Objective evaluation method for quality of three-dimensional image based on improved structural similarity

Abstract

The invention provides an objective evaluation method for the quality of a three-dimensional image based on improved structural similarity, which comprises the steps of firstly establishing a method for calculating the mean structural similarity of a certain distortion image; calculating a frequency domain structural similarity index; calculating a texture information coefficient; weighting an image region by using a spatial position factor; considering an image central region in which the human eyes are interested, and calculating a spatial position influence coefficient; integrating the texture information coefficient and the spatial position influence coefficient into a comprehensive weighting coefficient according to a formula provided in the description, carrying out weighted averaging on the frequency domain structural similarity index of each image block by using the coefficient, and calculating the average structural similarity; and calculating the average structural similarity of a left viewpoint and the average structural similarity of a right viewpoint of the three-dimensional image according to method established by the steps for calculating the average structural similarity of the distortion image, and acquiring a quality evaluation index of the three-dimensional image. The objective evaluation method provided by the invention can make overall and accurate comprehensive evaluation for the quality of the three-dimensional image.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to an image quality evaluation method, in particular to a stereoscopic image objective quality evaluation method based on improved structural similarity. Background technique [0002] With the vigorous development of multimedia technology, stereoscopic image technology came into being. However, there is not yet a complete set of objective evaluation system of stereoscopic image quality to evaluate the quality of distorted stereoscopic images, and there are still great limitations in evaluating the quality of stereoscopic images. [0003] At present, the evaluation of stereoscopic images includes subjective evaluation and objective evaluation. The former relies on the subjective feeling of the observer, but the conclusion of the evaluation is greatly influenced by the observer's own factors, which is time-consuming and labor-intensive; Therefore, it is very necessary to seek an object...

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the shortcomings of the traditional structural similarity index measurement (SSIM) in stereoscopic image quality evaluation, and provides a stereoscopic image quality evaluation method based on improved structural similarity, which introduces structural information into the frequency domain, Combining the texture features of the image and the spatial position information of the image, it can make a comprehensive and accurate comprehensive evaluation of the quality of the stereoscopic image

Images