Method for obtaining clothes display image based on image recognition and application

Abstract

The invention relates to the technical field of smart home, and particularly provides a method for obtaining a clothes display image based on image recognition, an application, a control device and a medium. The method for obtaining the clothes display image based on image recognition comprises the following steps: establishing a clothes database; wherein the clothes database comprises a plurality of clothes images; acquiring a user's shot image of the to-be-displayed clothes; and determining a display image according to similarity analysis of the shot image and the clothes image. The invention further provides application of the method in clothes management. According to the invention, the quality of the display image for clothes management is improved, and the aesthetic degree is increased.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and specifically provides a method, application, control device and medium for acquiring clothing display images based on image recognition. Background Art

[0002] As people's living standards continue to improve, the number of clothes per capita is also increasing. The main reasons are as follows:

[0003] 1. Improved economic development: With economic development, people's living standards have improved. People can earn more income and buy more clothes. In addition, people's occupation, social status, age and other factors will also affect their requirements and willingness to buy clothes.

[0004] 2. Changes in consumption concepts: With the development of society, consumption concepts have also changed. More and more people are beginning to pay attention to fashionable, personalized, and diversified consumption. People are no longer satisfied with a single clothing brand and color, but are pursuing richer and more personalized clothing choices.

[0005] 3. Technological progress: The development of modern technology has provided more possibilities for the production and design of clothing. People can produce clothing of various materials and styles, and also add more functions and properties to clothing, such as anti-wrinkle, antibacterial, quick-drying, etc.

[0006] 4. Diversification of information dissemination channels: With the development of the Internet and social media, people can obtain more clothing information and shopping channels. People can buy fashion brands from all over the world online, and can also see friends, family or strangers’ clothing sharing and shopping experience on social media.

[0007] 5. Improvement in logistics, storage and transportation technology: With the continuous improvement of logistics, storage and transportation technology, people can buy and store clothes more conveniently. For example, the improvement of storage technology allows people to buy the clothes they need in a shorter time, and the development of logistics technology also provides more guarantees for the transportation and storage of clothes.

[0008] However, too many clothes also bring many problems in clothing management. For example, as the number of clothes in the home increases, people may not remember which clothes they have, resulting in duplicate purchases or idle clothes. When there are a lot of clothes in the closet, it is very troublesome to manually search through multiple pieces of clothing to find a certain piece of clothing.

[0009] In recent years, with the promotion of the concepts of the Internet of Things and smart homes, in order to improve the efficiency of clothing management, smart wardrobe products with smart functions have been launched on the market, and clothing management is carried out using app cloud wardrobes in smart homes.

[0010] A cloud wardrobe is a digital wardrobe that helps people better manage, preserve and display their clothing. Cloud wardrobes are usually connected to smartphones, tablets or other devices, where users can upload and download photos, while also being able to access their collections at any time through cloud storage.

[0011] The necessity of cloud wardrobe lies in that as people buy more clothes, traditional wardrobes can no longer meet people's needs. The emergence of cloud wardrobe provides people with a better solution, allowing people to manage their clothes more easily and access their collections anytime and anywhere.

[0012] Cloud Wardrobe can also help save people time in organizing their wardrobes. Traditional wardrobes require people to spend a lot of time organizing and categorizing clothes, while Cloud Wardrobe can help users better organize their wardrobes through automatic identification and classification. This allows users to find the clothes they need more quickly and easily, avoiding wasting a lot of time on organizing their wardrobes.

[0013] Cloud wardrobe is very important for modern people. It can help people better manage, preserve and display their clothes, and also improve the efficiency of people organizing their wardrobes.

[0014] In the existing clothing management technology, it is often necessary to manage the clothes based on the pictures of the clothes to be managed, but there are some problems. For example, when using the app cloud wardrobe to store clothing information, the clothes taken by the user have unfavorable factors such as cluttered background and dim light. At present, when users store clothes in the cloud wardrobe, they use the directly photographed images, which are not aesthetically pleasing and are not conducive to image reading and recognition. Summary of the invention

[0015] In order to overcome the above-mentioned defects, the present invention provides a method, a control device and a medium for acquiring clothing display images based on image recognition, so as to improve the quality of display images used for clothing management and increase the aesthetics.

[0016] In a first aspect, the present invention provides a method for acquiring a clothing display image based on image recognition, comprising:

[0017] Establishing a clothing database; wherein the clothing database includes a plurality of clothing images;

[0018] Obtaining a user's photographed image of the clothing to be displayed;

[0019] A display image is determined based on similarity analysis between the captured image and the clothing image.

[0020] Further, the determining of the display image based on the similarity analysis between the photographed photo and the clothing image includes:

[0021] Respectively obtaining the similarity between the captured image and each clothing image in the clothing database;

[0022] Acquire the clothing image with the highest similarity;

[0023] Determining whether the similarity is higher than a preset threshold;

[0024] If it is higher than a preset threshold, the clothing image with the highest similarity is used as the display image.

[0025] Furthermore, after the step of determining whether the similarity is higher than a preset threshold, the method further includes:

[0026] If it is not higher than the preset threshold, the captured image will be used as the display image.

[0027] Furthermore, the clothing database also includes:

[0028] A feature vector corresponding to each clothing image.

[0029] Furthermore, the feature vector is a one-dimensional vector.

[0030] Furthermore, after the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises:

[0031] A feature vector of the captured image is obtained.

[0032] Furthermore, the feature vector of the captured image is a one-dimensional feature vector.

[0033] Further, the determining the display image according to the similarity analysis between the captured image and the clothing image includes:

[0034] The display image is determined based on the similarity analysis between the acquired feature vector of the captured image and each feature vector in the clothing database.

[0035] Furthermore, the Euclidean distance algorithm is used for similarity analysis.

[0036] Furthermore, the clothing database includes a number of clothing images, including:

[0037] The clothing database includes clothing images of several different brands.

[0038] Furthermore, after the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises:

[0039] Get the clothing brand to be displayed input by the user;

[0040] The similarity analysis between the captured image and the clothing image includes:

[0041] Acquire clothing images of the same brand as the clothing to be displayed from a clothing database;

[0042] Based on the similarity analysis between the photographed image and the clothing image of the same brand.

[0043] In a second aspect, the present invention also provides application of the method in clothing management.

[0044] In a third aspect, a control device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the method for acquiring clothing display images based on image recognition as described in any of the technical solutions of the method for acquiring clothing display images based on image recognition.

[0045] In a fourth aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, wherein the program codes are suitable for being loaded and run by a processor to execute the method for acquiring clothing display images based on image recognition as described in any of the technical solutions of the method for acquiring clothing display images based on image recognition.

[0046] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0047] In the technical solution for implementing the present invention, the present invention finds the image most similar to the picture taken by the user through similarity analysis. When the similarity exceeds a preset threshold, the most similar image found in the database replaces the image taken by the user himself, and is used to display the image of the clothing in the clothing management process, thereby obtaining a more standard, clearer and more aesthetically pleasing image, which is convenient for clothing identification and subsequent clothing management.

[0048] In the technical solution of the present invention, the clothing database includes clothing images of several different brands. By combining the brand's clothing data with image retrieval technology, the online clothing images corresponding to the clothing photographed by the user are matched to increase the aesthetics. Clothes are classified by brand, which greatly improves the speed of clothing image matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The disclosure of the present invention will become more easily understood with reference to the accompanying drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present invention. In addition, similar numbers in the figures are used to represent similar components, among which:

[0050] Figure 1 is a flow chart of main steps of a method for acquiring clothing display images based on image recognition according to an embodiment of the present invention;

[0051] Figure 2 is a flowchart of main steps of determining a display image based on similarity analysis between the photographed photo and the clothing image according to an embodiment of the present invention;

[0052] Figure 3 is a flow chart including a step of if the value is not higher than a preset threshold value according to an embodiment of the present invention;

[0053] Figure 4 It is a flowchart of main steps of determining a display image based on similarity analysis of feature vectors between the captured image and the clothing image according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0055] In the description of the present invention, "module" and "processor" may include hardware, software or a combination of the two. A module may include hardware circuits, various suitable sensors, communication ports, and memories, and may also include software parts, such as program codes, or a combination of software and hardware. The processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, hardware, or a combination of the two. Non-temporary computer-readable storage media include any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and the like. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a similar meaning to "A and / or B", and may include only A, only B, or A and B. The singular terms "one" and "the" may also include plural forms.

[0056] In the current traditional clothing management, users directly take photos of the clothes to be managed and then upload them to the system. Users take photos of clothes themselves, which has the following problems:

[0057] The influence of light and background: When taking photos, the light and background may affect the quality of clothing photos. For example, if the light is too weak or too strong, or the background is too cluttered or too clear, it will affect the effect of clothing photos.

[0058] Camera and lens selection: When users take photos of clothing themselves, they may choose the wrong camera or lens, resulting in reduced photo quality. For example, choosing the wrong resolution, focal length, lens, etc. will affect the effect of the photo.

[0059] Shooting skills and experience: When users take photos of clothing by themselves, they may not be able to take high-quality photos due to lack of shooting skills and experience. For example, not using the virtual image lens correctly, not using the background blur correctly, etc., will affect the effect of the photo.

[0060] Post-processing: After taking photos of clothing, users may perform post-processing, such as cropping, color adjustment, and photo editing, to improve the quality of the photos. However, performing post-processing too frequently may cause the photos to lose their sense of reality, thus affecting the quality of the photos.

[0061] The material and characteristics of clothing: When users take photos of clothing themselves, they may not be able to take high-quality photos due to the material and characteristics of the clothing. For example, some clothing may require special shooting angles or lighting to show the best texture and effect.

[0062] To sum up, when users take photos of clothes by themselves, factors such as light, background, camera, lens, shooting techniques, post-processing, material and characteristics of the clothes may affect the quality of the photos.

[0063] In view of the above problems, the present invention provides a method for obtaining clothing display images based on image recognition, referring to Figure 1 ,include:

[0064] S100, establishing a clothing database; wherein the clothing database includes a plurality of clothing images;

[0065] S200, obtaining a photographed image of the clothing to be displayed by the user;

[0066] S300, determining a display image based on similarity analysis between the captured image and the clothing image.

[0067] In one application scenario, the clothing images in the clothing database are derived from clothing pictures on sales websites and clothing sales platforms. As more and more users choose to shop online, and merchants generally operate both online and offline, most clothing images are available online. In order to display these clothing images clearly when they are sold, with high image quality and clear background, the clothing pictures on the Internet are collected to form a database.

[0068] Users take photos of the clothes to be displayed and collect the photos;

[0069] Compare the clothing images taken by the user with the clear, high-quality images in the database.

[0070] Through similarity comparison and analysis, the image selected for final display is determined.

[0071] In one embodiment, referring to Figure 2 , the determining of the display image according to the similarity analysis between the photographed photo and the clothing image comprises:

[0072] S310, respectively obtaining the similarity between the captured image and each clothing image in the clothing database;

[0073] S320, acquiring the clothing image with the highest similarity;

[0074] S330, determining whether the similarity is higher than a preset threshold;

[0075] S340: If the similarity is higher than a preset threshold, the clothing image with the highest similarity is used as a display image.

[0076] Since the clothing database contains a large number of clothing images, in order to determine which clothing image can be used to accurately display the content of the captured image, it is necessary to determine the similarity between the captured image and the clothing image, and find the clothing image that is most similar to the captured image from the clothing database. The determination criterion is similarity.

[0077] If they are similar enough or the similarity is high to a certain extent, that is, the similarity is higher than a preset threshold, it means that the clothing image can reflect the content of the captured image.

[0078] At this time, the image taken by the user himself is replaced by the more standard, clearer and more aesthetic clothing image as the display image. The user uses the clothing image to refer to the corresponding clothing in clothing management.

[0079] The present invention finds the image most similar to the picture taken by the user through similarity analysis. When the similarity exceeds a preset threshold, the most similar image found in the database replaces the image taken by the user himself, and is used to display the clothing in the clothing management process, so that a more standard, clearer and more aesthetic image is obtained, which is convenient for clothing identification and subsequent clothing management.

[0080] In an application scenario, a user takes a photo of clothing Z and obtains a captured image M z , the clothing database contains clothing images of clothing A, B, C, D, and E, which are: M a , M b , M c , M d , M eThese images are obtained from online sales platforms or exhibition platforms.

[0081] Compare M z With M a , M b , M c , M d , M e Which of the following is the most similar? z With M d The highest similarity is 90%, then it is determined whether the similarity is higher than a preset threshold value, which is 85%. After determination, it is higher than the preset threshold value, indicating that there is a high probability that clothing D and clothing Z are the same clothing. The image of clothing Z that is finally used for product display is M. d .

[0082] In one embodiment, referring to Figure 3 After the step of determining whether the similarity is higher than a preset threshold, the method further comprises:

[0083] S350: If the value is not higher than the preset threshold, the captured image is used as a display image.

[0084] In the present invention, the serial number serves as an identification and does not strictly limit the order of precedence. For example, S350 and S340 are parallel judgment steps and do not distinguish between the order of precedence.

[0085] In an application scenario, still referring to the above application scenario, if the preset threshold is 95% similarity, after judgment, it is not higher than the preset threshold, indicating that the clothing images in the clothing database are most likely not the same product as clothing Z. In order to ensure that the clothing display photos are not distorted, the image of clothing Z used for product display is finally used as M z .

[0086] In one embodiment, the clothing database further includes:

[0087] A feature vector corresponding to each clothing image.

[0088] Each clothing image corresponds to a feature vector.

[0089] In one embodiment, the feature vector is a one-dimensional vector.

[0090] The feature vector of the clothing image is obtained through an image recognition algorithm.

[0091] In one embodiment, after the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises:

[0092] A feature vector of the captured image is obtained.

[0093] The feature vector of the captured image is obtained through an image recognition algorithm.

[0094] In an application scenario, the feature vector of the captured image is a one-dimensional feature vector.

[0095] In one embodiment, referring to Figure 4 , the determining of the display image according to the similarity analysis between the captured image and the clothing image comprises:

[0096] S301, respectively obtaining the similarity between the feature vector of the captured image and the feature vector of each clothing image in the clothing database;

[0097] S302, obtaining a clothing image having the highest similarity to the feature vector;

[0098] S303, determining whether the similarity is higher than a preset threshold;

[0099] S304: If the similarity is higher than a preset threshold, the clothing image with the highest feature vector similarity is used as a display image.

[0100] S305: If the value is not higher than the preset threshold, the captured image is used as a display image.

[0101] S304 and S305 are parallel judgment steps, and the order of precedence is not particularly distinguished.

[0102] In one embodiment, the similarity is determined using Euclidean distance.

[0103] The Euclidean distance algorithm is a commonly used algorithm for calculating image similarity. Its principle is to transform the feature vector of the image into the Euclidean space and then calculate the distance between the two vectors. The Euclidean distance algorithm can cluster the corresponding feature points together. The distance between the feature points indicates the degree of similarity between them. The smaller the distance, the higher the similarity, and vice versa. Therefore, the Euclidean distance algorithm is often used to determine whether two image blocks in an image are similar, or to determine whether different feature points have similar features.

[0104] In an application scenario, a user takes a photo of clothing Z and obtains a captured image M z , the corresponding feature vector is obtained by pre-training the model based on the image recognition algorithm as a 1×1024 vector. The clothing database contains clothing images of clothing A, B, and C, which are respectively: M a , M b , M c These images are obtained from online sales platforms or exhibition platforms, and the corresponding feature vectors obtained through the trained model are: 1×1015, 1×1033, and 1×1023 vectors.

[0105] Compare which feature vector of the 1×1024 vector is most similar to that of the 1×1015, 1×1033, and 1×1023 vectors, and use the Euclidean distance algorithm to determine the M c With M d The similarity is the highest, which is 87%. Then it is determined whether the similarity is higher than a preset threshold value, which is 85%. After determination, it is higher than the preset threshold value, indicating that there is a high probability that clothing C and clothing Z are the same clothing. The image of clothing Z used for product display is finally used as M. c .

[0106] In one embodiment, the clothing database includes a plurality of clothing images, including:

[0107] The clothing database includes clothing images of several different brands.

[0108] A clothing database of each brand's clothing is established, and the database is divided into clothing sets of different genders under different brands.

[0109] In one embodiment, after the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises:

[0110] Obtain the brand of clothing to be displayed input by the user; obtain the brand of the clothing by interacting with the user;

[0111] The similarity analysis between the captured image and the clothing image includes:

[0112] Acquire clothing images of the same brand as the clothing to be displayed in the clothing database;

[0113] Under the brand, a similarity analysis is performed based on the captured image and clothing images of the same brand.

[0114] As people pursue a better quality of life, more and more users will choose branded clothing, and users often choose clothing from one or several brands. There are several reasons for this:

[0115] 1. Brand effect: When buying clothes, people may be affected by the brand effect. Clothes of a certain brand usually have a high reputation and popularity in the market. People may think that these clothes are of better quality and more cost-effective, so they are more willing to choose this brand.

[0116] 2. Product quality: People pay attention to product quality when buying clothes. A certain brand of clothing may have higher requirements in production process, fabric selection, etc., so as to ensure product quality. In addition, people may also think that these clothes are more comfortable and durable.

[0117] 3. Price factor: Under the premise of ensuring product quality, people may consider price factors. A certain brand of clothing may be positioned in the mid-to-high-end market and the price is relatively high. However, due to its good product quality, people may think it is worth the money.

[0118] 4. Personal preferences: Each user may have different needs and preferences. When buying clothes, people may pay attention to the general style, color, size and other information of the clothes to find clothes that are more suitable for them. A certain brand of clothes may have a certain market share in the market, thus meeting the needs of different users.

[0119] 5. Social trends: As fashion trends continue to change, a certain brand of clothing may become a hot commodity in the market. In this case, people may be influenced by social trends and choose to buy clothing of this brand.

[0120] Therefore, clothing can be classified by brand, which greatly improves the speed of clothing image matching.

[0121] The invention also provides application of the method in clothing management.

[0122] In a smart home, when using the app cloud wardrobe to store clothing information, the clothes photographed by users have unfavorable factors such as cluttered backgrounds and dim light. In the early stage, when users stored clothes in the cloud wardrobe, they used images directly taken, which had poor aesthetics. The present invention uses image retrieval technology combined with brand clothing data to match the online clothing images corresponding to the clothes photographed by users, thereby increasing the aesthetics.

[0123] First, a clothing database of various brands of clothing is established. The database is divided into clothing sets of different brands and genders, and a clothing detection algorithm is used to obtain the feature vector of each brand of clothing. After the user takes a clothing image, the brand of the clothing is obtained through interaction with the user. When the user is ready to store, the user's clothing is detected using image detection technology, and the feature vector of the clothing is obtained. The feature vector of the clothing is used to perform similarity matching with the feature vector of the clothing in the corresponding clothing brand database to obtain the clothing with the highest similarity as the display image of the clothing taken by the user this time.

[0124] This results in images of higher quality, better definition, and easier display and identification of clothing, thereby facilitating clothing management.

[0125] In one embodiment, the clothing database further includes:

[0126] A matching object image corresponding to each of the clothing images.

[0127] In application, for example, when a clothing management system such as a smart wardrobe or a cloud wardrobe manages clothing, a user needs to search for clothing Z, and the display image of clothing Z uses clothing image M in the clothing database. a exhibit.

[0128] The clothing management system displays the display image M of clothing Z. a When the recommended matching image associated with the clothing Z is displayed, that is, the recommended matching image associated with the clothing image M a Corresponding matching object images. For example, if clothing Z is pants, the management platform will simultaneously push tops, coats or shoes that match the clothing Z for the user's reference, saving the user the energy and time spent on matching by themselves. The recommended matching can be clothing that the user has stored in the management system for joint management, or clothing sold by a merchant. The matching can also be linked to a mall, and the user can click to enter and purchase. As people's living standards improve, personal image management is becoming more and more important. The application of the present invention can help users improve the utilization rate and aesthetic matching of clothing, and improve the efficiency of user image management.

[0129] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0130] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0131] Furthermore, the present invention also provides a control device. In one embodiment of the control device according to the present invention, the control device includes a processor and a storage device. The storage device can be configured to store a program for executing the method for acquiring clothing display images based on image recognition in the above method embodiment. The processor can be configured to execute the program in the storage device, which includes but is not limited to the program for executing the method for acquiring clothing display images based on image recognition in the above method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device can be a control device device formed by various electronic devices.

[0132] Furthermore, the present invention also provides a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program for executing the method for acquiring clothing display images based on image recognition in the above-mentioned method embodiment, and the program can be loaded and run by the processor to implement the above-mentioned method for acquiring clothing display images based on image recognition. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0133] Further, it should be understood that since the setting of each module is only for illustrating the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only schematic.

[0134] It is understood by those skilled in the art that the modules in the device can be adaptively split or merged. Such splitting or merging of specific modules will not cause the technical solution to deviate from the principle of the present invention, and therefore, the technical solutions after splitting or merging will fall within the protection scope of the present invention.

[0135] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for acquiring clothing display images based on image recognition, characterized in that: include: Establishing a clothing database; wherein the clothing database includes a plurality of clothing images; Obtaining a user's photographed image of the clothing to be displayed; A display image is determined based on similarity analysis between the captured image and the clothing image.

2. The method according to claim 1, characterized in that The determining of the display image according to the similarity analysis between the photographed photo and the clothing image comprises: Respectively obtaining the similarity between the captured image and each clothing image in the clothing database; Acquire the clothing image with the highest similarity; Determining whether the similarity is higher than a preset threshold; If it is higher than a preset threshold, the clothing image with the highest similarity is used as a display image; If it is not higher than the preset threshold, the captured image will be used as the display image.

3. The method according to claim 1, characterized in that The clothing database also includes: A feature vector corresponding to each clothing image.

4. The method according to claim 3, characterized in that After the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises: Acquire a feature vector of the captured image.

5. The method according to claim 4, characterized in that The determining of the display image according to the similarity analysis between the captured image and the clothing image comprises: The display image is determined based on the similarity analysis between the acquired feature vector of the captured image and each feature vector in the clothing database.

6. The method according to claim 1, characterized in that The clothing database includes a number of clothing images, including: The clothing database includes clothing images of several different brands.

7. The method according to claim 6, characterized in that After the step of obtaining the photographed image of the clothing to be displayed by the user, the method further comprises: Get the clothing brand to be displayed input by the user; The similarity analysis between the captured image and the clothing image includes: Acquire clothing images of the same brand as the clothing to be displayed from a clothing database; Based on the similarity analysis between the photographed image and the clothing image of the same brand.

8. Application of the method according to any one of claims 1 to 7 in clothing management.

9. A control device, comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the clothing management method based on image recognition according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the clothing management method based on image recognition according to any one of claims 1 to 7.

Images