Garment steamer ironing methods, devices, garment steamers, storage media and electronic devices

CN117689920BActive Publication Date: 2026-11-17HAIER YOUJIA INTELLIGENT TECH (BEIJING) CO LTD +2
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211049158.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-30
Publication Date
2026-11-17
Estimated Expiration
2042-08-30

AI Technical Summary

Technical Problem

[0005]本申请提供一种挂烫机熨烫方法、装置、挂烫机、存储介质及电子装置,用以解决现有技术中低频熨烫标数量非常少且不均衡,导致熨烫图标识别准确性较低的缺陷,实现以设置多种检测过程,对熨烫图标进行目标检测识别,从而提高水洗唛图像中熨烫图标的识别准确率,为挂烫机生成更为准确的熨烫参数

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117689920B_ABST
    Figure CN117689920B_ABST
Patent Text Reader

Abstract

This application discloses a garment steamer ironing method, apparatus, garment steamer, storage medium, and electronic device, relating to the field of smart home / intelligent home technology. The garment steamer ironing method includes: performing image recognition on a care label image; performing target detection based on the image recognition results; when determining that the garment care implementation type is ironable, performing ironing information recognition on the care label image; and obtaining one or more corresponding ironing parameter recognition methods based on the ironing information recognition results to obtain the garment steamer's ironing parameters through the ironing parameter recognition methods; generating an ironing mode corresponding to the garment steamer based on the ironing parameters; and controlling the garment steamer according to the ironing mode. This application avoids the problem of poor recognition performance caused by insufficient training samples in target detection models, thus improving the recognition accuracy of ironing information in care label images.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of smart home technology, and in particular to a garment steamer ironing method, apparatus, garment steamer, storage medium and electronic device. Background Technology

[0002] With the development of smart homes, target detection technology is increasingly being applied to garment steamers. The target detection method for the wash label on garment steamers mainly involves labeling the wash label training data with bounding boxes and categories. Then, deep learning target detection methods, such as ResNet, ResNext, and ResNest, are used to train the model. This enables the detection of the wash label's bounding box position and category information in the image, and then, based on the category information, the current ironing parameters of the garment steamer are determined.

[0003] Due to the inherent nature of deep learning algorithms, each care label category requires at least thousands of labeled data points, with a relatively balanced number of labels across categories. However, during actual training data collection, statistics revealed significant differences in the distribution of label numbers across categories. High-frequency categories could have thousands of labels, while most categories had fewer than a hundred, exhibiting a severe long-tail effect. This resulted in the target detection algorithm applied to garment steamers failing to accurately identify ironing information.

[0004] Therefore, there is an urgent need for a garment steamer ironing method, device, garment steamer, storage medium, and electronic device to solve the above problems. Summary of the Invention

[0005] This application provides a garment steamer ironing method, apparatus, garment steamer, storage medium, and electronic device to address the shortcomings of existing technologies where the number of low-frequency ironing marks is very small and uneven, resulting in low accuracy of ironing mark recognition. It achieves target detection and recognition of ironing marks by setting multiple detection processes, thereby improving the recognition accuracy of ironing marks in care label images and generating more accurate ironing parameters for the garment steamer.

[0006] This application provides a garment steamer ironing method, including:

[0007] Image recognition is performed on the water care label image, and target detection is performed based on the image recognition results;

[0008] When the garment care implementation type is determined to be ironable, the ironing information of the care label image is identified, and one or more corresponding ironing parameter identification methods are obtained based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods.

[0009] Based on the ironing parameters, an ironing mode corresponding to the garment steamer is generated, and the garment steamer is controlled according to the ironing mode.

[0010] According to the ironing method of the garment steamer provided in this application, the method further includes:

[0011] When the garment care implementation type is determined to be non-ironable, the shape recognition of the care label in the care label image is performed, and based on the shape recognition result, it is determined whether the care label in the care label image is a non-ironable icon.

[0012] If the care label is not an "iron-free" icon, the garment care information corresponding to the care label is determined based on the shape recognition result of the care label, and the garment care information is displayed through the garment steamer. The garment care information includes one or more of the following: do not wash, do not bleach, and do not tumble dry.

[0013] According to the ironing method of a garment steamer provided in this application, the step of determining whether the care label in the care label image is a non-ironable icon based on the shape recognition result includes:

[0014] If the care label image does not include any preset care label shape, the care label in the care label image is determined to be a non-ironing icon, wherein the preset care label shape includes one or more combinations of circles, triangles and rectangles.

[0015] According to the ironing method of a garment steamer provided in this application, the image recognition of the care label image includes:

[0016] Obtain an image of the care label on the target garment;

[0017] The care label image is input into the first recognition model to identify the garment care method, and the garment care implementation type output by the first recognition model is obtained. The first recognition model is trained from sample care label images labeled with garment care implementation type tags.

[0018] According to the garment steamer ironing method provided in this application, the first recognition model is trained through the following steps:

[0019] Acquire images of multiple sample washing labels;

[0020] A training sample set is constructed by labeling each of the sample care label images with a corresponding garment care implementation type label, wherein the garment care implementation type label includes at least an ironable label and a non-ironable label;

[0021] The first recognition model is obtained by training the convolutional neural network using the training sample set.

[0022] According to the garment steamer ironing method provided in this application, when determining that the garment care implementation type is ironable, the method involves identifying ironing information from the care label image and, based on the ironing information identification result, obtaining one or more corresponding ironing parameter identification methods to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods, including:

[0023] When the garment care implementation type is determined to be ironable, the text information of the care label image is recognized to obtain the corresponding care label text content recognition result;

[0024] If the text content recognition result of the care label does not contain any text information, the care label image is input into the second recognition model to recognize ironing information, and ironing icon information output by the second recognition model is obtained. The second recognition model is trained by sample care label images marked with ironing icon labels.

[0025] Based on the ironing icon information, the ironing parameters of the garment steamer are generated.

[0026] According to the ironing method of the garment steamer provided in this application, the method further includes:

[0027] If the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule to obtain the ironing parameters of the garment steamer.

[0028] According to the ironing method of the garment steamer provided in this application, the method further includes:

[0029] If it is determined that the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule, and the image of the care label is input into the second recognition model for ironing information recognition.

[0030] Based on the category mapping results and the ironing icon information, the ironing parameters of the garment steamer are obtained.

[0031] According to the ironing method of a garment steamer provided in this application, after performing image recognition on the care label image and target detection based on the image recognition result, the method further includes:

[0032] The area corresponding to the care label in the care label image is cropped to obtain a target image, which is then used to identify ironing information or shape.

[0033] This application also provides a garment steamer ironing device, including:

[0034] The garment care implementation type detection module is used to perform image recognition on care label images and target detection based on the image recognition results;

[0035] The ironing information detection module is used to identify ironing information in the care label image when the garment care implementation type is determined to be ironable, and to obtain one or more corresponding ironing parameter identification methods based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods.

[0036] The control module is used to generate an ironing mode corresponding to the garment steamer based on the ironing parameters, and to control the garment steamer according to the ironing mode.

[0037] This application also provides a computer-readable storage medium comprising a stored program, wherein the program, when executed, implements the garment steamer ironing method as described above.

[0038] This application also provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the ironing method of any of the above-described garment steamers through the computer program.

[0039] The garment steamer ironing method, apparatus, steamer, storage medium, and electronic device provided in this application first identify the garment care method from the care label image. When the garment care method is determined to be ironable, ironing information is then identified from the care label image. Based on the ironing information identification results, ironing parameters for controlling the garment steamer are generated. Compared with the prior art, by performing multi-stage detection and identification on the care label image, the problem of poor recognition effect due to insufficient training samples in the target detection model is avoided, thus improving the recognition accuracy of ironing information in the care label image. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of the hardware environment for an interaction method of a smart device according to an embodiment of this application;

[0043] Figure 2A flowchart illustrating the ironing method using a garment steamer provided in this application;

[0044] Figure 3 A schematic diagram of the ironing device for the garment steamer provided in this application;

[0045] Figure 4 A schematic diagram of the electronic device provided in this application. Detailed Implementation

[0046] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0047] It should be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0048] According to one aspect of the embodiments of this application, a garment steamer ironing method is provided. This garment steamer ironing method is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned garment steamer ironing method can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0049] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0050] In existing washing label ironing information recognition models, the number of categories in the collected washing and ironing label training data varies greatly, resulting in extremely poor recognition performance for low-frequency categories. Furthermore, during the training process of some recognition models, due to the lack of labeling for other categories of washing labels besides ironing labels, labels similar to non-ironing labels, such as do not dry clean, do not bleach, and do not tumble dry, are easily misidentified as non-ironing labels when the recognition model identifies them. In other words, the model easily misidentifies similar non-ironing categories as non-ironing categories.

[0051] Figure 2 The flowchart illustrates the ironing method using a garment steamer provided in this application, as follows: Figure 2 As shown, this application provides a garment steamer ironing method, including:

[0052] Step 101: Perform image recognition on the wash label image and target detection based on the image recognition results.

[0053] In this application, the image of the care label of the target garment can first be acquired through a camera mounted on the garment steamer or through a user's mobile terminal (e.g., a mobile phone or tablet). Then, the acquired care label image is preliminarily identified, i.e., the garment care method is identified. In one embodiment, the care label image can be identified using a pre-trained target recognition model (i.e., a first recognition model). During training, this model only needs to be trained using two types of ironing labels: ironable and non-ironable, thus quickly completing the model training. This allows the trained model to simply output whether the garment is ironable or not after acquiring the care label image.

[0054] Step 102: When the garment care implementation type is determined to be ironable, the ironing information of the care label image is identified, and one or more corresponding ironing parameter identification methods are obtained based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods.

[0055] In this application, in step 101, when determining that the garment care type of the target garment is ironable, it is necessary to further recognize the ironing text information in the care label image. Because existing ironing information recognition models are primarily trained on sample images labeled with ironing type tags, these models have poor performance in recognizing ironing text information. Furthermore, the number of sample images containing ironing text information is relatively small, and the number used in typical training processes is limited, resulting in the model's inability to accurately identify the ironing information in such images. Therefore, in this application, after determining that the garment care implementation type is ironable, it is necessary to identify ironing information in the care label image, that is, to identify the text information in the care label image. If the identification result does not contain text information (i.e., it does not contain descriptive information about ironing, such as ironing temperature parameters and ironing time, etc.), the ironing icon containing text descriptions can be defined as a low-frequency category. Generally, the number of such ironing icons is small, both on the garment and in the training samples. Then, the ironing icon can be identified by the pre-trained ironing icon recognition model (i.e., the second recognition model), thereby obtaining the ironing parameters corresponding to the target garment. Since the ironing icon does not contain text about ironing parameters, the input data when the ironing icon recognition model is used for identification can be considered as high-frequency classification data. That is, this type of data is a large number of sample data during the model training stage, which ensures that the model can output a high accuracy when identifying such images. In one embodiment, if the ironing information recognition result contains text content, the text content and the ironing icon can be recognized separately. By combining the two different ironing parameter recognition methods, a more accurate ironing parameter recognition result can be obtained. For example, the ironing icon recognition result is that it can be ironed at high temperature, and the text content recognition result is 200 degrees Celsius. Based on these two recognition results, the garment steamer can be adjusted to the high temperature setting first, and then the ironing temperature can be set to 200 degrees Celsius.

[0056] Step 103: Based on the ironing parameters, generate the ironing mode corresponding to the garment steamer, and control the garment steamer according to the ironing mode.

[0057] In this application, after determining that the target garment is ironable, the ironing icon is re-identified using an ironing icon recognition model, thereby outputting the ironing parameters corresponding to the ironing icon. These ironing parameters are then sent to the control unit of the garment steamer to complete the ironing control of the garment steamer. In one embodiment, for ironing icons containing ironing text information, a pre-built mapping rule database can be used to match the text information in the ironing icon with the database to obtain the corresponding mapping result. This allows the ironing icon recognition model and the mapping rule database to simultaneously send their respective outputs to the garment steamer for controlling the ironing mode. For example, the ironing icon recognition model might output a maximum ironing temperature of 110 degrees Celsius (corresponding to a "■" symbol in the ironing icon, which is a solid black dot). The text content below the ironing icon can be used to generate corresponding ironing time parameters through the mapping rule database (e.g., text information about the duration below the ironing icon). When the garment steamer receives these two ironing parameters, it automatically switches to the corresponding ironing mode.

[0058] The garment steamer ironing method provided in this application first identifies the garment care method in the care label image. When the garment care method is determined to be ironable, the ironing information in the care label image is then identified. Based on the ironing information identification results, ironing parameters for controlling the garment steamer are generated. Compared with the prior art, by performing multi-stage detection and identification on the care label image, the problem of poor recognition effect caused by insufficient training samples in the target detection model is avoided, thereby improving the recognition accuracy of ironing information in the care label image.

[0059] Based on the above embodiments, the method further includes:

[0060] When the garment care implementation type is determined to be non-ironable, the shape recognition of the care label in the care label image is performed, and based on the shape recognition result, it is determined whether the care label in the care label image is a non-ironable icon.

[0061] If the care label is not an "iron-free" icon, the garment care information corresponding to the care label is determined based on the shape recognition result of the care label, and the garment care information is displayed through the garment steamer. The garment care information includes one or more of the following: do not wash, do not bleach, and do not tumble dry.

[0062] In this application, since most garment care labels feature an "iron-safe" icon, indicating that some garments made of special materials are not suitable for ironing, the training process for the model (i.e., the first recognition model) suffers from a shortage of samples for this category (i.e., the "iron-safe" icon). This results in inconsistent accuracy when the model identifies these "iron-safe" icons. For example, due to the limited sample size, the model may incorrectly identify care types such as "do not dry clean," "do not bleach," and "do not tumble dry" as "iron-safe," because these icons contain an "×" symbol, leading to misidentification. Therefore, when the model outputs an "iron-safe" garment care type, this output should be defined as a pending result, indicating that it is not suitable and requires further evaluation. Furthermore, when it is determined that the infeasibility type of the care label is not an "iron-free" icon, the garment care infeasibility information is determined based on the shape of the care label, such as "do not wash" or "do not bleach," and corresponding information, such as voice and text information, is generated and displayed through the voice module or display module of the garment steamer.

[0063] Based on the above embodiments, determining whether the care label in the care label image is a non-ironing icon based on the shape recognition result includes:

[0064] If the care label image does not include any preset care label shape, the care label in the care label image is determined to be a non-ironing icon, wherein the preset care label shape includes one or more combinations of circles, triangles and rectangles.

[0065] In this application, when the output result of the first recognition model is an "unfeasible" type, the care label identified in the image is temporarily designated as an "iron-free" icon. This requires performing Hough circle, triangle, and rectangle detection on the care label. If no circle (corresponding to dry cleaning), triangle (corresponding to bleaching), or rectangle (corresponding to tumble drying) is found, the "unfeasible" type of the care label can be determined as an "iron-free" icon. Corresponding "iron-free" notification information, such as voice or text messages, is then generated and sent to the garment steamer or the user's mobile terminal to inform the user. If any one of the circles, triangles, or rectangles is present in the care label, it indicates that the care label represents other unfeasible garment care types.

[0066] Based on the above embodiments, the image recognition of the wash label image includes:

[0067] Obtain an image of the care label on the target garment;

[0068] The care label image is input into the first recognition model to identify the garment care method, and the garment care implementation type output by the first recognition model is obtained. The first recognition model is trained from sample care label images labeled with garment care implementation type tags.

[0069] In this application, a first recognition model is constructed by training a convolutional neural network. The training process of this model only requires two types of ironing icons, namely ironable and non-ironable, as sample data, thereby quickly completing the training of the model.

[0070] Based on the above embodiments, the first recognition model is trained through the following steps:

[0071] Acquire images of multiple sample washing labels;

[0072] A training sample set is constructed by labeling each of the sample care label images with a corresponding garment care implementation type label, wherein the garment care implementation type label includes at least an ironable label and a non-ironable label;

[0073] The first recognition model is obtained by training the convolutional neural network using the training sample set.

[0074] In this application, the large number of ironable icons makes the model highly accurate in recognizing this category. As for non-ironable icons, although the number of sample data for this type is small, this application will further detect the non-ironable icons identified by the first recognition model through shape detection, thereby improving the recognition accuracy of ironable icons.

[0075] Based on the above embodiments, when the garment care implementation type is determined to be ironable, ironing information is identified in the care label image, and one or more corresponding ironing parameter identification methods are obtained based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods, including:

[0076] When the garment care implementation type is determined to be ironable, the text information of the care label image is recognized to obtain the corresponding care label text content recognition result;

[0077] If the text content recognition result of the care label does not contain any text information, the care label image is input into the second recognition model to recognize ironing information, and ironing icon information output by the second recognition model is obtained. The second recognition model is trained by the sample care label image of the ironing icon label.

[0078] Based on the ironing icon information, the ironing parameters of the garment steamer are generated.

[0079] In this application, Optical Character Recognition (OCR) technology can be used to recognize text information in the area corresponding to the ironable icon obtained by the first recognition model. When the area does not contain text content, the ironable icon is recognized again by the second recognition model to obtain the ironing icon information. For example, if the ironing icon contains two "■" symbols, the output of the second recognition model is that the maximum ironing temperature is 150 degrees Celsius. Since there are a large number of such ironing icons, the second recognition model can accurately complete the recognition task after being trained based on these sample data.

[0080] Based on the above embodiments, the method further includes:

[0081] If the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule to obtain the ironing parameters corresponding to the garment steamer.

[0082] In this application, category mapping is performed according to the preset mapping rules of OCR regular expressions. When the recognition result of the text content of the care label can be mapped to the corresponding category through the preset ironing rules, the ironing parameters are obtained. If it cannot be mapped, it means that the text content is not related to ironing.

[0083] Based on the above embodiments, the method further includes:

[0084] If it is determined that the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule, and the image of the care label is input into the second recognition model for ironing information recognition.

[0085] Based on the category mapping results and the ironing icon information, the ironing parameters of the garment steamer are obtained.

[0086] In this application, for cases where the care label image contains text information, two ironing parameter recognition methods can be combined. That is, the recognition result of the text content of the care label is mapped to the category of the preset ironing rules, and the care label image is input into the second recognition model for ironing information recognition, thereby obtaining the recognition results corresponding to the two ironing parameter recognition methods. Finally, the two recognitions are combined and merged to generate the ironing mode corresponding to the garment steamer.

[0087] Based on the above embodiments, after performing image recognition on the wash label image and target detection based on the image recognition result, the method further includes:

[0088] The area corresponding to the care label in the care label image is cropped to obtain a target image, which is then used to identify ironing information or shape.

[0089] In this application, after the first recognition model completes the initial recognition of the care label image, the region of the ironing icon in the care label image can be obtained according to the output of the first recognition model. Then, by cropping the region, the image containing only the ironing icon is used as the target image for subsequent target recognition and detection, so as to reduce interference in the recognition process.

[0090] In one embodiment, the ironing method of the garment steamer of this application is described in general, and the specific steps are as follows:

[0091] Step 101: Divide all the acquired water washing and ironing icon training data into two categories: ironable and non-ironable (the difference lies in whether there is an "×" symbol in the middle of the ironing icon). Then, label them according to the object detection method and train them using the object detection method to obtain the first recognition model for recognizing the two types of targets: ironable and non-ironable.

[0092] Step 102: Recognize the care label image using the first recognition model. If the recognition result is "not ironable", proceed to step 103; if the recognition result is "ironable", proceed to step 106.

[0093] Step 103: Crop the unironable icon into a smaller image (i.e., the target image) according to the frame coordinates (x,y,w,h). Then perform traditional circle detection, triangle detection, and rectangle detection on the smaller image. If any of the above shapes exist, proceed to step 104; if none of the above shapes exist, proceed to step 105.

[0094] Step 104: If the detected small image is an icon that cannot be dry cleaned, bleached, or turned over to dry, that is, the small image contains a circle, triangle, or rectangle, it means that the icon is not an unironable icon. Therefore, the information of the icon is not output and there is no need to adjust the ironing mode of the garment steamer.

[0095] Step 105: If the detected small image is indeed an unironable icon, proceed to step 111.

[0096] Step 106: Crop the ironable icon into a smaller image according to the frame coordinates (x,y,w,h), and perform OCR recognition on the smaller image. Two situations will occur: if the OCR recognizes text (including numerical content), proceed to step 107; or if the OCR does not recognize any text, proceed to step 110.

[0097] Step 107: Perform category mapping according to the mapping rules of OCR regular expressions. There are two possible situations: if the category can be mapped, proceed to step 108; if the category cannot be mapped, proceed to step 109.

[0098] Step 108: Generate corresponding ironing parameters based on the mapped category. For example, if the text content is 80-120 degrees Celsius, it can be mapped to the 80-120 temperature parameter (which is an output low-frequency category), proceeding to step 111.

[0099] Step 109: For categories that do not exist in the mapping rules, no output results need to be generated. For example, if the text content is "199", it cannot be matched with any category by regular expression, so no output is generated.

[0100] Step 110: When the OCR cannot recognize any text, the ironable icon is directly recognized by the second recognition model, and the corresponding ironing parameters are output.

[0101] Step 111: Combine the outputs of Step 108 and Step 110 and send them to the garment steamer to execute the corresponding ironing mode.

[0102] The garment steamer ironing device provided in this application is described below. The garment steamer ironing device described below can be referred to in correspondence with the garment steamer ironing method described above.

[0103] Figure 3 This is a schematic diagram of the ironing device for the garment steamer provided in this application, as shown below. Figure 3 As shown, this application provides a garment steamer ironing device, including a garment care implementation type detection module 301, an ironing information detection module 302, and a control module 303. The garment care implementation type detection module 301 performs image recognition on a care label image and performs target detection based on the image recognition result. The ironing information detection module 302, when determining that the garment care implementation type is ironable, performs ironing information recognition on the care label image and obtains one or more corresponding ironing parameter recognition methods based on the ironing information recognition result, so as to obtain the ironing parameters of the garment steamer through the ironing parameter recognition methods. The control module 303 generates an ironing mode corresponding to the garment steamer based on the ironing parameters and controls the garment steamer according to the ironing mode.

[0104] The garment steamer ironing device provided in this application first identifies the garment care method in the care label image. When it is determined that the garment care method is ironable, the ironing information in the care label image is then identified. Based on the ironing information identification result, ironing parameters for controlling the garment steamer are generated. Compared with the prior art, by performing multi-stage detection and identification on the care label image, the problem of poor recognition effect caused by insufficient training samples in the target detection model is avoided, thereby improving the recognition accuracy of ironing information in the care label image.

[0105] Based on the above embodiments, the device further includes a care label shape detection module and a garment care prompt module. The care label shape detection module is used to perform shape recognition on the care label in the care label image when it is determined that the garment care implementation type is non-ironable, and determine whether the care label in the care label image is a non-ironable icon based on the shape recognition result. The garment care prompt module is used to determine the garment care non-implementation information corresponding to the care label based on the shape recognition result if the care label is not a non-ironable icon, and display the garment care non-implementation information through the garment steamer. The garment care non-implementation information includes one or more of the following: not washable, not bleachable, and not tumble dry.

[0106] Based on the above embodiments, the care label shape detection module is specifically used to determine that the care label in the care label image is a non-ironing icon if the care label image does not include any preset care label shape, wherein the preset care label shape includes one or more combinations of circles, triangles and rectangles.

[0107] Based on the above embodiments, the garment care implementation type detection module includes an image acquisition unit and a first recognition unit. The image acquisition unit is used to acquire the care label image of the target garment. The first recognition unit is used to input the care label image into a first recognition model to identify the garment care method and obtain the garment care implementation type output by the first recognition model. The first recognition model is trained by sample care label images labeled with garment care implementation type tags.

[0108] Based on the above embodiments, the device further includes a sample image acquisition module, a training set construction module, and a training module. The sample image acquisition module is used to acquire multiple sample care label images. The training set construction module is used to label each of the sample care label images with a corresponding garment care implementation type label to construct a training sample set. The garment care implementation type label includes at least an ironable label and a non-ironable label. The training module is used to train a convolutional neural network using the training sample set to obtain the first recognition model.

[0109] Based on the above embodiments, the ironing information detection module includes a text recognition unit, a second recognition unit, and an ironing parameter generation unit. The text recognition unit is used to recognize text information in the care label image when the garment care implementation type is determined to be ironable, obtaining the corresponding care label text content recognition result. The second recognition unit is used to input the care label image into a second recognition model for ironing information recognition if the care label text content recognition result does not contain any text information, obtaining ironing icon information output by the second recognition model. The second recognition model is trained from sample care label images with ironing icon labels. The ironing parameter generation unit is used to generate ironing parameters for the garment steamer based on the ironing icon information.

[0110] Based on the above embodiments, the device further includes an ironing parameter mapping module, which is used to map the text content recognition result of the wash label to a preset ironing rule if the text content recognition result of the wash label contains text information, and obtain the ironing parameters of the garment steamer.

[0111] Based on the above embodiments, the ironing information detection module is further configured to: when it is determined that the text content recognition result of the care label contains text information, map the text content recognition result of the care label to a preset ironing rule, and input the care label image into a second recognition model for ironing information recognition; and obtain the ironing parameters of the garment steamer based on the category mapping result and the ironing icon information.

[0112] Based on the above embodiments, the device further includes an image acquisition module, used to perform image cropping processing on the area corresponding to the wash label in the wash label image to obtain a target image, so as to perform ironing information recognition or shape recognition on the target image.

[0113] This application also provides a garment steamer, including the garment steamer ironing device described in the above embodiments, as well as a steam heater, a casing, a water tank, a steam nozzle, a steam duct, and a retractable support. The garment steamer provided in this application, through its ironing device, identifies the garment care method from the care label image. When the garment care method is determined to be ironable, ironing information is then identified from the care label image. Based on the ironing information identification result, ironing parameters for controlling the garment steamer are generated. Compared to existing technologies, by performing multi-stage detection and identification on the care label image, the problem of poor recognition performance due to insufficient training samples in the target detection model is avoided, thus improving the accuracy of ironing information recognition in the care label image.

[0114] Figure 4 A schematic diagram of the structure of the electronic device provided in this application, such as Figure 4As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a garment steamer ironing method, which includes: performing image recognition on a care label image and performing target detection based on the image recognition result; when determining that the garment care implementation type is ironable, performing ironing information recognition on the care label image, and obtaining one or more corresponding ironing parameter recognition methods based on the ironing information recognition result, so as to obtain the ironing parameters of the garment steamer through the ironing parameter recognition method; generating an ironing mode corresponding to the garment steamer based on the ironing parameters, and controlling the garment steamer according to the ironing mode.

[0115] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the garment steamer ironing method provided by the above methods. The method includes: performing image recognition on a care label image and performing target detection based on the image recognition result; when determining that the garment care implementation type is an ironable type, performing ironing information recognition on the care label image and obtaining one or more corresponding ironing parameter recognition methods according to the ironing information recognition result, so as to obtain the ironing parameters of the garment steamer through the ironing parameter recognition method; generating an ironing mode corresponding to the garment steamer based on the ironing parameters, and controlling the garment steamer according to the ironing mode.

[0117] In another aspect, this application also provides a computer-readable storage medium, which includes a stored program, wherein the program, when running, executes the garment steamer ironing method provided by the above methods. The method includes: performing image recognition on a care label image and performing target detection based on the image recognition result; when determining that the garment care implementation type is an ironable type, performing ironing information recognition on the care label image, and obtaining one or more corresponding ironing parameter recognition methods according to the ironing information recognition result, so as to obtain the ironing parameters of the garment steamer through the ironing parameter recognition methods; generating an ironing mode corresponding to the garment steamer based on the ironing parameters, and controlling the garment steamer according to the ironing mode.

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for ironing with a garment steamer, characterized in that, include: Image recognition is performed on the care label image to determine the garment care application type; When the garment care implementation type is determined to be ironable, the ironing information of the care label image is identified, and one or more corresponding ironing parameter identification methods are obtained based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods. Based on the ironing parameters, an ironing mode corresponding to the garment steamer is generated, and the garment steamer is controlled according to the ironing mode; The method further includes: When the garment care implementation type is determined to be non-ironable, the shape recognition of the care label in the care label image is performed, and based on the shape recognition result, it is determined whether the care label in the care label image is a non-ironable icon. If the care label is not an "iron-free" icon, the garment care information corresponding to the care label is determined based on the shape recognition result of the care label, and the garment care information is displayed through the garment steamer. The garment care information includes one or more of the following: do not wash, do not bleach, and do not tumble dry.

2. The ironing method using a garment steamer according to claim 1, characterized in that, The step of determining whether the care label in the care label image is a non-ironable icon based on the shape recognition result includes: If the care label image does not include any preset care label shape, the care label in the care label image is determined to be a non-ironing icon, wherein the preset care label shape includes one or more combinations of circles, triangles and rectangles.

3. The ironing method using a garment steamer according to claim 1, characterized in that, The image recognition of the wash label image includes: Obtain an image of the care label on the target garment; The care label image is input into the first recognition model to identify the garment care method, and the garment care implementation type output by the first recognition model is obtained. The first recognition model is trained from sample care label images labeled with garment care implementation type tags.

4. The ironing method using a garment steamer according to claim 3, characterized in that, The first recognition model is trained through the following steps: Acquire images of multiple sample washing labels; A training sample set is constructed by labeling each of the sample care label images with a corresponding garment care implementation type label, wherein the garment care implementation type label includes at least an ironable label and a non-ironable label; The first recognition model is obtained by training the convolutional neural network using the training sample set.

5. The ironing method using a garment steamer according to claim 1, characterized in that, When the garment care application type is determined to be ironable, the ironing information of the care label image is identified, and one or more corresponding ironing parameter identification methods are obtained based on the ironing information identification results. The ironing parameters of the garment steamer are obtained through these ironing parameter identification methods, including: When the garment care implementation type is determined to be ironable, the text information of the care label image is recognized to obtain the corresponding care label text content recognition result; If the text content recognition result of the care label does not contain any text information, the care label image is input into the second recognition model to recognize ironing information, and ironing icon information output by the second recognition model is obtained. The second recognition model is trained by sample care label images marked with ironing icon labels. Based on the ironing icon information, the ironing parameters of the garment steamer are generated.

6. The ironing method using a garment steamer according to claim 5, characterized in that, The method further includes: If the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule to obtain the ironing parameters of the garment steamer.

7. The garment steamer ironing method according to claim 6, characterized in that, The method further includes: If it is determined that the text content recognition result of the care label contains text information, the text content recognition result of the care label is mapped to a preset ironing rule, and the image of the care label is input into the second recognition model for ironing information recognition. Based on the category mapping results and the ironing icon information, the ironing parameters of the garment steamer are obtained.

8. A garment steamer ironing device, characterized in that, include: The garment care implementation type detection module is used to perform image recognition on the care label image to obtain the garment care implementation type; The ironing information detection module is used to identify ironing information in the care label image when the garment care implementation type is determined to be ironable, and to obtain one or more corresponding ironing parameter identification methods based on the ironing information identification results, so as to obtain the ironing parameters of the garment steamer through the ironing parameter identification methods. The control module is used to generate an ironing mode corresponding to the garment steamer based on the ironing parameters, and to control the garment steamer according to the ironing mode; The device further includes: The care label shape detection module is used to perform shape recognition on the care label in the care label image when the garment care implementation type is determined to be non-ironable, and to determine whether the care label in the care label image is a non-ironable icon based on the shape recognition result. The garment care reminder module is used to determine the garment care infeasibility information corresponding to the care label based on the shape recognition result of the care label if the care label is not an "iron-free" icon, and to display the garment care infeasibility information through the garment steamer. The garment care infeasibility information includes one or more of the following: do not wash, do not bleach, and do not tumble dry.

9. A garment steamer, characterized in that, It includes the garment steamer ironing device as described in claim 8, as well as a steam heater, a housing, a water tank, a steam nozzle, a steam duct, and a retractable support.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

11. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 through the computer program.

Citation Information

Patent Citations

  • Washing mode determination method and system, storage medium and electronic device

    CN113417107A

  • Garment steamer ironing method, control device, garment steamer and electronic equipment

    CN114481584A