Structure texture sparse representation based objective assessment method for stereoscopic image quality

Abstract

The present invention discloses a structure texture sparse representation based objective assessment method for stereoscopic image quality. The method comprises: in a training phase, performing separation of structure and texture on left view point images of a plurality of distortion stereoscopic images, performing dictionary training on a collection constructed by sub blocks of all structural images through an unsupervised learning mode to obtain a structure dictionary table, and performing dictionary training on a collection constructed by sub blocks of all texture images to obtain a texture dictionary table. In a test phase, according to the structure dictionary table and the texture dictionary table, performing joint optimization to obtain a structure sparse coefficient matrix and a texture sparse coefficient matrix, and calculating an image quality object evaluation value of the distortion stereoscopic images, so that an excellent consistency is maintained with a subject evaluation value, the structure dictionary table and the texture dictionary table do not need to be calculated again in the testing phase, calculating complexity is reduced, and the subjective evaluation value is not needed to be foreseen, and thus the method is applicable to practical application occasions.

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 of structure texture. 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. . Due to the influence of acquisition system, storage compression and transmission equipment, stereoscopic images will inevitably introduce a series of distortions. Compared with single-channel images, stereoscopic images need...

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