An Objective Evaluation Method of Stereo Image Quality Based on Sparse Feature Similarity

Abstract

The invention discloses a stereo image quality objective evaluation method based on sparse feature similarity, and the method comprises the steps: extracting a fusion image dictionary table and a view point image dictionary table; employing a first-order binocular fusion model, extracting a first-order image sparse feature image through the fusion image dictionary table, extracting the sparse feature images of the left and right view point images through the view point image dictionary table, carrying out the fusion of the sparse feature images of the left and right view point images through a second-order binocular fusion model, and obtaining a second-order fusion sparse feature image; obtaining an objective quality evaluation prediction value of a distortion stereo image through a sparse feature similarity method. The method is advantageous in that the method avoids a complex machining learning and training process at a dictionary learning stage, and does not need to know the subjective evaluation values of each stereo image without distortion in advance; the method can effectively express the binocular vision characteristics at a quality prediction stage through the first-order binocular fusion model and the second-order binocular fusion model, so the method can effectively improve the correlation between the objective evaluation result and subjective perception.

Description

technical field [0001] The invention relates to an objective evaluation method of stereoscopic image quality, in particular to an objective evaluation method of stereoscopic image quality based on sparse feature similarity. Background technique [0002] Since entering the 21st century, with the maturity of stereoscopic image / video system processing technology and the rapid development of computer network and communication technology, people have a strong demand for stereoscopic image / video system. Compared with the traditional single-viewpoint image / video system, the stereoscopic image / video system is more and more popular because it can provide depth information to enhance the visual reality and give users an immersive new visual experience. It is considered to be the main development direction of the next-generation media, and has aroused widespread concern in the academic and industrial circles. However, in order to obtain better stereoscopic presence and visual experien...

AI Technical Summary

Problems solved by technology

Among them, the commonly used method in the 2D-based evaluation method is to directly use the classic planar image quality evaluation method to evaluate the quality of the stereoscopic image. The biggest difference between the stereoscopic image and the planar image is that the stereoscopic image has a sense of depth and presence. However, this The method does not take into account the characteristics of the left-viewpoint image and the right-viewpoint image, or only evaluates the quality of the left-viewpoint image and the quality of the right-viewpoint image, without combining the visual characteristics of binocular fusion, which leads to the correlation between the final objective evaluation result and subjective perception. Poor sex

Images