Weighted Block Image Quality Assessment for Compression Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing approaches to determine perceptual image quality after compression are challenging and often produce insufficient or complex results, especially when trying to optimize compression settings for image or video data.

Innovation Solution

A method that divides images or video frames into blocks and assigns weights to each block based on quality metrics, allowing for a weighted combination of these metrics in a high-dimensional weight space to produce an improved quality assessment and optimize compression settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If compression is applied to conserve network bandwidth, then network resource usage is reduced, but image quality deteriorates

Engineering Contradiction:
Improvenetwork bandwidthVSAvoidimage quality
Core Design Contradiction:
Loss of energyVSManufacturing precision

Solution Approach 1:

The patent divides the image into multiple blocks and assigns different quality metrics to different blocks based on their importance. Critical regions (e.g., faces, text) receive higher quality preservation while less important regions accept higher compression, resolving the contradiction by applying non-uniform quality standards across the image.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent changes compression parameters dynamically based on block importance and content characteristics. By adjusting compression strength per block rather than applying uniform compression, the system preserves network bandwidth while maintaining acceptable quality in critical areas.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If existing quality assessment methods are used, then quality measurement is attempted, but the assessment is either insufficient or computationally expensive

Engineering Contradiction:
Improvequality assessment accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the image into blocks and assesses quality metrics for each block separately using simplified models. This segmentation allows parallel processing and reduces overall computational complexity while maintaining comprehensive quality coverage across the entire image.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces weight factors as intermediaries that combine multiple simple quality metrics into a comprehensive assessment. These weights act as mediators that synthesize information from different metric types without requiring complex computational models, achieving accurate assessment with reduced complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4462780A1Quality assessment and optimization in content management systems and applications
Publication Date: 2024.11.13 MELLANOX TECHNOLOGIES LTD(IL)
  • EP4462780A1 patent drawingFigure 1
  • EP4462780A1 patent drawingFigure 2A~2C
  • EP4462780A1 patent drawingFigure 3A~3B

AI summary

Approaches in accordance with various illustrative embodiments provide for the determination and/or optimization of the quality of an image or video, such as an image that has been compressed for transmission or storage then decompressed for presentation. Weights can be determined for a set of weight-based quality metrics to produce an overall quality metric that is a weighted combination of these metrics. Because different portions of an image or video frame may have different types of features, an image or video frame can be divided into blocks of pixels, for example, with different weights being assigned to different blocks using quality metrics. Different metrics can be considered as points in a high-dimensional weight space, with each dimension corresponding to a weight of a block. A combination of these points results in an improved quality metric. Compression settings can be updated based in part upon the overall quality metric values.