Method and electronic device for processing clothing label image, and computer-readable recording medium

Patent metadata

Field	Value
Publication number	US-2024112477-A1
Application number	US-202318375236-A
Country	US
Kind code	A1
Filing date	Sep 29, 2023
Priority date	Sep 29, 2022
Publication date	Apr 4, 2024
Grant date	—

Abstract

A method of processing an image by an electronic device, includes: obtaining a label image of a label including at least one symbol associated with handling of clothing item; obtaining, from the label image, text information associated with the handling of the clothing item; identifying, from the label image, the at least one symbol associated with the handling of the clothing item, based on the text information and the label image; and obtaining handling information related to the clothing item based on the identified at least one symbol.

First claim

What is claimed is:

1 . A method of processing an image by an electronic device, the method comprising:
obtaining a label image including at least one symbol associated with handling of clothing item; obtaining, from the label image, text information associated with the handling of the clothing item; identifying, from the label image, the at least one symbol associated with the handling of the clothing item, based on the text information and the label image; and obtaining handling information related to the clothing item based on the identified at least one symbol.

2 . The method of claim 1 , wherein the obtaining of the text information associated with the handling of the clothing item comprises:
obtaining a plurality of texts from the label image by applying the label image to an optical character recognition (OCR) model; and extracting at least one text associated with the handling of the clothing item from among the plurality of texts by applying the plurality of texts to at least one artificial intelligence (AI) model trained to infer texts associated with handling of clothing item.

3 . The method of claim 2 , wherein the extracting of the at least one text associated with the handling of the clothing item comprises:
obtaining weight information about weights representing a correlation between the plurality of texts by applying the plurality of texts to a first AI model; and extracting the at least one text associated with the handling of the clothing item from among the plurality of texts by applying the plurality of texts and the weight information to a second AI model.

4 . The method of claim 3 , wherein the first AI model is an AI model trained to infer the weights representing the correlation between the plurality of texts, and
the second AI model is an AI model trained to infer the texts associated with the handling of the clothing item.

5 . The method of claim 1 , wherein the identifying of the at least one symbol comprises:
extracting at least one image feature associated with the at least one symbol by inputting the label image to an image feature extraction network; and identifying, from the label image, the at least one symbol associated with the handling of the clothing item by applying the text information associated with the handling of the clothing item, including the at least one text associated with the handling of the clothing item, and the at least one image feature associated with the at least one symbol, to a third AI model trained to infer symbols associated with the handling of the clothing item.

6 . The method of claim 1 , wherein the text information associated with the handling of the clothing item comprises at least one of a type of clothing, a fiber material, a fiber ratio, or precautions corresponding to the clothing item.

7 . The method of claim 1 , further comprising:
obtaining appearance information for identifying the clothing item; and displaying clothing information including the handling information and the appearance information.

8 . The method of claim 1 , further comprising:
obtaining a user input requesting information about a recommendation operation corresponding to the handling information; identifying whether the clothing item is manageable in at least one clothing management device, based on the handling information; and providing information about whether the clothing item is manageable in the at least one clothing management device, based on the user input.

9 . The method of claim 8 , wherein the providing of the information about whether the clothing item is manageable in the at least one clothing management device comprises:
obtaining information about the recommendation operation to be performed by the at least one clothing management device by analyzing the handling information based on identifying that the clothing item is manageable in the at least one clothing management device; and transmitting the information about the recommendation operation to the at least one clothing management device.

10 . The method of claim 8 , wherein the providing of the information about whether the clothing item is manageable in the at least one clothing management device comprises providing a notification that the at least one clothing management device is unable to handle the clothing item, based on identifying that the clothing item is unmanageable in the at least one clothing management device.

11 . The method of claim 1 , further comprising:
transmitting the label image to a server; and receiving, from the server, the at least one symbol or the handling information.

12 . The method of claim 1 , wherein the handling information comprises at least one of washing information, drying information, spin-drying information, ironing information, or dry cleaning information corresponding to the clothing item.

13 . An electronic device for processing an image, the electronic device comprising:
a memory storing one or more instructions; and at least one processor configured to execute the one or more instructions stored in the memory to:
obtain a label image including at least one symbol associated with handling of clothing item;
obtain, from the label image, text information associated with the handling of the clothing item;
identify, from the label image, the at least one symbol associated with the handling of the clothing item, based on the text information and the label image; and
obtain handling information related to the clothing item based on the identified at least one symbol.

14 . The electronic device of claim 13 , wherein the at least one processor is further configured to execute the one or more instructions to:
obtain a plurality of texts from the label image by applying the label image to an optical character recognition (OCR) model; and extract at least one text associated with the handling of the clothing item from among the plurality of texts by applying the plurality of texts to at least one artificial intelligence (AI) model trained to infer texts associated with the handling of clothing item.

15 . The electronic device of claim 14 , wherein the at least one processor is further configured to execute the one or more instructions to:
obtain weight information about weights representing a correlation between the plurality of texts by applying the plurality of texts to a first AI model; and extract the at least one text associated with the handling of the clothing item from among the plurality of texts by applying the plurality of texts and the weight information to a second AI model.

16 . The electronic device of claim 15 , wherein the first AI model is an AI model trained to infer the weights representing the correlation between the plurality of texts, and
the second AI model is an AI model trained to infer the texts associated with the handling of the clothing.

17 . The electronic device of claim 13 , wherein the at least one processor is further configured to execute the one or more instructions to:
extract at least one image feature associated with the at least one symbol by inputting the label image to an image feature extraction network; and identify, from the label image, the at least one symbol associated with the handling of the clothing item by applying the text information associated with the handling of the clothing item, including the at least one text associated with the handling of the clothing item, and the at least one image feature associated with the at least one symbol, to a third AI model trained to infer symbols associated w

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Younguk
• Kim Jongyeong
• Kim Hyunhan
• Kim Hyosang
• Seo Chanwon
• Hyun Hyein

Classifications

• G06V20/62 Primary

  Text, e.g. of license plates, overlay texts or captions on TV images · CPC title

• G06V10/82 Primary

  using neural networks · CPC title

• G06V30/196

  using sequential comparisons of the image signals with a plurality of references · CPC title

• G06V30/148

  Segmentation of character regions · CPC title

• G06V10/80

  Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level (multimodal speaker identification or verification G10L17/10) · CPC title