Non-reference quality evaluation method for fuzzy distortion three-dimensional images

Abstract

The invention discloses a non-reference quality evaluation method for fuzzy distortion three-dimensional images. In a training phase, multiple distortionless three-dimensional images and corresponding fuzzy distortion three-dimensional images are selected to constitute a training image set, the fuzzy distortion three-dimensional images are decomposed by means of bidimensional empirical mode decomposition to obtain intrinsic mode function images, and a vision dictionary table is constructed by means of a K mean value clustering method; objective evaluation metric values of pixels in the fuzzy distortion three-dimensional images are obtained, so that a visual quality table is constructed; in a testing phase, three-dimensional images to be tested are decomposed through bidimensional empirical mode decomposition to obtain intrinsic mode function images, and then image quality objective evaluation predicted values of the images to be tested are obtained according to the vision dictionary table and the visual quality table. The method has the advantages that complicated machine learning and training processes are not needed in the training phase, the image quality objective evaluation predicted values can be obtained only through a simple vision dictionary search process in the testing phase, and consistency of subjective evaluation values is good.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a no-reference quality evaluation method for blurred and distorted stereoscopic images. 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 evaluate t...

AI Technical Summary

Problems solved by technology

The current no-reference quality evaluation usually uses machine learning to predict the evaluation model, which has high computational complexity, 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