Visual Quality Degradation Measurement via Subjective Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for measuring visual quality degradation in digital content, such as images and videos, fail to accurately quantify the impact of encoding processes on subjective human perception, leading to inconsistencies in assessing the quality of digital content across different encoding processes.
Innovation Solution
A computer-implemented method and system that maps objective quality metrics to subjective metrics, approximating human visual system assessments by processing original and encoded digital content data to identify and quantify visual artefacts like ringing, blocking, blurring, motion disparity, flickering, and pulsing, using a database of human ratings to establish non-linear mappings between objective and subjective metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If objective quality metrics are used to measure visual quality degradation, then measurement precision is improved, but the ability to approximate subjective human visual system assessment deteriorates
Solution Approach 1:
The patent introduces mapping functions as intermediary elements that translate objective quality metrics into subjective quality assessments. These mapping functions serve as mediators between the objective measurement domain and the subjective perception domain, allowing the system to maintain measurement precision while approximating human visual system assessment through learned relationships between objective metrics and subjective ratings
Solution Approach 2:
The patent transforms objective quality metrics into subjective quality assessments by applying parameter changes through mapping functions. These functions modify the parameters of objective metrics (such as PSNR, SSIM) to reflect subjective perception characteristics, enabling the system to maintain precise measurements while adapting them to approximate human visual system responses
2Measurement precision
If multiple visual artefact types are analyzed separately, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the visual quality assessment into distinct artefact type analyses (e.g., compression artefacts, transmission artefacts, processing artefacts). Each segment is evaluated separately using specific mapping functions, improving measurement precision for each artefact type while organizing the complexity into manageable, modular components
Solution Approach 2:
The patent creates a universal framework where a single quality assessment system handles multiple visual artefact types through configurable mapping functions. This multi-functional approach allows the same system architecture to analyze different artefact types by selecting appropriate mapping functions, reducing overall device complexity while maintaining precision for each specific artefact analysis
Data Source
AI summary
Disclosed here are methods, systems, and devices for measuring visual quality degradation of digital content caused by an encoding process. There is received first data for a digital content item, which is not encoded by the encoding process, and second data for the digital content item, which is encoded by the encoding process. For a given artefact type, the first data and the second data are processed to obtain a first quality metric measuring visual quality degradation in the digital content item attributable to the given artefact type caused by the encoding process. A stored mapping corresponding to the given artefact type is applied to the first quality metric to obtain a second quality metric which measures visual quality degradation in the digital content item attributable to the given artefact type caused by the encoding process and approximates subjective assessment of the digital content item by a human visual system.