Clothing image library establishment method and device, target identification method and device, equipment and medium
By establishing a clothing image library, using the data correlation between seller and buyer in the shopping platform, the association relationship between non-standard data of clothing and standard data is determined, which solves the problem of low local clothing feature recognition efficiency and improves recognition accuracy and efficiency.
Patent Information
- Application Number
- CN202310536890.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-11
- Publication Date
- 2024-11-12
AI Technical Summary
In the process of human body recognition, the recognition efficiency and reliability based on local clothing features are low, resulting in large investment in human resources and inaccurate recognition results.
By establishing a clothing image library, using the seller display clothing links on the shopping platform to establish identification information and candidate reference clothing standard data, as well as the feedback pictures in the buyer feedback information as candidate reference clothing non-standard data, determine the non-standard data of the clothing to be matched and The target refers to the association relationship of the standard data of clothing, and then the target personnel are identified.
It improves the recognition efficiency and recognition accuracy of target personnel, reduces the acquisition cost of clothing image library, and enhances the authenticity of data.
Smart Images

Figure CN118939824A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to the establishment of a clothing image library, a target recognition method, a device, a equipment and a medium. Background Art
[0002] Currently, human body recognition is used in many scenarios. When performing human body recognition, facial features, body features, and clothing features of a person can be used. When determining a person to be recognized, only a partial image of the person can be obtained, such as a back or side image. At this time, the person to be recognized can only be recognized based on the partial clothing features in the partial image.
[0003] At present, when identifying people based on their local clothing features, the commonly used technical means is to compare clothing features and then perform manual comparison. However, since the local clothing features are not obvious, the clothing comparison results are often inaccurate, resulting in large human resource investment and low recognition efficiency and reliability. Summary of the invention
[0004] The present invention provides a method, device, equipment and medium for establishing a clothing image library, and target recognition, so as to solve the problems of low reliability of recognition results and low recognition efficiency when target personnel are recognized based on local clothing features.
[0005] According to one aspect of the present invention, a method for establishing a clothing image library is provided, wherein the method comprises:
[0006] Establish identification information for each seller displaying clothing links on the shopping platform;
[0007] Using the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information;
[0008] The feedback picture in the buyer feedback information in the seller display clothing link is used as candidate reference clothing non-standard data associated with the identification information.
[0009] According to another aspect of the present invention, a method for identifying a target person based on clothing is provided, wherein the method comprises:
[0010] Obtain non-standard data of clothing to be matched of the target person;
[0011] According to the matching result of the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data in the pre-established clothing image library, target reference clothing standard data associated with the to-be-matched clothing non-standard data is determined; wherein the clothing image library includes the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data determined according to the shopping behavior; the association relationship is determined according to the method for establishing the clothing image library described in any embodiment of the present invention;
[0012] A target complete image of the target person is acquired from the image to be identified according to the target reference clothing standard data.
[0013] According to another aspect of the present invention, a device for establishing a clothing image library is provided, characterized in that it comprises:
[0014] A clothing identification creation module is used to create identification information for each seller in the shopping platform to display clothing links;
[0015] A reference clothing standard data determination module, configured to use the display image in the seller's display clothing link as candidate reference clothing standard data associated with the identification information;
[0016] The first reference clothing non-standard data determining module is used to use the feedback picture in the buyer feedback information in the seller display clothing link as the candidate reference clothing non-standard data associated with the identification information.
[0017] According to another aspect of the present invention, a clothing-based target person recognition device is provided, characterized in that it comprises:
[0018] A clothing non-standard data acquisition module is used to acquire the non-standard clothing data to be matched of the target person;
[0019] a clothing standard data determination module, configured to determine target reference clothing standard data associated with the clothing non-standard data to be matched based on a matching result between the clothing non-standard data to be matched and candidate reference clothing non-standard data in a pre-established clothing image library; wherein the clothing image library includes an association relationship between candidate reference clothing non-standard data and candidate reference clothing standard data determined based on shopping behavior; the association relationship is determined according to the clothing image library establishment device described in any embodiment of the present invention;
[0020] The person standard data determination module is used to obtain a target complete image of the target person from the image to be identified based on the target reference clothing standard data.
[0021] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0022] at least one processor; and
[0023] a memory communicatively connected to the at least one processor; wherein,
[0024] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the clothing-based target person recognition method or clothing image library establishment method described in any embodiment of the present invention.
[0025] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the clothing-based target person recognition method or clothing image library establishment method described in any embodiment of the present invention when executed.
[0026] The technical solution of the embodiment of the present invention predetermines the association relationship between candidate reference clothing non-standard data and candidate reference clothing standard data through daily shopping behavior, and determines the associated clothing standard data for the clothing non-standard data through the association relationship, and then identifies the target person according to the clothing standard data, thereby solving the problem of low efficiency and low reliability of personnel identification only through local features of clothing, and improving the recognition efficiency and recognition accuracy of the target person.
[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0029] Figure 1 is a flow chart of a method for establishing a clothing image library provided according to Embodiment 1 of the present invention;
[0030] Figure 2 is a flowchart of a method for identifying a target person based on clothing provided according to Embodiment 2 of the present invention;
[0031] Figure 3 is a structural schematic diagram of a device for establishing a clothing image library provided according to Embodiment 3 of the present invention;
[0032] Figure 4is a structural schematic diagram of a clothing-based target person recognition device provided according to a fourth embodiment of the present invention;
[0033] Figure 5 It is a structural schematic diagram of an electronic device for implementing the clothing-based target person recognition method or clothing image library establishment method of an embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0035] It should be noted that the terms "candidate", "target", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0036] Embodiment 1
[0037] Figure 1 This is a flow chart of a method for establishing a clothing image library provided in the first embodiment of the present invention. This embodiment is a detailed description of the establishment of the clothing image library in the above embodiment. Figure 1 As shown, the method includes:
[0038] S110, establishing identification information for each seller in the shopping platform to display clothing links.
[0039] Each clothing link displayed by each seller in each shopping platform is used as a candidate reference clothing, and unique identification information is established for the candidate reference clothing. Exemplarily, a unique number is established for each clothing item on the shopping platform as its identification information.
[0040] S120: Use the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information.
[0041] The shopping platform may be an online shopping platform of various brand merchants or a comprehensive shopping website or shopping APP, etc., and the candidate reference clothing standard data is determined from clothing pictures in clothing links displayed by sellers on various shopping platforms.
[0042] Specifically, the links of clothing displayed by sellers are obtained from various shopping platforms, and each link is used as a candidate reference clothing. Since most of the clothing displayed by sellers are full-body effect pictures of models, the images in the links of clothing displayed by sellers are used as the standard data of candidate reference clothing. For example, the homepage image of each product displayed in the shopping app is obtained as the standard data of candidate reference clothing for the product.
[0043] Exemplarily, Table 1 shows the association relationship between candidate reference clothing standard data and identification information of seller display clothing links.
[0044] Table 1
[0045] Link Number Candidate reference clothing standard data number Image storage path 00001 000001 XXXX 00001 000002 XXXX 00001 000003 XXXX
[0046] Among them, the link number is used to distinguish the clothing links displayed by the seller, each candidate reference clothing is associated with at least one candidate reference clothing standard data, and identification number information is established for the candidate reference clothing standard data under each link number, and the image storage path identifies the storage path of the candidate reference clothing standard data corresponding to the number, so that the image can be retrieved according to the storage path.
[0047] S130: Use the feedback picture in the buyer's feedback information in the seller's clothing display link as candidate reference clothing non-standard data associated with the identification information.
[0048] Since sellers mostly display the overall effect of clothes when displaying them, and buyers mostly provide feedback on parts of the clothes when purchasing clothes, such as the side, back, and clothing pattern features, when determining the candidate reference clothing non-standard data associated with the candidate reference clothing standard data, it can be obtained from the feedback pictures in the buyer feedback information in the acquisition link of the candidate reference clothing standard data.
[0049] Exemplarily, the clothing image information in the buyer's reality show picture in the seller's display clothing link is obtained as the candidate reference clothing non-standard data associated with the candidate reference clothing standard data obtained from the link. For example, since there may be other images unrelated to the clothing in the buyer's reality show picture, before determining the candidate reference clothing non-standard data, the buyer's reality show picture is matched with the candidate reference clothing standard data in the seller's display clothing link, and the matching degree exceeds the preset threshold value as the associated candidate reference clothing non-standard data. The specific value of the preset threshold value can be determined according to the actual scenario and is not limited here.
[0050] Exemplarily, Table 2 shows the association relationship between the candidate reference clothing standard data, the candidate reference clothing non-standard data, and the identification information of the seller's display clothing link.
[0051] Table 2
[0052]
[0053] Among them, identification number information is established for each candidate reference clothing non-standard data, and an association relationship between the candidate reference clothing standard data and the candidate reference clothing non-standard data is established through the seller's display clothing link number.
[0054] In a feasible embodiment, after S120, the method further includes:
[0055] Obtain candidate user feedback images;
[0056] The candidate user feedback image is matched with the display image in each seller display clothing link, and the seller display clothing link with the highest matching degree is determined as the target seller display clothing link associated with the candidate user feedback image, and the candidate user feedback image is used as the candidate reference clothing non-standard data associated with the identification information corresponding to the target seller display clothing link.
[0057] In order to ensure the feature richness of the candidate reference clothing non-standard data, real clothing effect pictures of real users in daily life can be collected in advance as candidate user feedback images, and the candidate user feedback images are matched with the candidate reference clothing standard data in each seller's clothing display link, and the seller's clothing display link with the highest matching degree is determined as the target seller's clothing display link, and the candidate user feedback image is used as the candidate reference clothing non-standard data associated with the candidate reference clothing standard data corresponding to the target seller's clothing display link.
[0058] Exemplarily, the shopping platform's image search function is used to search for the same style in the photos of real people wearing clothes, and the clothing link with the highest matching degree is selected as the target seller to display the clothing link, or the clothing link with the highest matching degree is manually selected as the target seller to display the clothing link based on the search results for the same style.
[0059] The non-standard data of candidate reference clothing is expanded through the matching results of candidate user feedback images and seller displayed clothing links, which improves the richness of the clothing image library and further improves the accuracy of identifying the target person based on the non-standard data of clothing to be matched.
[0060] According to the matching results of the non-standard clothing data to be matched and the candidate reference clothing non-standard data in the pre-established clothing image library, the target reference clothing standard data associated with the non-standard clothing data to be matched is determined.
[0061] Based on a predetermined clothing image library, candidate reference clothing standard data associated with the clothing non-standard data to be matched is determined as target reference clothing standard data according to the association relationship between the candidate reference clothing non-standard data and the standard data in the image library.
[0062] When an accident occurs at a certain place, a side or back photo of the suspected person's clothing is obtained, and the photo is used as a data source to search and compare with the candidate reference clothing non-standard data in the clothing image library, and the candidate reference clothing standard data associated with the candidate reference clothing non-standard data with the highest matching degree is determined as the target reference clothing standard data. The target reference clothing standard data is used for image search and comparison, and then compared with the image captured in the actual scene, thereby improving the recognition accuracy.
[0063] Since the clothing standard data provided by the seller includes the complete features of the clothing, the complete features of the clothing are used for comparison, which expands the comparison conditions and improves the success rate of the comparison. In addition, the clothing image library in this embodiment is associated with daily data such as shopping, which reduces the acquisition cost of the clothing image library, and the data in the image library is more authentic.
[0064] Embodiment 2
[0065] Figure 2 A flowchart of a method for identifying a target person based on clothing is provided for the second embodiment of the present invention. This embodiment is applicable to the case where a target person is identified and tracked based on the local features of the target person's clothing. The method can be performed by a target person identification device based on clothing. The target person identification device based on clothing can be implemented in the form of hardware and / or software. The target person identification device based on clothing can be configured in a device with computing capabilities such as a server. Figure 2 As shown, the method includes:
[0066] S210: Acquire non-standard data of clothing to be matched of the target person.
[0067] The target person refers to the person who needs to be identified or tracked. For example, if a suspect is found in the video image of the accident scene, the suspect is determined to be the target person. The non-standard clothing data to be matched refers to an image including the side or back of the target person. For example, if only the side of the suspect appears in the video image of the accident scene, the image including the side of the suspect is used as the non-standard clothing data to be matched.
[0068] Specifically, when only a side image of the target person is obtained, since it is impossible to accurately identify the target person based on the side face image, it is necessary to use the local features of the clothing to identify the target person, and the side image is used as the non-standard clothing data to be matched for the target person. Exemplarily, the camera at the accident scene only captures the side image of the suspect, and the side image is used as the non-standard clothing data to be matched. The local clothing features in the non-standard clothing data to be matched are used to match the video images captured by cameras at other locations, so as to obtain a complete frontal image of the target person with the same clothing features, thereby realizing the identification of the target person.
[0069] S220: Determine target reference clothing standard data associated with the non-standard clothing data to be matched according to the matching result between the non-standard clothing data to be matched and candidate reference clothing non-standard data in a pre-established clothing image library.
[0070] The clothing image library includes the association relationship between the candidate reference clothing non-standard data determined according to the shopping behavior and the candidate reference clothing standard data. The candidate reference clothing refers to the clothing that the candidate has a tendency to buy. The clothing with a tendency to buy is determined in advance according to the daily behavior of all users, and the association relationship between the non-standard data and the standard data of various candidate clothing is established according to the relevant purchase information of the clothing.
[0071] Exemplarily, due to the completeness of the products on the current online shopping platforms, candidate reference clothing is determined based on the clothing information published on the online shopping platforms, and non-standard data and standard data are determined based on the various clothing pictures included in the clothing information, so as to establish a clothing image library including the association relationship between the non-standard data of candidate reference clothing and the standard data of candidate reference clothing, wherein the standard data of candidate reference clothing is determined based on the clothing pictures displayed by the sellers of the reference clothing, including the front and side pictures of the clothing; the non-standard data of candidate reference clothing is determined based on the clothing pictures displayed by the buyers of the reference clothing, including the side and back pictures of the clothing.
[0072] In a feasible embodiment, S220 includes:
[0073] According to the matching results of the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data, determining the target reference clothing non-standard data from the candidate reference clothing non-standard data;
[0074] Based on the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data, the candidate reference clothing standard data associated with the target reference clothing non-standard data is determined as the target reference clothing standard data associated with the clothing non-standard data to be matched.
[0075] Since the non-standard clothing data to be matched only includes local features of clothing, the non-standard clothing data to be matched is matched with the candidate reference clothing non-standard data in the clothing image library, that is, local features are matched with local features to avoid errors caused by matching non-standard data with complete clothing features. The candidate reference clothing non-standard data that best matches the non-standard clothing data to be matched is determined as the target reference clothing non-standard data, and the candidate reference clothing standard data associated with the target reference clothing non-standard data in the clothing image library is used as the target reference clothing standard data associated with the non-standard clothing data to be matched.
[0076] S230: Obtain a target complete image of the target person from the image to be identified according to the target reference clothing standard data.
[0077] Since the target reference clothing standard data includes all clothing features of the target person, the clothing features in the target reference clothing standard data are matched in the image to be identified, and the image whose clothing features of the person are most matched with the target reference clothing standard data is the target complete image of the target person.
[0078] For example, the camera at the accident scene only captures the side image of the suspect, and the side image is matched in the clothing image library to find the complete clothing image of the suspect, and the complete clothing image is used to match the video image captured by the camera at other locations to obtain the complete front image of the target person with the same clothing features, thereby realizing the identification of the target person. Alternatively, the camera at the accident scene only captures the back image of the suspect, and the back image is matched in the clothing image library to find the complete clothing image included in the clothing standard data of the suspect, and the complete clothing image is used to match the video image captured by the camera at other locations to obtain the complete front image or complete side image of the target person with the same clothing features.
[0079] The technical solution of the embodiment of the present invention predetermines the association relationship between candidate reference clothing non-standard data and candidate reference clothing standard data through daily shopping behavior, and determines the associated clothing standard data for the clothing non-standard data through the association relationship, and then identifies the target person according to the clothing standard data, thereby solving the problem of low efficiency and low reliability of personnel identification only through local features of clothing, and improving the recognition efficiency and recognition accuracy of the target person.
[0080] Embodiment 3
[0081] Figure 3 This is a schematic diagram of the structure of a device for establishing a clothing image library provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:
[0082] A clothing identification creation module 310 is used to create identification information for each seller displaying clothing links in the shopping platform;
[0083] A reference clothing standard data determination module 320 is used to use the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information;
[0084] The first reference clothing non-standard data determining module 330 is configured to use the feedback picture in the buyer feedback information in the seller display clothing link as the candidate reference clothing non-standard data associated with the identification information.
[0085] Optionally, the device further comprises a second reference clothing non-standard data determination module, which is used to: after taking the display picture in the seller's display clothing link as the candidate reference clothing standard data associated with the identification information, obtain a candidate user feedback image;
[0086] The candidate user feedback image is matched with the display image in each seller display clothing link, and the seller display clothing link with the highest matching degree is determined as the target seller display clothing link associated with the candidate user feedback image, and the candidate user feedback image is used as the candidate reference clothing non-standard data associated with the identification information corresponding to the target seller display clothing link.
[0087] The device for establishing a clothing image library provided in the embodiment of the present invention can execute the method for establishing a clothing image library provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0088] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.
[0089] Embodiment 4
[0090] Figure 4 This is a schematic diagram of the structure of a clothing-based target person identification device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device comprises:
[0091] The clothing non-standard data acquisition module 410 is used to acquire the non-standard data of the clothing to be matched of the target person;
[0092] The clothing standard data determination module 420 is used to determine the target reference clothing standard data associated with the clothing non-standard data to be matched according to the matching result between the clothing non-standard data to be matched and the candidate reference clothing non-standard data in the pre-established clothing image library; wherein the clothing image library includes the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data determined according to the shopping behavior;
[0093] The person complete image determination module 430 is used to obtain a target complete image of the target person from the image to be identified according to the target reference clothing standard data.
[0094] Optionally, the clothing standard data determination module is specifically used to:
[0095] Determining target reference clothing non-standard data from the candidate reference clothing non-standard data according to a matching result between the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data;
[0096] Based on the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data, the candidate reference clothing standard data associated with the target reference clothing non-standard data is determined as the target reference clothing standard data associated with the to-be-matched clothing non-standard data.
[0097] The clothing-based target person recognition device provided in the embodiment of the present invention can execute the clothing-based target person recognition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0098] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.
[0099] Embodiment 5
[0100] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
[0101] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0102] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0103] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0104] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the method for target person recognition based on clothing or the establishment of a clothing image library.
[0105] In some embodiments, the clothing-based target person recognition method or the clothing image library establishment method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the clothing-based target person recognition method or the clothing image library establishment method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the clothing-based target person recognition method or the clothing image library establishment method by any other appropriate means (for example, by means of firmware).
[0106] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific reference products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0107] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0108] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 of the foregoing.
[0109] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0110] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0111] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0112] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for establishing a clothing image library, characterized in that: The method comprises: Establish identification information for each seller displaying clothing links on the shopping platform; Using the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information; The feedback picture in the buyer feedback information in the seller display clothing link is used as candidate reference clothing non-standard data associated with the identification information.
2. The method according to claim 1, characterized in that After taking the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information, the method further includes: Obtain candidate user feedback images; The candidate user feedback image is matched with the display image in each seller display clothing link, and the seller display clothing link with the highest matching degree is determined as the target seller display clothing link associated with the candidate user feedback image, and the candidate user feedback image is used as the candidate reference clothing non-standard data associated with the identification information corresponding to the target seller display clothing link.
3. A clothing-based target person recognition method, characterized in that: The method comprises: Obtain non-standard data of clothing to be matched of the target person; According to the matching result between the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data in the pre-established clothing image library, target reference clothing standard data associated with the to-be-matched clothing non-standard data is determined; wherein the clothing image library includes the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data determined according to the shopping behavior; the association relationship is determined according to the method for establishing the clothing image library according to claim 1 or 2; A target complete image of the target person is acquired from the image to be identified according to the target reference clothing standard data.
4. The method according to claim 3, characterized in that According to the matching result of the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data in the pre-established clothing image library, determining the target reference clothing standard data associated with the to-be-matched clothing non-standard data, including: Determining target reference clothing non-standard data from the candidate reference clothing non-standard data according to a matching result between the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data; Based on the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data, the candidate reference clothing standard data associated with the target reference clothing non-standard data is determined as the target reference clothing standard data associated with the to-be-matched clothing non-standard data.
5. A device for establishing a clothing image library, characterized in that: include: A clothing identification creation module is used to create identification information for each seller displaying clothing links on the shopping platform; A reference clothing standard data determination module, configured to use the display image in the seller's display clothing link as candidate reference clothing standard data associated with the identification information; The first reference clothing non-standard data determining module is used to use the feedback picture in the buyer feedback information in the seller display clothing link as the candidate reference clothing non-standard data associated with the identification information.
6. The device according to claim 5, characterized in that The device further comprises a second reference clothing non-standard data determining module, which is used to: After taking the display picture in the seller's display clothing link as candidate reference clothing standard data associated with the identification information, obtaining a candidate user feedback image; The candidate user feedback image is matched with the display image in each seller display clothing link, and the seller display clothing link with the highest matching degree is determined as the target seller display clothing link associated with the candidate user feedback image, and the candidate user feedback image is used as the candidate reference clothing non-standard data associated with the identification information corresponding to the target seller display clothing link.
7. A clothing-based target person identification device, characterized in that: include: A clothing non-standard data acquisition module is used to acquire the non-standard clothing data to be matched of the target person; A clothing standard data determination module, used to determine target reference clothing standard data associated with the clothing non-standard data to be matched according to the matching result between the clothing non-standard data to be matched and the candidate reference clothing non-standard data in the pre-established clothing image library; wherein the clothing image library includes the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data determined according to the shopping behavior; the association relationship is determined according to the clothing image library establishment device according to claim 5 or 6; The person standard data determination module is used to obtain a target complete image of the target person from the image to be identified based on the target reference clothing standard data.
8. The device according to claim 7, characterized in that The clothing standard data determination module is specifically used for: Determining target reference clothing non-standard data from the candidate reference clothing non-standard data according to a matching result between the to-be-matched clothing non-standard data and the candidate reference clothing non-standard data; Based on the association relationship between the candidate reference clothing non-standard data and the candidate reference clothing standard data, the candidate reference clothing standard data associated with the target reference clothing non-standard data is determined as the target reference clothing standard data associated with the to-be-matched clothing non-standard data.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for establishing a clothing image library described in any one of claims 1-2 or the method for target person recognition based on clothing described in any one of claims 3-4.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for establishing a clothing image library as described in any one of claims 1-2 or the method for identifying a target person based on clothing as described in any one of claims 3-4 when executed.
Citation Information
Patent Citations
Information obtaining method and apparatus
CN107870908A
A case intelligent serial-parallel method based on face recognition
CN109190498A
Authentication method and system, and storage medium
CN109508524A
Pedestrian re-recognition interactive retrieval method and system based on camera position
CN112949539A
Image recognition method and device, electronic equipment and readable storage medium
CN113963197A
