Color image quality comprehensive evaluation method

Abstract

The invention discloses a color image quality comprehensive evaluation method. According to the method, first, a to-be-evaluated color image and a corresponding reference image are input; color spacetransformation is performed on the reference image and the to-be-evaluated image, and brightness channel graphs and chrominance channel graphs of the reference image and the to-be-evaluated image areobtained; the chrominance channel graphs of the reference image and the to-be-evaluated image are extracted, and chrominance similarity features are calculated; the brightness channel graphs of the reference image and the to-be-evaluated image are extracted, and log-Gabor wavelets are used to obtain phase-consistent similarity features; position saliency features of the reference image and the to-be-evaluated image are acquired; pooling is performed on the phase-consistent similarity features and the chrominance similarity features through a position saliency feature weighted standard deviation ; and the quality of the to-be-evaluated image is obtained. Through the method, different characteristics of human vision systems are fully considered, the three aspects are reasonably combined, andthe quality of the color image is well evaluated.

Description

technical field [0001] The invention belongs to the field of image quality evaluation, in particular to a color image quality comprehensive evaluation method based on phase consistency similarity, chromaticity similarity and position salience. Background technique [0002] At present, the full-reference image quality evaluation methods mainly used in the field of image quality evaluation are mean square error, peak signal-to-noise ratio method, etc. These methods only consider the pixel-by-pixel difference between the reference image and the image to be evaluated, and do not consider the human vision The characteristics of the system. Therefore these methods cannot reflect the subjective quality of the image well. [0003] The human visual system is sensitive to edge structure information; and it is more sensitive to the distortion perception of the central area of ​​the image than the edge area; the difference in different color spaces of color images also needs to be cons...

AI Technical Summary

Problems solved by technology

However, some existing evaluation methods that consider the visual characteristics of the human eye, s

Images