Light field image quality evaluation method based on polar plane multi-scale Gabor feature similarity

Abstract

The invention relates to a light field image quality evaluation method based on polar plane multi-scale Gabor feature similarity. The method comprises the following steps of respectively extracting the polar planes from a reference light field image and a distorted light field image; respectively calculating the Gabor feature maps of the reference polar plane graph and the distortion polar plane graph under three scales and four directions; respectively fusing the Gabor feature maps of the same scale and different directions of the reference polar plane graph and the distorted polar plane graph to obtain a polar plane multi-scale Gabor feature map, and further calculating to obtain a polar plane multi-scale Gabor feature similarity map; and obtaining a final distorted light field image quality evaluation value based on the polar plane multi-scale Gabor feature similarity graph. According to the method, the detail information of the polar plane image is described by utilizing the polarplane multi-scale Gabor characteristics, so that the change of the scene structure in the light field image is reflected, and the method has better light field image quality evaluation performance.

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 light field image quality evaluation method based on polar plane multi-scale Gabor feature similarity. Background technique [0002] With the rapid development of visual media technology, light field imaging has attracted close attention from academia and industry, and has been widely used in the field of computer graphics, such as 3D reconstruction, multi-view segmentation, synthetic aperture imaging, etc. Unlike conventional imaging, light field imaging collects light flow in any direction from any point in space. The resulting light field image is often more able to reflect the position and direction information in the real scene. [0003] In the process of generation, processing, compression, storage, transmission and rendering of light field images, various distortions will inevitably be introduced, which will affect the p...

AI Technical Summary

Problems solved by technology

[0003] During the generation, processing, compression, storage, transmission and rendering of light field images, various distortions will inevitably be introduced, which will affect the perceived quality of light field images and related system performance.

Although a lot of work has been carried out in the field of image quality assessment, most of the existing quality assessment algorithms are designed for natural images, and they are often not suitable for light field image quality assessment.

Images