High-dynamic-range (HDR) image quality evaluation method based on tensor domain curvature analysis

Abstract

The invention provides a high-dynamic-range (HDR) image quality evaluation method based on tensor domain curvature analysis. Tensor decomposition in the method can maintain most color information of an HDR image, and curvature analysis can extract structure information of the HDR image; an effective feature set is constructed through combination of tensor decomposition and curvature analysis, andis used to characterize different distortion degrees of HDR image blocks; then local features of the HDR image are extracted from a label matrix reconstructed and obtained by utilizing the feature setand a sparse dictionary with labels; and finally, predicted quality of the image is obtained through aggregating the local features and global features of the HDR image. The method of the invention is tested on two public databases; and experiment results show that performance indexes thereof are all superior to those of other non-reference metrics, and it means that consistency of the method with human visual perception is higher.

Description

technical field [0001] The invention relates to the technical field of high dynamic range image quality evaluation, in particular to a high dynamic range image quality evaluation method based on tensor domain curvature analysis. Background technique [0002] Among the sources of information that people obtain, digital visual information accounts for the majority, such as high-definition television, Internet video streaming, video conferencing, etc., so it is necessary to use some methods to evaluate the quality of received visual information, especially as it has become a major development Trend high dynamic range information, high dynamic range (High Dynamic Range), referred to as HDR information. The difference between the HDR image and the low dynamic range image is that the high dynamic range image has no limited maximum and minimum brightness values, and its brightness value is linearly related to the physical brightness value of the real scene. Therefore, HDR images c...

AI Technical Summary

Problems solved by technology

However, the above-mentioned HDR image quality evaluation methods only consider brightness information, and they are all reference image evaluation methods, and reference images are required in the evaluation process

[0004] Since the above-mentioned full-reference image quality assessment method requires that there must be a reference image for comparison with the distorted image, however, in many applications, the reference image is not available or does not exist, this requirement limits the use of the full-reference image quality assessment method range, so it is necessary to introduce a no-reference image quality evaluation method for HDR images

Images