Personalized Video Coding Module Using User Sensitivity Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional video coding methods do not effectively account for individual user sensitivity and preference, leading to suboptimal image processing and user experience, as they rely on average human vision system models that fail to reflect personalized sensitivity and preference variations.
Innovation Solution
A video coding module that performs training operations to generate personal video parameters based on user sensitivity and preference information, using a training unit to collect feedback and adjust image encoding and decoding processes accordingly, thereby optimizing image processing for individual users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional video coding methods using average human vision system models are used, then the system complexity is low and ease of operation is maintained, but the image quality and user satisfaction are suboptimal because they fail to account for individual user sensitivity and preference variations
Solution Approach 1:
The system performs a training operation before actual video coding to collect user sensitivity and preference information. This preliminary action creates a personalized model that is then used during normal operation, allowing the system to achieve personalized image processing without adding complexity to the core coding functions.
Solution Approach 2:
The system changes the parameters used in video coding from fixed average HVS model parameters to dynamic personal video parameters. These parameters are adjusted based on individually collected user sensitivity and preference data, enabling optimized image quality for each user while maintaining system efficiency.
2Adaptability or versatility
If personal video parameters are generated through training operations, then adaptability to individual users is improved, but the time required for initial setup and processing increases
Solution Approach 1:
The training operation collects user sensitivity and preference information through selective questioning rather than comprehensive measurement. The system gathers only the essential parameters needed for personalization, performing a partial action that achieves adequate personalization without excessive time investment.
3Measurement precision
If user feedback is collected through sequential display of test images with varying parameters, then measurement precision of user sensitivity is improved, but the time required for training operation increases
Solution Approach 1:
The system changes parameters of test images sequentially during the training operation, varying factors such as brightness, contrast, and color to measure different aspects of user sensitivity. By systematically changing parameters and observing user responses, the system achieves precise sensitivity measurement while managing training time through efficient parameter variation.
Data Source
AI summary
A training operation is performed on the video coding module to generate a personal video parameter based on information on a sensitivity of a user and a preference of a user. An image is received through an imaging device. The image is encoded based on the personal video parameter to generate an encoded image. The encoded image is decoded based on the personal video parameter to generate a first decoded image.