Natural-scene-based reference-free high-dynamic image quality evaluation algorithm

Abstract

Disclosed in the invention is a natural-scene-based reference-free high-dynamic image quality evaluation algorithm. The algorithm is implemented as follows: step one, carrying out perceptually uniform(PU) coding on an HDR image to obtain a corresponding LDR image; step two, carrying out mean subtracted contrast normalization on the LDR image; step three, extracting an image feature of a salient region image block; and step four, carrying out image quality calculation, obtaining features of an original HDR image and a distorted HDR image, and carrying out fitting by using an MVG model to obtain a mean value and a variance matrix v- and sigma. Compared with the prior art, the natural-scene-based reference-free high-dynamic image quality evaluation algorithm has the following advantages: theconsistency with the human-eye-based objective high-dynamic image quality evaluation is high; no complicated conversion is needed during the calculation process; the complexity is low; the real-timehigh-dynamic image quality evaluation is realized; because of combination of the high-dynamic image with the reference-free image quality evaluation, the universality is high; and the novel idea is provided for the study on the high-dynamic image quality evaluation.

Description

technical field [0001] The invention relates to image quality evaluation technology, in particular to a high dynamic image quality evaluation algorithm without reference. Background technique [0002] Scenes in nature have a very large dynamic range, the ratio of the brightness of the brightest object to the brightness of the darkest object is 10 8 cd / m 2 , and the range that the human eye can see is 10 5 cd / m 2 about. However, traditional TV systems provide a standard dynamic range (SDR) of about 1000:1 (the ratio between the brightest and darkest brightness), which is far from the range that the human eye can perceive, causing the human eye to eventually The perceived level of the picture is poor, and a lot of details are lost. [0003] A high dynamic range (High Dynamic Range, HDR) image can record a scene with a high brightness dynamic range, which is more in line with the visual characteristics of the human eye. HDR can solve the TV display problem very well, maki...

AI Technical Summary

Problems solved by technology

[0004] Due to the larger dynamic range of HDR images, the typical quality evaluation algorithms currently applied to LDR images, such as PSNR and SSIM evaluation algorithms that rely on the perceptual linearity between input pixel values ​​and do not consider factors such as brightness masking, are not very good. Good rated HDR image quality

[0005] The subjective image quality evaluation method requires repeated experiments on multiple test images, which is time-consuming, expensive, and difficult to operate, so an objective image quality evaluation method is needed

Images