Universal no-reference image quality evaluation method based on transformation domain and spatial domain

Abstract

The invention discloses a universal no-reference image quality evaluation method based on natural scene statistics of a transformation domain and a spatial domain. The method comprises the following steps of (1) carrying out NSCT (Non Subsampled Contourlet Transform) decomposition on an image to obtain sub-band coefficients, which have the same size as an original image and are in different scales and different directions; (2) extracting a mutual information statistics characteristic between a relative coefficient and a father coefficient of an NSCT sub-band; (3) extracting a structural information statistics characteristic between the relative coefficient and the father coefficient of the NSCT sub-band; (4) extracting an MSCN (Mean Subtracted Contrast Normalized) coefficient of the original image and a neighborhood coefficient statistics characteristic thereof; and (5) respectively constructing a no-reference image quality evaluation model and an image distortion type recognition model by utilizing SVR (Support Vector Regression) and an SVC (Support Vector Classifier) on the basis of the characteristics. In comparison with the prior art, the method has the advantages of consistent evaluation result and human subjective evaluation height, high classification accuracy, low computing complexity, stronger application value and the like.

Description

technical field [0001] The present invention relates to a method for image quality evaluation, mainly relates to a general non-reference image quality evaluation method based on transformation domain and space domain, belongs to the technical field of image analysis, and can be widely used in video and image transmission, intelligent video monitoring and Digital TV and other fields. Background technique [0002] With the mass promotion of electronic products such as SLR cameras, smart phones, and tablet computers, digital images have become an indispensable means of exchanging information in people's daily lives. However, in the process of image acquisition, transmission, compression, processing and reconstruction, due to the limitations of electron optical system, compression transmission algorithm, human factors and other conditions, the acquired images inevitably have various distortions, so Image Quality Assessment (IQA) has become one of the most important research top...

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to solve the problem that the traditional no-reference quality evaluation method does not consider the influence of distortion on the pixel itself, pixel correlation, image multi-scale and multi-direction at the same time, resulting in inaccurate evaluation results, and provides a method based on transform domain and a general-purpose no-reference image quality assessment method in the spatial domain to meet the effective no-reference evaluation of images

Images