracy.

[0054] In the embodiments of the present application, in view of the "long time and low efficiency" in the prior art, the present application provides a solution for automatically calculating the area ratio of each material, specifically: obtaining the upper image data of the finished shoe, and extracting the convolution input feature map of the specific area based on the finished shoe upper image data; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper through a box body made of a reflective surface on the inner wall and a light-shielding material on the outer wall; obtaining the upper material area ratio based on the convolution input feature map of the specific area; obtaining the shoe export tariff based on the upper material area ratio. The problem of long time and low efficiency in the prior art is solved by automatically calculating the area ratio of each material, achieving the effect of simple operation, improving work efficiency, saving time and improving accuracy. The AI ​​recognition software for upper materials and surface area realizes the automatic recognition and segmentation of upper materials and surface area by combining image features and prompt information. The Transformer-based model has strong generalization ability and flexibility, and can adapt to various segmentation tasks.

[0055] Reference Figure 1 , shows a flowchart of a method for calculating tariffs on finished shoes provided in an embodiment of the present application, which specifically includes the following steps:

[0056] S110, obtaining image data of the upper of a finished shoe, and extracting a convolution input feature map of a specific area based on the image data of the upper of the finished shoe; wherein the image data of the upper of the finished shoe is obtained by flattening and photographing the cut upper of a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material;

[0057] S120, obtaining the proportion of the upper material area according to the convolution input feature map of the specific area;

[0058] S130. Obtain the export tariff of shoes according to the proportion of the upper material area.

[0059] Next, the method for calculating the tariff based on finished shoes in this exemplary embodiment will be further described.

[0060] As described in the above step S110, the upper image data of the finished shoe is obtained, and the convolution input feature map of the specific area is extracted based on the upper image data of the finished shoe; wherein, the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material.

[0061] In one embodiment of the present invention, the specific process of "obtaining the upper image data of the finished shoe, and extracting the convolution input feature map of the specific area based on the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material;" can be further explained in combination with the following description.

[0062] As described in the following steps, feature extraction is performed based on the finished shoe upper image data to obtain image features; mask conversion is performed based on the image features to obtain a convolution input feature map of a specific area.

[0063] In one embodiment of the present invention, the specific process of the step of "extracting features based on the finished shoe upper image data to obtain image features" can be further explained in combination with the following description.

[0064] As described in the following steps, formatting is performed based on the finished upper image data to obtain formatted upper data; and feature extraction is performed based on the formatted upper data to obtain image features.

[0065] In a specific embodiment, a shoe image is input, and an Imageencode operation is performed on the shoe image using a Vit model to obtain an image embedding.

[0066] Image encoder:

[0067] Input: The default is a 1024x1024 shoe image. If the size is inconsistent, the original image will be resized according to the longest side.

[0068] Output: 1x256x64x64 image embedding of a single image, i.e. the encoded shoe image features.

[0069] In a specific embodiment, a masked convolution layer is obtained by performing mask conv on the image embedding: the image_embeddings of the shoe are obtained through the image encoder, and then the different features of the input shoe image (edges, lines, etc.) are extracted through the masked convolution layer (MaskedConvolution) operation to obtain the convolution input feature map of the specific area of ​​the shoe.

[0070] As described in the above step S120, the upper material area ratio is obtained according to the convolution input feature map of the specific area.

[0071] In one embodiment of the present invention, the specific process of "obtaining the proportion of the upper material area according to the convolution input feature map of the specific area" in step S120 can be further explained in combination with the following description.

[0072] As described in the following steps, encoding is performed based on the convolution input feature map of the specific area to obtain a square area; cutting is performed based on the square area to obtain a segmented image; and the proportion of the upper material area is obtained based on the segmented image.

[0073] As an example, a square area is obtained by encoding the convolution input feature map of the specific area, and the user input prompt is encoded or convolutionally encoded using the CLIP model to obtain prompt encode: the user inputs the prompt, and the CLIP model compares the vector relationship between the shoe image and the instruction, learns the matching relationship between the two, and realizes the mutual understanding of the image and the input instruction. In the interface, the user manually selects the area that needs to be recognized by AI, and the CLIP model will calculate and determine a square area, and then accurately select a square area.

[0074] In an embodiment of the present invention, the specific process of the step of "cutting the square area to obtain a segmented image" can be further explained in combination with the following description.

[0075] As described in the following steps, dynamic mask prediction is performed based on the square area to obtain a pre-segmented image; and adjustment is performed based on the pre-segmented image to obtain a segmented image.

[0076] As an example, the segmented image is obtained by adjusting according to the pre-segmented image. Specifically, if the output mask does not meet the requirements, the prompt can be adjusted and the third step can be repeated until a suitable mask is obtained. If the obtained shoe segmentation image does not meet the requirements, it needs to be adjusted. The user inputs the prompt and uses the CLIP model for re-encoding or convolution encoding to obtain an accurate segmented shoe image.

[0077] Select the required mask and obtain the area of ​​the required region through the CV library: For each segmented shoe image, read the shoe image through the Cv2.imread() function in the CV library, read the relevant contours through the cv2.findcontours function, and then calculate its area.

[0078] In an embodiment of the present invention, the specific process of the step of "performing dynamic mask prediction according to the square area to obtain a pre-segmented image" can be further explained in combination with the following description.

[0079] As described in the following steps, points and boxes are encoded by position encoding according to the square area to obtain a mask; and a pre-segmented image is obtained according to the mask.

[0080] As an example, the mask decoder performs dynamic mask prediction on the mask convolutional layer and prompt encoder to upsample the image code and output each mask and mask probability.

[0081] Specifically, the shoe image is segmented through the mask decoder and the prompt encoder, and the segmentation prompt is performed using the following conditions:

[0082] 1. Points - A set of points associated with the object that should be segmented. The Prompt encoder converts the points into embedded values ​​using positional encoding.

[0083] 2. Boxes - The bounding box that the object should be segmented in. Similar to points, the coordinates of the bounding box are encoded using position encoding.

[0084] 3. Segmentation Mask - The segmentation mask provided by the user is embedded using convolution and element-wise summed with the image embedding.

[0085] 4. Text - text representation encoded by the CLIP model.

[0086] The system identifies the upper part within the square area and obtains its outer contour, ultimately segmenting the various parts of the shoe shape image.

[0087] As described in the above step S130, the shoe export tariff is obtained according to the proportion of the upper material area.

[0088] In an embodiment of the present invention, the specific process of "obtaining the shoe export tariff according to the proportion of the upper material area" in step S130 can be further explained in combination with the following description.

[0089] As described in the following steps, the export tariff of shoes is calculated based on the area ratio of the upper material and the customs tariff, as follows: Figure 4 and Figure 5 shown.

[0090] In a specific embodiment, the upper of the finished shoe is cut along the adhesive line, and the upper is placed on the scanning platform in the box 2 as flat as possible with the upper facing upwards. The device is turned on, the software is started, and the sample 3 is scanned by the camera 1. After the scanning is completed, the software automatically marks the areas according to different colors or materials. The tester determines whether the software marking is correct based on the actual material of the sample 3. If there is an error, it needs to be adjusted. After the adjustment is completed, it is confirmed. The software will analyze and calculate according to the marked area. Finally, the calculation result can be read. Figure 3 shown.

[0091] In a specific embodiment, in the first step, a picture is input, and an Imageencode operation is performed on the picture using a Vit model to obtain an image embedding.

[0092] In the second step, the masked convolution layer is obtained by performing mask conv on the image embedding.

[0093] The third step is to encode or convolutionally encode the user input prompt using the CLIP model to obtain promptencode.

[0094] In the fourth step, the mask decoder performs dynamic mask prediction on the mask convolution layer and prompt encoder, upsamples the image code, and outputs each mask and mask probability.

[0095] Step 5: If the output mask does not meet the requirements, you can adjust the prompt and repeat step 3 until a suitable mask is obtained.

[0096] Step 6. Select the required mask and obtain the area of ​​the required region through the CV library.

[0097] In a specific embodiment, the upper material and surface area AI recognition software is a Transformer-based model for image segmentation tasks. It generates high-quality object masks by combining images and prompts. The core idea is to use a general visual model to recognize and segment any object in the image.

[0098] The main components of the AI ​​recognition software for upper materials and surface area include:

[0099] A backbone network for extracting image features. This network is usually a pre-trained convolutional neural network (CNN) such as ResNet or Vision Transformer (ViT).

[0100] A hint encoder that encodes the user input hint (such as a text label or a bounding box) into a vector representation. This encoder can be a simple linear layer or a more complex structure such as a recurrent neural network (RNN) or a Transformer.

[0101] A segmentation head is used to fuse the image features and the vector representation output by the hint encoder to generate the final segmentation mask. This head is usually a lightweight neural network such as a convolutional neural network (CNN) or a fully connected layer.

[0102] During the training process, AI recognition software uses a large amount of labeled image data for supervised learning. The training goal is usually to minimize the difference between the predicted mask and the true mask, such as using the cross entropy loss function. In addition, SAM can also use unlabeled data for self-supervised learning to improve the generalization ability of the model.

[0103] In the inference phase, the AI ​​recognition software first extracts the features of the input image and then generates corresponding segmentation masks based on the prompts provided by the user. These masks can be used for various applications such as object detection, instance segmentation, and semantic segmentation.

[0104] In short, the shoe upper material and surface area AI recognition software realizes automatic recognition and segmentation of shoe upper materials and surface area by combining image features and prompt information. This Transformer-based model has strong generalization ability and flexibility and can adapt to various segmentation tasks, such as Figure 7 shown.

[0105] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0106] Reference Figure 2 , shows a tariff calculation device based on finished shoes provided by an embodiment of the present application, which specifically includes the following modules:

[0107] Convolution input feature map module: used to obtain the upper image data of the finished shoe, and extract the convolution input feature map of the specific area according to the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material;

[0108] The shoe upper material area ratio module is used to obtain the shoe upper material area ratio according to the convolution input feature map of the specific area;

[0109] Shoe export tariff module: used to obtain shoe export tariff according to the proportion of the upper material area.

[0110] In one embodiment of the present invention, the convolution input feature map module includes:

[0111] An image feature submodule, used for extracting features based on the finished shoe upper image data to obtain image features;

[0112] The specific area submodule is used to perform mask conversion according to the image features to obtain a convolution input feature map of the specific area.

[0113] In one embodiment of the present invention, the image feature submodule includes:

[0114] A format upper data submodule, used for formatting the finished upper image data to obtain format upper data;

[0115] The image feature extraction submodule is used to extract features based on the formatted upper data to obtain image features.

[0116] In one embodiment of the present invention, the upper material area proportion module includes:

[0117] A square region submodule, used for encoding a square region according to a convolution input feature map of the specific region;

[0118] A segmented image submodule, used for cutting the square area to obtain a segmented image;

[0119] The upper material area submodule is used to obtain the upper material area ratio according to the segmented image.

[0120] In one embodiment of the present invention, the image segmentation submodule includes:

[0121] A pre-segmented image submodule, used for performing dynamic mask prediction based on the square area to obtain a pre-segmented image;

[0122] The adjustment submodule is used to adjust the pre-segmented image to obtain a segmented image.

[0123] In one embodiment of the present invention, the module includes:

[0124] An encoding submodule, used for encoding points and boxes according to the square area through position encoding to obtain a mask;

[0125] The mask submodule is used to obtain a pre-segmented image according to the mask.

[0126] Reference Figure 6 , showing a computer device based on the method for calculating tariffs on finished shoes of the present application, which may specifically include the following:

[0127] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 connecting different system components (including the memory 28 and the processing unit 16).

[0128] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, an Audio Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0129] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0130] Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 6 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of the various embodiments of the present application.

[0131] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0132] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable an operator to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through the I / O interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) through a network adapter 20. Figure 6 As shown, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0133] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28, such as implementing a method for calculating tariffs based on finished shoes provided in an embodiment of the present application.

[0134] That is, when the processing unit 16 executes the program, the following is achieved: acquiring the upper image data of the finished shoe, and extracting the convolution input feature map of the specific area based on the upper image data; wherein the upper image data of the finished shoe is acquired by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a shading material; obtaining the proportion of the upper material area based on the convolution input feature map of the specific area; and obtaining the export tariff of the shoe based on the upper material area proportion.

[0135] In an embodiment of the present application, the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a method for calculating tariffs based on finished shoes as provided in all embodiments of the present application is implemented.

[0136] That is, when the program is executed by the processor, it is implemented as follows: obtaining the upper image data of the finished shoe, and extracting the convolution input feature map of the specific area based on the finished shoe upper image data; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box with a reflective inner wall and a shading outer wall; obtaining the proportion of the upper material area based on the convolution input feature map of the specific area; and obtaining the export tariff of the shoe based on the upper material area proportion.

[0137] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0138] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the operator's computer, partially on the operator's computer, as an independent software package, partially on the operator's computer, partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the operator's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0140] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0141] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0142] The above is a detailed introduction to the method, device, equipment and storage medium for calculating tariffs on finished shoes provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes, and the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for calculating the tariff on finished shoes, the method being used to calculate the export tariff on shoes by calculating the proportion of upper materials, characterized in that: include: Acquire the upper image data of the finished shoe, and extract the convolution input feature map of the specific area according to the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material; Obtaining the proportion of the upper material area according to the convolution input feature map of the specific area; The export tariff of shoes is obtained based on the proportion of the upper material area.

2. The method for calculating tariffs on finished shoes according to claim 1, characterized in that: The step of extracting the convolution input feature map of a specific area based on the finished shoe upper image data comprises: Extracting features based on the finished shoe upper image data to obtain image features; Mask conversion is performed based on the image features to obtain a convolution input feature map of a specific area.

3. The method for calculating tariffs on finished shoes according to claim 2, characterized in that: The step of extracting features based on the finished shoe upper image data to obtain image features includes: Formatting the finished upper image data to obtain formatted upper data; Feature extraction is performed based on the formatted upper data to obtain image features.

4. The method for calculating tariffs on finished shoes according to claim 1, characterized in that: The step of obtaining the proportion of the upper material area according to the convolution input feature map of the specific area includes: Encoding the convolution input feature map of the specific area to obtain a square area; Cutting the square area to obtain a segmented image; The proportion of the upper material area is obtained according to the segmented image.

5. The method for calculating the tariff of finished shoes according to claim 4, characterized in that: The step of obtaining a segmented image by cutting the square area comprises: Performing dynamic mask prediction according to the square area to obtain a pre-segmented image; Adjustment is performed according to the pre-segmented image to obtain a segmented image.

6. The method for calculating the tariff of finished shoes according to claim 5, characterized in that: The step of performing dynamic mask prediction based on the square area to obtain a pre-segmented image comprises: According to the square area, points and boxes are encoded by position encoding to obtain a mask; A pre-segmented image is obtained according to the mask.

7. A device for calculating the tariff of finished shoes, which is used to calculate the export tariff of shoes by calculating the proportion of upper materials, characterized in that: include: A convolution input feature map module is used to obtain the upper image data of the finished shoe, and extract the convolution input feature map of a specific area according to the upper image data of the finished shoe; wherein the upper image data of the finished shoe is obtained by flattening and photographing the cut upper in a box whose inner wall is a reflective surface and whose outer wall is a light-shielding material; A shoe upper material area ratio module, used to obtain the shoe upper material area ratio according to the convolution input feature map of the specific area; The shoe export tariff module is used to obtain the shoe export tariff according to the proportion of the upper material area.

8. The finished shoe tariff calculation device according to claim 7, characterized in that: The convolution input feature map module includes: An image feature submodule, used for extracting features based on the finished shoe upper image data to obtain image features; The specific area submodule is used to perform mask conversion according to the image features to obtain a convolution input feature map of the specific area.

9. An electronic device, characterized in that The method comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the method for calculating tariffs based on finished shoes as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for calculating tariffs based on finished shoes according to any one of claims 1 to 6 are implemented.

Images