Control method of laundry treating apparatus and laundry treating apparatus

Abstract

The present application relates to the field of clothes processing equipment, and particularly provides a control method of clothes processing equipment and clothes processing equipment, aiming at solving the problem that the matching clothes characteristic information of the existing clothes care machine is not accurate enough. To this end, the control method of the present application comprises: acquiring a to-be-processed clothes image; identifying a first clothes color of the to-be-processed clothes image; analyzing a similarity value of each pre-stored clothes image in a database and the to-be-processed clothes image; performing similarity sorting on each pre-stored clothes image based on the similarity value; optimizing the similarity sorting based on the first clothes color and a second clothes color of the pre-stored clothes image; and executing a clothes characteristic information acquisition strategy according to the optimization result.

Description

Technical Field

[0001] This invention relates to the field of garment processing equipment, and specifically provides a control method for garment processing equipment and garment processing equipment. Background Technology

[0002] As living standards continue to improve, people's demand for clothing care has increased dramatically. Clothing care machines are dedicated to providing meticulous care for clothing and can support the care of clothing made of materials such as cotton, linen, wool, silk, polyester fiber, nylon, and denim.

[0003] In order to determine the material of the garment to be cared for among a variety of garment materials and then match the appropriate garment care procedure, the prior art has a technical solution that compares the attribute vector matrix of the garment image to be cared for with the garment attribute vector matrix in the garment attribute database, and then determines whether to identify the garment attribute in the garment attribute database as the garment attribute of the garment to be cared for based on the comparison result. This method determines the garment attribute of the garment to be cared for, and the garment attribute includes the garment material.

[0004] However, this control method may match clothing information that is very similar in image but different in material type and content. For example, two garments may be 60% wool and 100% wool respectively. The images of such garments are very similar, but the above method is very likely to make a mistake. Since different material types and contents often correspond to different garment care procedures, this may result in the inability to accurately match garment care procedures.

[0005] Accordingly, there is a need in the art for a new control method for garment processing equipment and a new garment processing equipment to solve the above-mentioned problems. Summary of the Invention

[0006] The present invention aims to solve the above-mentioned technical problem, namely, to solve the problem that the clothing feature information matched by existing clothing care machines is not accurate enough.

[0007] In a first aspect, the present invention provides a control method for a garment processing device, characterized in that the control method includes: acquiring an image of garments to be processed; identifying a first garment color in the image of garments to be processed; analyzing the similarity values ​​between each pre-stored garment image in a database and the image of garments to be processed; sorting each pre-stored garment image based on the similarity values; optimizing the similarity sorting based on the first garment color and a second garment color in the pre-stored garment image; and executing a garment feature information acquisition strategy according to the optimization result.

[0008] By analyzing the similarity values ​​between pre-stored clothing images and clothing images to be processed in the database, and sorting the pre-stored clothing images based on the similarity values, an image that is relatively close to the clothing image to be processed can be obtained at the overall image level. Then, the similarity sorting is further optimized at the color level to obtain an image that is even closer to the clothing image to be processed, thereby improving the accuracy of the acquired clothing images. This can help obtain clothing feature information and solve the problem that the clothing feature information matched by existing clothing care machines is not accurate enough.

[0009] In the preferred embodiment of the control method for the above-mentioned clothing processing equipment, the step of "optimizing the similarity ranking based on the first clothing color and the second clothing color of the pre-stored clothing image" further includes: excluding the pre-stored clothing images corresponding to the second clothing color that is different from the first clothing color, so as to obtain the similarity ranking of the remaining pre-stored clothing images.

[0010] In the preferred embodiment of the control method for the aforementioned clothing processing equipment, the step of "executing a clothing feature information acquisition strategy based on the optimization result" further includes: comparing the similarity value corresponding to the first-ranked pre-stored clothing image with a preset value among the remaining pre-stored clothing images; determining whether the clothing is being processed for the first time based on the comparison result; selectively acquiring the clothing feature information corresponding to the first-ranked pre-stored clothing image based on the determination result; wherein, the first-ranked pre-stored clothing image is the pre-stored clothing image corresponding to the largest similarity value among the remaining pre-stored clothing images.

[0011] When using the above technical solution, after determining the image that is closest to the image of the clothing to be processed, it is also necessary to determine whether the clothing corresponding to the closest pre-stored clothing image is the same clothing as the clothing to be processed, and to choose whether to obtain the clothing feature information of the closest pre-stored clothing image based on the determination result, so as to avoid the situation that the obtained clothing feature information is not accurate enough.

[0012] In the preferred embodiment of the control method for the above-mentioned clothing processing equipment, the step of "analyzing the similarity value between each pre-stored clothing image in the database and the clothing image to be processed" further includes: analyzing the similarity value between each pre-stored clothing image in the database and the clothing image to be processed through an image retrieval algorithm.

[0013] With the above technical solution, regardless of the angle at which the image acquisition device captures the image, the same garment can be found, thereby improving the accuracy of the information acquired.

[0014] In the preferred embodiment of the control method for the above-mentioned clothing processing equipment, the pre-stored clothing images are all images of clothing that have been processed by the clothing processing equipment.

[0015] By adopting the above technical solution, the present invention can accurately match specific data, that is, all the specific data are the user's own family clothes, without other interfering information, if the database contains images of the clothes to be processed, that is, it can accurately match the same clothes that have been photographed before, and thus can obtain the clothing material information very accurately, especially when the clothing material includes the material ratio, it can ensure the accuracy of the information obtained.

[0016] In the preferred embodiment of the control method for the above-mentioned clothing processing equipment, the clothing feature information is the input clothing feature information; and / or the clothing feature information is clothing material information.

[0017] When the above technical solution is adopted, it is convenient to directly retrieve the input clothing material information when it is determined that it is the same piece of clothing as the clothing to be processed, so that the obtained clothing material information is very accurate.

[0018] In the preferred embodiment of the control method for the aforementioned clothing processing equipment, the step of "determining whether the clothing is being processed for the first time based on the comparison result; selectively acquiring clothing feature information corresponding to the first-ranked pre-stored clothing image based on the determination result" further includes: when the similarity value corresponding to the first-ranked pre-stored clothing image is greater than a preset value, it is determined that the clothing is not being processed for the first time, and then the clothing feature information corresponding to the first-ranked pre-stored clothing image is acquired; when the similarity value corresponding to the first-ranked pre-stored clothing image is less than or equal to a preset value, it is determined that the clothing is being processed for the first time, and then the clothing feature information corresponding to the first-ranked pre-stored clothing image is not acquired.

[0019] When the above technical solution is adopted, the clothing material information corresponding to the clothing image is only obtained when it is determined that the clothing in the closest pre-stored clothing image is the same clothing to be processed, so as to ensure the accuracy of the clothing feature information with small differences, such as clothing material information. If it is determined that they are not the same clothing, the clothing material information corresponding to the clothing image is not obtained, so as to avoid the clothing material information being inaccurate.

[0020] In the preferred embodiment of the control method for the above-mentioned clothing processing equipment, after the step of "not acquiring the clothing feature information corresponding to the first-ranked pre-stored clothing image", the control method further includes: sending a prompt message for inputting clothing feature information.

[0021] By employing the aforementioned technical solution, the material information of the garments being processed can be accurately matched, regardless of whether it's the first or subsequent processing, thus ensuring the accuracy of the garment processing procedure. Furthermore, for the same garment, the user only needs to input the material information once, eliminating the need for repeated input. For a limited number of household garments, this allows for complete automation.

[0022] In a preferred embodiment of the control method for the aforementioned clothing processing equipment, the step of "identifying the first clothing color of the clothing image to be processed" further includes: retrieving a first preset algorithm to restore the clothing image to be processed, obtaining a restored image; retrieving a second preset algorithm to analyze the restored image to obtain a primary RGB value; determining the first clothing color of the clothing image to be processed based on the primary RGB value and multiple standard RGB values ​​in a color library; and / or the second clothing color of the pre-stored clothing image is obtained based on the following method: retrieving a first preset algorithm to restore the pre-stored clothing image, obtaining a restored image; retrieving a second preset algorithm to analyze the restored image to obtain a primary RGB value; and determining the second clothing color of the pre-stored clothing image based on the primary RGB value and multiple standard RGB values ​​in a color library.

[0023] By adopting the above technical solution, it is ensured that the colors of the acquired clothing image to be processed and the pre-stored clothing image are obtained accurately in the same way, thereby avoiding errors when performing color optimization comparison, and thus ensuring the accuracy of the closest pre-stored clothing image.

[0024] In another aspect, the present invention also provides a garment processing device, characterized in that the garment processing device includes a memory and a processor, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded by the processor and run the control method of the garment processing device described in any of the above embodiments. Attached Figure Description

[0025] The preferred embodiments of the present invention are described below with reference to the accompanying drawings, in which:

[0026] Figure 1 This is the main flowchart of the control method for the clothing processing equipment of the present invention;

[0027] Figure 2 The alignment table for selecting the top 5 pre-stored clothing images with similarity values ​​and second clothing colors in the control method of the clothing processing equipment of the present invention is as follows:

[0028] Figure 3 This is an optimized reference table of pre-stored clothing images, similarity values, and second clothing colors for the control method of the clothing processing equipment of the present invention.

[0029] Figure 4 This is a possible logic diagram of the control method for the clothing processing equipment of the present invention. Detailed Implementation

[0030] First, it should be noted that the following embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention. For example, although the following embodiments are explained in conjunction with a garment care machine, this is not restrictive. The technical solution of the present invention is also applicable to washing machines, shoe washing machines, sock washing machines, etc., and this change in application does not deviate from the principles and scope of the present invention.

[0031] It should be noted that in the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, to better illustrate this invention, numerous specific details are set forth in the following detailed embodiments. Those skilled in the art should understand that this invention can be practiced without certain specific details.

[0032] To address the problem of insufficient accuracy in matching garment feature information in existing garment care machines, this invention provides a control method for a garment care machine. The garment care machine includes an image acquisition device, which can take various forms, such as a camera or a webcam. More specifically, the garment care machine may have a webcam inside its care chamber, along with a supplementary light. When garments are placed inside the care chamber, the supplementary light is activated, and the webcam captures an image of the garments to be processed.

[0033] like Figure 1 As shown, the control method of the garment care machine of the present invention includes the following steps:

[0034] Step S100: Obtain the image of the clothing to be processed.

[0035] When the user puts the clothes to be processed into the garment care machine, the image acquisition device acquires an image of the clothes to be processed.

[0036] Step S200: Identify the first clothing color in the clothing image to be processed.

[0037] Preferably, the method for identifying the first clothing color in an image of clothing to be processed according to the present invention includes the following steps:

[0038] Step S201: Call the first preset algorithm to restore the image of the clothing to be processed, and obtain the restored image.

[0039] Before step S201, a clothing detection model can be used to identify the clothing image to be processed, thereby identifying the coordinates of the clothing in the image. For example, these coordinates include the coordinates of four positions: top, bottom, left, and right. The area enclosed by these four coordinates is considered the clothing region. Then, the clothing region is cropped to remove the background of the clothing image, thus eliminating the influence of the background environment. The preferred clothing detection model is the YOLOv5 model, but other models can also be used, such as RetinaNet, FCOS, Faster R-CNN, SPPNet, SSD, and YOLO.

[0040] In step S201, the first preset algorithm is preferably the MSRCP algorithm in image enhancement. The MSRCP algorithm can accurately restore the clothing image to be processed, especially for images taken in low-light environments, making the colors in the restored image infinitely close to the true colors. Of course, as long as it can restore the clothing image to be processed, the first preset algorithm can be other algorithms, such as the MSRCR algorithm, SSR algorithm, MSR algorithm, etc.

[0041] Step S202: Call the second preset algorithm to analyze the restored image to obtain the main RGB value.

[0042] Preferably, the second preset algorithm is the K-means algorithm, which obtains the principal RGB value of the restored image. This means that the principal RGB value is one of all RGB values ​​in the restored image. Of course, other algorithms can also be used as long as they can obtain the principal RGB value of the image, such as the KNN algorithm.

[0043] Step S203: Determine the color of the clothing image to be processed based on the main RGB value and multiple standard RGB values ​​in the color library.

[0044] This invention pre-establishes a color library containing multiple standard RGB values, such as 1366 RGB color values, each with a corresponding color name. The invention can calculate the similarity between the primary RGB value and multiple standard RGB values ​​in the color library, and then use the color name of the standard RGB value corresponding to the highest similarity value as the first clothing color in the clothing image to be processed. The similarity value can be calculated using Euclidean distance or cosine distance.

[0045] Step S300: Analyze the similarity values ​​between each pre-stored clothing image in the database and the clothing image to be processed.

[0046] Preferably, the similarity values ​​between the pre-stored clothing images in the database and the clothing image to be processed can be analyzed using an image retrieval algorithm. Specifically, the feature vectors of the clothing image to be processed and the pre-stored clothing images in the database are extracted using the ReID network in the image retrieval algorithm, and then the similarity value between the feature vector of the clothing image to be processed and the feature vector of the pre-stored clothing images in the database is calculated using cosine similarity.

[0047] Since the angle at which the image acquisition device captures the clothing may be different each time a user cares for the clothing, if the same piece of clothing is stored in the database, image retrieval technology can be used to find the same piece of clothing regardless of the angle at which the image acquisition device captures the image, thereby improving the accuracy of the information obtained.

[0048] Of course, the above embodiments are not intended to limit the scope of protection of the present invention. As long as the similarity value between the pre-stored clothing image and the clothing image to be processed can be analyzed, other means can also be used for analysis.

[0049] Step S400: Sort the pre-stored clothing images by similarity based on their similarity values.

[0050] Possibly, the similarity values ​​can be sorted from largest to smallest, with higher similarity values ​​appearing earlier in the list. The corresponding pre-stored clothing images can then be sorted accordingly. For example, if the similarity values ​​of images A, B, C, D, E, and F with the image to be processed are 0.95, 0.93, 0.9, 0.89, 0.88, and 0.5, respectively, the sorting result would be: 1. 0.95; 2. 0.93; 3. 0.9; 4. 0.89; 5. 0.88; 6. 0.5. The corresponding sorting result for the pre-stored clothing images would be: 1. Image A; 2. Image B; 3. Image C; 4. Image D, Image E, and Image F. It should be noted that the sorting method used in this invention should be interpreted broadly; the sorting does not necessarily mean that the pre-stored clothing images must have a specific sequence number. For example, the sorting of pre-stored clothing images can be based on the magnitude of the similarity values.

[0051] Furthermore, pre-stored clothing images ranked before a preset value in similarity can be selected. For example, the top 5 pre-stored clothing images in similarity ranking can be selected, where the earlier the image is, the higher the similarity value, thus obtaining the 5 pre-stored clothing images most similar to the clothing to be processed. The preset value can also be other numbers, and this invention does not limit its application.

[0052] Step S500: Optimize the similarity ranking based on the first clothing color and the second clothing color of the pre-stored clothing image.

[0053] The second clothing color of the pre-stored clothing image can be obtained in various ways. Preferably, the method for obtaining the second clothing color is the same as or similar to the method for obtaining the first clothing color of the clothing image to be processed described above, and will not be repeated here. Of course, the second clothing color can also be obtained in other ways. For example, the second clothing color may be pre-input by the user and stored in the clothing care machine, and it may correspond to the pre-stored clothing image. In use, the second clothing color corresponding to the pre-stored clothing image can be directly retrieved. All of these are within the protection scope of this invention.

[0054] Preferably, the similarity ranking of pre-stored clothing images whose similarity ranking is higher than a preset value is optimized. Specifically, the optimization method is to exclude pre-stored clothing images corresponding to a second clothing color that is different from the first clothing color, in order to obtain the similarity ranking of the remaining pre-stored clothing images.

[0055] For example, such as Figure 2 As shown, the top 5 pre-stored clothing images with the highest similarity are selected. The similarity values ​​between the clothing image to be processed and the pre-stored clothing images are sorted from highest to lowest. The corresponding pre-stored clothing images and their corresponding second clothing colors are: Image A - dark gray, Image B - black, Image C - black, Image D - brown, and Image E - black. If the first clothing color of the identified clothing image to be processed is black, then dark gray and brown, which have different colors, are excluded. Figure 3 As shown, the optimized similarity ranking of the pre-stored clothing images, i.e. the similarity ranking of the remaining pre-stored clothing images, is: Image B, Image C, Image E.

[0056] Step S600: Execute the clothing feature information acquisition strategy based on the optimization results.

[0057] Step S600 further comprises: comparing the similarity value corresponding to the top-ranked pre-stored clothing image with a preset value among the remaining pre-stored clothing images; determining whether the clothing is being processed for the first time based on the comparison result; selectively acquiring clothing feature information corresponding to the top-ranked pre-stored clothing image based on the determination result; specifically, when the similarity value corresponding to the top-ranked pre-stored clothing image is greater than the preset value, it is determined that the clothing is not being processed for the first time, and the clothing feature information corresponding to the top-ranked pre-stored clothing image is acquired; when the similarity value corresponding to the top-ranked pre-stored clothing image is less than or equal to the preset value, it is determined that the clothing is being processed for the first time, and the clothing feature information corresponding to the top-ranked pre-stored clothing image is not acquired; wherein, the top-ranked pre-stored clothing image is the pre-stored clothing image corresponding to the maximum similarity value among the remaining pre-stored clothing images. Furthermore, the preset value in this step can be obtained through experiments.

[0058] Among them, the preferred clothing feature information is clothing material information, but it can also be clothing type, etc. For ease of explanation, the clothing feature information of the present invention will be introduced as clothing material information in the following text. It can be understood that the clothing material information of the present invention can include not only the material, but also the material percentage, such as 60% wool, etc.

[0059] In the example of step S500, the first-ranked pre-stored clothing image is image B. The similarity value corresponding to image B is compared with a preset value. For example, when the preset value is 0.92, since the similarity value corresponding to image B is 0.93, that is, the similarity value corresponding to image B is greater than the preset value. In this case, it is determined that the clothing is not being processed for the first time, that is, it is determined that the clothing in image B and the clothing to be processed are the same piece of clothing. At this time, the clothing material information corresponding to image B is obtained. When the first clothing color is brown, the first-ranked pre-stored clothing image is image D. Since the similarity value corresponding to image D is 0.89, and the preset value is 0.92, that is, the similarity value corresponding to image D is less than the preset value. In this case, it is determined that the clothing is being processed for the first time, that is, it is determined that the clothing in the pre-stored clothing image corresponding to the largest similarity value after optimization is not the same piece of clothing as the clothing to be processed. At this time, in order to avoid the introduction of insufficient clothing material information, the clothing material information corresponding to image B is not obtained.

[0060] In other words, after identifying the image that is closest to the image to be processed among the pre-stored clothing images after optimization and sorting, it is also necessary to determine whether the clothing corresponding to the closest pre-stored clothing image is the same clothing as the clothing to be processed. Only when it is determined that they are the same clothing will the clothing material information corresponding to the clothing image be obtained, so as to ensure the accuracy of the clothing feature information such as clothing material information that are only slightly different.

[0061] Preferably, the clothing material information corresponding to the first-ranked pre-stored clothing image is the input clothing material information.

[0062] Typically, each garment has a care label. Users can input the fabric information from the care label into the garment care machine, such as through a smart terminal app connected to the machine or through the machine's control panel. For a more specific example, if the care label indicates 60% wool, the user inputs "60% wool" into the garment care machine. After receiving the input fabric information, the machine stores it and associates it with a pre-stored garment image, storing it in a database. This allows for direct retrieval of the fabric information when it is determined that the image matches the garment to be processed, resulting in highly accurate fabric information.

[0063] Furthermore, if the material information of the garment corresponding to the first-ranked pre-stored garment image is not retrieved, a prompt message for inputting the garment material information is sent. That is, to ensure the accuracy of the retrieved material information, the user is reminded that this is the first time the garment is being processed, and a prompt message for inputting the material information is sent. After the user inputs the material information, the garment care machine retrieves and stores it, and associates it with the garment image acquired by the image acquisition device. This allows the material information to be directly retrieved the next time the same garment is processed, without needing to be entered again.

[0064] Preferably, the pre-stored clothing images are all images of clothing that have been processed by a clothing care machine.

[0065] If the database is only used to store images of clothing belonging to one's own family, each time a different garment is treated by the garment care machine, a different garment image is stored in the database. These garment images can be acquired using the image acquisition device described above. Specifically, each pre-stored garment image in the database corresponds to garment material information; that is, each pre-stored garment image is associated with corresponding garment material information. For example, a mapping table is established between pre-stored garment images and garment material information. By searching for a pre-stored garment image, the garment material information corresponding to that pre-stored garment image can be determined. The method for associating pre-stored garment images with corresponding garment material information is not limited to the above embodiments; any method that can associate the two is within the scope of protection of this invention.

[0066] Since all the pre-stored clothing images in the database are images of clothing that have been treated by the clothing care machine, the clothing can be matched with the same clothing that was previously photographed during the matching process. The matching process is an exact match rather than an approximate match. In particular, compared with the approximate match scheme that stores a large amount of standard data in the database, the technical solution of this invention can accurately match the same clothing, and thus can obtain clothing material information very accurately. Especially when the clothing material includes the material ratio, it can ensure the accuracy of the information obtained.

[0067] Furthermore, after obtaining clothing material information, such as when it is determined that the clothing is not being processed for the first time, the clothing feature information corresponding to the first-ranked pre-stored clothing image is obtained, or when a prompt message for inputting clothing material information is sent, the clothing material information input by the user is obtained, and a clothing processing program is recommended based on that clothing material information.

[0068] By acquiring accurate information about the garment's material, the machine can recommend a suitable garment care procedure for the user's reference. The machine may execute the procedure if the user selects a recommended procedure or if the user does not confirm within a preset time. Different garment materials correspond to different procedures; once the material information is determined, the procedure can be specified. The procedure can be customized to suit specific needs.

[0069] The aforementioned control method ensures accurate matching of fabric material information for all garments, whether processing them for the first time or not, thus guaranteeing the precision of the garment processing procedure. Furthermore, for the same garment, the user only needs to input the fabric material information once, eliminating the need for repeated input. For a limited number of household garments, this allows for complete automation.

[0070] The garment care machine of the present invention is especially designed for home users. While achieving automated care, it can also ensure the accuracy of the matched garment material information, thereby achieving precise care.

[0071] Furthermore, the strategies for acquiring clothing feature information are not limited to the above-described implementation methods. In less advanced cases, for example, clothing feature information corresponding to the first-ranked pre-stored clothing image can be directly acquired. Those skilled in the art can adjust the acquisition strategy, and these are all within the protection scope of this invention.

[0072] Furthermore, the specific implementation of optimizing the similarity ranking based on the first and second clothing colors is not limited to the one mentioned above. For example, a pre-stored clothing image corresponding to the second clothing color that is the same as the first clothing color can also be extracted to obtain the similarity ranking of the extracted pre-stored clothing images. These implementations do not deviate from the principle of the present invention and are all within the protection scope of the present invention.

[0073] like Figure 2 As shown, the possible complete process of the garment processing device of the present invention is as follows:

[0074] Step S701: Obtain the image of the clothing to be processed.

[0075] Step S702: Identify the first clothing color in the clothing image to be processed.

[0076] Step S703: Analyze the similarity values ​​between each pre-stored clothing image in the database and the clothing image to be processed using an image retrieval algorithm.

[0077] Step S704: Sort the pre-stored clothing images by similarity based on their similarity values.

[0078] Step S705: Select the top 10 pre-stored clothing images with the highest similarity values.

[0079] Step S706: Identify the second clothing color of the top 10 pre-stored clothing images with the highest similarity values.

[0080] Step S707: Among the top 10 pre-stored clothing images, exclude the pre-stored clothing images corresponding to the second clothing color that is different from the first clothing color, to obtain the remaining pre-stored clothing images sorted.

[0081] Step S708: Compare the similarity value of the first image in the remaining pre-stored clothing images with a preset value.

[0082] Step S709: Determine if the similarity value is greater than the preset value. If yes, proceed to step S710; otherwise, proceed to step S711.

[0083] Step S710: Use the clothing material corresponding to the pre-saved clothing image as the clothing material for this care, and then execute step S712.

[0084] Step S711: Remind the user that this is the first time the garment has been cared for, and prompt the user to enter the garment material to obtain the garment material, and then proceed to step S712.

[0085] Step S712: Recommend a care procedure based on the fabric material.

[0086] In addition, the present invention provides a garment processing device, which includes a memory and a processor. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to perform the control method of the garment processing device in the foregoing embodiments.

[0087] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles 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 such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A control method for a garment processing device, characterized in that, The control method includes: Obtain the image of the clothing to be processed; Identify the first clothing color in the clothing image to be processed; Analyze the similarity values ​​between each pre-stored clothing image in the database and the clothing image to be processed; The pre-stored clothing images are sorted by similarity based on the similarity values. The similarity ranking is optimized based on the first clothing color and the second clothing color of the pre-stored clothing image; Based on the optimization results, a strategy for acquiring clothing feature information is implemented. The step of "optimizing the similarity ranking based on the first clothing color and the second clothing color of the pre-stored clothing image" further includes: Exclude the pre-stored clothing images corresponding to the second clothing color that is different from the first clothing color, and obtain the similarity ranking of the remaining pre-stored clothing images; The step of "implementing a clothing feature information acquisition strategy based on the optimization results" further includes: Among the remaining pre-stored clothing images, the similarity value corresponding to the first-ranked pre-stored clothing image is compared with a preset value; Determine whether the clothing has undergone initial processing based on the comparison results; Based on the judgment result, selectively obtain the clothing feature information corresponding to the first-ranked pre-stored clothing image; Among them, the first-ranked pre-stored clothing image is the pre-stored clothing image corresponding to the largest similarity value among the remaining pre-stored clothing images.

2. The control method for the garment processing equipment according to claim 1, characterized in that, The step of "analyzing the similarity values ​​between each pre-stored clothing image in the database and the clothing image to be processed" further includes: The similarity values ​​between each pre-stored clothing image in the database and the clothing image to be processed are analyzed using an image retrieval algorithm.

3. The control method for the garment processing equipment according to claim 1, characterized in that, The pre-stored clothing images are all images of clothing that have been processed by the clothing processing equipment.

4. The control method for the garment processing equipment according to any one of claims 1 to 3, characterized in that, The clothing feature information is the input clothing feature information; and / or The clothing feature information refers to the clothing material information.

5. The control method for the garment processing equipment according to claim 1, characterized in that, "Determine whether the clothing has undergone initial processing based on the comparison results;" The step of "selectively obtaining the clothing feature information corresponding to the first-ranked pre-stored clothing image based on the judgment result" further includes: When the similarity value of the first-ranked pre-stored clothing image is greater than the preset value, it is determined that the clothing is not processed for the first time, and the clothing feature information corresponding to the first-ranked pre-stored clothing image is obtained. If the similarity value of the first-ranked pre-stored clothing image is less than or equal to a preset value, the clothing is considered to be being processed for the first time, and the clothing feature information corresponding to the first-ranked pre-stored clothing image is not obtained.

6. The control method for the garment processing equipment according to claim 5, characterized in that, After the step of "not acquiring the clothing feature information corresponding to the first-ranked pre-stored clothing image", the control method further includes: Send a prompt message asking for input of clothing feature information.

7. The control method for the garment processing equipment according to claim 1, characterized in that, The step of "identifying the first clothing color of the clothing image to be processed" further includes: The first preset algorithm is invoked to restore the image of the clothing to be processed, and the restored image is obtained; The second preset algorithm is invoked to analyze the restored image to obtain the main RGB values; The first clothing color of the clothing image to be processed is determined based on the primary RGB value and multiple standard RGB values ​​in the color library; and / or The second clothing color of the pre-stored clothing image is obtained based on the following method: The first preset algorithm is invoked to restore the pre-stored clothing image, resulting in the restored image; The second preset algorithm is invoked to analyze the restored image to obtain the main RGB values; The second clothing color of the pre-stored clothing image is determined based on the main RGB value and multiple standard RGB values ​​in the color library.

8. A garment processing device, characterized in that, The garment processing device includes a memory and a processor, the memory being adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to perform the control method of the garment processing device according to any one of claims 1 to 7.

Images