An Objective Evaluation Method of Stereo Image Quality Based on Sparse Representation

Abstract

The invention discloses an objective quality evaluation method for stereoscopic images based on sparse representation. In the training stage, a plurality of original undistorted stereoscopic image left viewpoint images are selected to form a training image set, and Gaussian difference filtering is used to filter each image in the training image set. Filter images of different scales to obtain filtered images of different scales, and use the K-SVD method to perform dictionary training operations on a set composed of all sub-blocks in all filtered images of different scales to construct a visual dictionary table; The test stereo image and its original undistorted stereo image are subjected to Gaussian difference filtering to obtain filtered images of different scales, and then non-overlapping block processing is performed on the filtered images of different scales, and the test image is calculated according to the constructed visual dictionary table The predicted value of the objective evaluation of image quality; the advantage is that no complicated machine learning training process is required in the training phase, and only the sparse coefficient matrix is ​​needed to calculate the predicted value of the objective evaluation of image quality in the testing phase, and the consistency with the subjective evaluation value is good .

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to an objective evaluation method of stereoscopic image quality based on sparse representation. Background technique [0002] With the rapid development of image coding technology and stereoscopic display technology, stereoscopic image technology has received more and more attention and applications, and has become a current research hotspot. Stereoscopic image technology utilizes the principle of binocular parallax of the human eye. Both eyes independently receive left and right viewpoint images from the same scene, and form binocular parallax through brain fusion, so as to enjoy stereoscopic images with a sense of depth and realism. . Compared with single-channel images, stereo images need to ensure the image quality of two channels at the same time, so it is very important to evaluate its quality. However, there is currently no effective objective evaluation method to evalu...

AI Technical Summary

Problems solved by technology

At present, the existing method is to predict the evaluation model through machine learning, but its computational complexity is high, and the training model needs to predict the subjective evaluation value of each evaluation image, which is not suitable for practical applications and has certain limitations.

Images