Camera image quality evaluation method and device

Abstract

The invention provides a camera image quality evaluation method and device, and belongs to the technical field of image quality evaluation. According to the method, a natural scene statistical model and local resolution features formed by three sets of features are utilized. As for the first set of features, four features are extracted by utilizing the linear relation between free energy and a structure degradation model. As for the second set of features, the statistical features of natural images are utilized, and generalized Gaussian distribution is utilized to measure deviation of distortion images and the natural scene statistical model so as to extract four features. As for the third set of features, three features are extracted by utilizing discrete wavelet decomposition to measure resolution of the images. The previous two sets of features measure naturalness of the images and are different in focus, wherein the first set of feature consider local autoregression, and the second set of features consider global histogram statistics. Finally, the quality score of the camera images is obtained by the result of the evaluation algorithm through the machine learning tool of a support vector machine, and the quality of the camera images is evaluated according to the quality score.

Description

technical field [0001] The invention relates to a camera image quality evaluation method and device, in particular to a camera image quality evaluation method and device based on natural scene statistics and definition. Background technique [0002] With the rapid development of mobile devices and networks, massive images are presented to users all the time. Due to the problems of device shooting itself, image processing and transmission process, images will inevitably be distorted and degraded. How to evaluate and Controlling the quality of these digital images has become even more important. [0003] In the past few years, image quality assessment has become a broad and fundamental problem, and many objective evaluation algorithms have emerged that can accurately evaluate the quality of distorted images. If the undistorted original image corresponding to the distorted image exists, and the evaluation algorithm can compare the two images to obtain the quality of the distor...

AI Technical Summary

Problems solved by technology

[0006] The above algorithms perform well in general image quality evaluation databases such as LIVE database, CSIQ database, etc., but the quality evaluation results for real camera images are not ideal

The reason is that the image distortion in the general image quality evaluation database is a kind of distortion, or the distortion is simulated by computer, while the real camera image contains multiple distortions at the same time, and the type of distortion is unpredictable

Therefore, it is very challenging to evaluate the quality of camera images.

Images