Personalized Image Correction via Neural Network Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image correction technologies in portable electronic devices often require significant user effort and fail to cater to individual aesthetic preferences, as they rely on generalized correction patterns that do not account for diverse user tastes.
Innovation Solution
An electronic device equipped with a processor that trains a neural network model using user-preferred correction patterns and type information to automatically correct images, allowing for personalized image adjustments based on user commands and metadata analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a generalized correction pattern is applied to automatically correct images, then user effort is reduced, but the correction does not satisfy diverse user aesthetic preferences
Solution Approach 1:
The system performs preliminary actions by collecting user correction commands and training data in advance, then uses this pre-learned knowledge to automatically apply personalized correction patterns without requiring users to manually adjust settings each time
Solution Approach 2:
The system enables self-service by automatically learning user preferences through their correction commands and autonomously applying personalized correction patterns to new images without requiring continuous user intervention or manual parameter adjustment
2Manufacturing precision
If manual image correction is performed to satisfy individual aesthetic preferences, then correction accuracy is improved, but user effort and time consumption increase
Solution Approach 1:
The system implements feedback by continuously learning from user correction commands and automatically adjusting the correction patterns to match user preferences, improving correction accuracy over time while reducing the need for manual intervention
Solution Approach 2:
The system replaces the mechanical process of manual image adjustment with an automated neural network-based correction system that learns user preferences and applies corrections autonomously, significantly reducing time consumption while maintaining high accuracy
3Adaptability or versatility
If a neural network model is trained with user correction commands, then personalized correction is achieved, but system complexity increases
Solution Approach 1:
The system achieves universality by designing a multi-functional neural network model that can handle various image correction tasks (brightness, contrast, saturation, etc.) and adapt to different user preferences through a single unified framework, avoiding the need for multiple separate systems
Data Source
AI summary
An electronic device and a controlling method thereof are provided. An electronic device includes a memory configured to store at least one instruction and a processor configured to execute the at least one instruction and operate as instructed by the at least one instruction. The processor is configured to: obtain a first image; based on receiving a first user command to correct the first image, obtain a second image by correcting the first image; based on the first image and the second image, train a neural network model; and based on receiving a second user command to correct a third image, obtain a fourth image by correcting the third image using the trained neural network model.