Electronic device for generating clothing management information and method of controlling the same
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in accurately determining clothing characteristics and management methods due to misunderstood or missing information on clothing labels, leading to incorrect operation of electronic devices.
Innovation Solution
An electronic device equipped with a camera, memory, and processor uses a neural network model to identify and correct misrecognized clothing management symbols, generating accurate management information based on label images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If clothing management symbols are automatically recognized using image processing, then the ease of operation is improved, but the measurement precision deteriorates due to misrecognized symbols
Solution Approach 1:
The system captures multiple images of the clothing label from different angles and positions, processes them to generate multiple recognition results, and then performs cross-validation by comparing these results. Symbols that appear consistently across multiple images are identified as reliable, while inconsistent recognitions are flagged for correction. This feedback mechanism through multi-image comparison significantly improves recognition accuracy while maintaining automatic operation.
Solution Approach 2:
The system performs preliminary capture of multiple label images at different angles and positions before final recognition. By pre-acquiring redundant image data from various perspectives, the system ensures that at least some images will contain clear, unobstructed views of the clothing management symbols, thereby improving the reliability of subsequent recognition without requiring manual intervention.
2Measurement precision
If multiple images are captured to improve recognition accuracy, then the measurement precision is improved, but the loss of time increases due to multiple capture operations
Solution Approach 1:
The system captures multiple images of the label, but does not require processing all captured images equally. Instead, it prioritizes images that show clear views of the management symbols and uses only the necessary subset for recognition. This partial processing approach reduces the effective time cost while maintaining the accuracy benefits of multiple captures.
Solution Approach 2:
The system rapidly captures multiple images in quick succession and uses efficient algorithms to skip over obviously poor-quality images, focusing processing only on images that contribute to accurate recognition. This rushing through the capture and selection process minimizes the perceived time delay while ensuring sufficient data quality for high-accuracy recognition.
3Reliability
If the system requires complete and accurate label information, then the reliability of clothing management is improved, but the ease of operation worsens because users must manually input information when labels are missing or damaged
Solution Approach 1:
The system automatically performs symbol recognition, cross-validation, and information extraction without requiring user intervention. Even when labels are partially damaged or difficult to read, the system uses multiple image captures and comparison algorithms to self-correct and extract the necessary clothing management information, eliminating the need for manual input while maintaining high reliability.
Solution Approach 2:
The system prepares for potential label issues by capturing multiple images in advance and having redundant recognition pathways ready. If the primary recognition fails or detects inconsistencies, the system automatically switches to alternative recognition methods or uses previously captured images, providing a cushion against failures without requiring user intervention to correct the problem.
Data Source
AI summary
Disclosed are an electronic device and a method of controlling the same. An electronic device according to an embodiment of the disclosure includes a camera, a memory configured to store at least one instruction, a display, and at least one processor configured to execute the at least one instruction to acquire a label image of clothing through the camera, generate management information on the clothing using the acquired label image, and control the display to display the generated management information. The at least one processor identifies a plurality of clothing management symbols included in the label image, identifies a misrecognized symbol among the plurality of identified clothing management symbols based on a standard type and a management type of each of the plurality of identified clothing management symbols, and corrects the identified misrecognized symbol based on at least one of a standard type and a management type of another normally recognized symbol.