Light field image quality evaluation method based on polar plane linear similarity

Abstract

The invention relates to a light field image quality evaluation method based on polar plane linear similarity. The method belongs to the field of image processing, is provided according to the sensitivity to scene structure change when a human vision system understands a light field image and rich scene structure change information contained in the light field image, and comprises the following steps: respectively extracting a polar plane graph from a reference light field image and a distorted light field image; extracting inear feature maps of the reference polar plane graph and the distortion polar plane graph, and acquiring a polar plane linear feature similarity map through calculation; and obtaining a final distorted light field image quality evaluation value based on the polar planelinear similarity graph. According to the method, the scene structure change in the light field image is described by fully utilizing the polar plane linear characteristics, so that the quality of the distorted light field image is evaluated, the subjective perception degree of a human eye subjective vision system on the light field image is reflected, and the light field image quality evaluationperformance is relatively good.

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 linear similarity. Background technique [0002] With the rapid development of technologies such as mobile Internet, cloud computing, and virtual reality, light field images have gained more and more attention and applications. Different from natural scene images, light field images mainly record the position and direction information of light radiation during propagation, breaking through the limitations of traditional imaging that simply project a 3D scene on a 2D plane, and can be widely used in multi-view imaging, 3D reconstruction, full focus imaging, depth estimation, virtual reality, augmented reality and other fields. [0003] Image processing is aimed at providing high-definition image quality. However, like natural scene images, light field images will ...

AI Technical Summary

Problems solved by technology

At present, there is a lack of methods for evaluating the quality of light field images in the field of image processing, and the research on quality evaluation methods for light field images has become an urgent need

Images