All-reference three-dimensional image quality objective evaluation method based on visual salient feature extraction

Abstract

The invention discloses an all-reference three-dimensional image quality objective evaluation method based on visual salient feature extraction. According to the method, a left view and a right view of a three-dimensional image pair are processed to obtain a corresponding disparity map; image fusion is performed on the left view and the right view of the three-dimensional image pair to obtain an intermediate reference image and an intermediate distortion image; a spectral residual visual saliency model is utilized to obtain a reference saliency map and a distortion saliency map, and a visual saliency map is obtained through integration; visual information features are extracted from the intermediate reference image and the intermediate distortion image, and depth information features are extracted from the disparity map of the three-dimensional image pair; similarity measurement is performed to obtain measurement indexes of all the visual information features of vision saliency enhancement; and support vector machine training prediction is performed, an objective quality score is obtained, mapping of three-dimensional image quality is realized, and measurement and evaluation of three-dimensional image quality are completed. Through the method, image quality objective evaluation and subjective evaluation have good consistency, and the performance is superior to that of existingthree-dimensional image quality evaluation methods.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for objectively evaluating the quality of a full-reference stereo image based on visually significant feature extraction. Background technique [0002] In the process of image sampling, transmission, compression and reproduction, images will always have various distortions, and humans have higher and higher requirements for the quality of image information. Therefore, with the development of 3D video and technology, the quality of stereo images Evaluation technology is becoming more and more important in human social life. Because the subjective stereoscopic image quality evaluation method requires the human observer to provide a subjective quality score for each image. These methods have shortcomings such as time-consuming and weak real-time performance. It is very necessary to develop an objective stereoscopic image quality evaluation method to realize...

AI Technical Summary

Problems solved by technology

However, since the research hotspots at home and abroad are mainly focused on full-reference and non-reference stereoscopic image quality evaluation measurement methods, among them, there are more studies on full-reference image quality evaluation, and the technology is relatively mature. The model established on this basis is consistent with Subjective measurement consistency is high

However, because the stereoscopic image visual model system is not perfect, the objective quality evaluation of stereoscopic images is still a hot and difficult point in current research.

Images