A no-reference color image quality assessment method based on color and structural distortion

By constructing a no-reference color image quality assessment method based on color and structural distortion, and utilizing the HSV color space and convolutional neural network model, the problem of the inability of existing technologies to effectively evaluate color image quality is solved, and accurate image quality assessment under no-reference conditions is achieved.

CN115880234BActive Publication Date: 2026-04-17EAST CHINA UNIV OF TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202211510202.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-29
Publication Date
2026-04-17
Estimated Expiration
2042-11-29

AI Technical Summary

Technical Problem

Existing image quality assessment methods fail to adequately consider the impact of color distortion on image quality when processing color images, and most algorithms fail to conform to human visual characteristics, resulting in discrepancies between experimental results and subjective perceptions. In particular, there is a lack of effective evaluation methods under conditions without reference.

Method used

A no-reference color image quality assessment method based on color and structural distortion is adopted. An end-to-end no-reference image quality assessment model is constructed through block operation, Scharr detection operator, HSV color space conversion and convolutional neural network model. The quality assessment is performed using the H channel and S channel in HSV color space, and feature fusion is performed by combining gradient information and color features.

Benefits of technology

It achieves accurate evaluation of color image quality under no-reference conditions, and the simulated quality score is consistent with the human visual system, overcoming the shortcomings of traditional methods and improving the accuracy and consistency of the evaluation.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application is suitable for the field of image processing, and provides a no-reference color image quality evaluation method based on color and structure distortion, comprising the following steps: performing a blocking operation on a color image to form a color distortion image block data set, and forming a training set and a test set; a group of two-dimensional Scharr detection operators are constructed, and convolution processing is performed on the input image block by using the two-dimensional Scharr detection operators to obtain gradient feature information of the distortion image block; the obtained image block data set is converted into an HSV color space; a no-reference image quality evaluation convolutional neural network model based on color and structure distortion is constructed according to the existing image block data set; and the divided training set is input into the constructed no-reference image quality evaluation convolutional neural network model to obtain a trained no-reference image quality evaluation model. The application has reasonable design, the simulated quality score and the real quality score have strong correlation and small error, and is worth promoting.
Need to check novelty before this filing date? Find Prior Art