Blind Image Quality Assessment Using Statistical Structural and Luminance Features

Blind image quality assessment (BIQA) aims to develop quantitative measures to automatically and accurately estimate perceptual image quality without any prior information about the reference image. In this paper, we introduce a novel BIQA metric by structural and luminance information, based on the characteristics of human visual perception for distorted image. We extract the perceptual structural features of distorted image by the local binary pattern distribution. Besides, the distribution of normalized luminance magnitudes is extracted to represent the luminance changes in distorted image. After extracting the features for structures and luminance, support vector regression is adopted to model the complex nonlinear relationship from feature space to quality measure. The proposed BIQA model is called no-reference quality assessment using statistical structural and luminance features (NRSL). Extensive experiments conducted on four synthetically distorted image databases and three naturally distorted image databases have demonstrated that the proposed NRSL metric compares favorably with the relevant state-of-the-art BIQA models in terms of high correlation with human subjective ratings. The MATLAB source code and validation results of NRSL are publicly online at http://www.ntu.edu.sg/home/wslin/Publications.htm.

I. Introduction

Digital images are subject to a broad spectrum of distortions during the process of acquisition, compression, transmission and reproduction. Therefore, it is essential to guarantee the quality of image content for end-users. Subjective viewing test is a natural way to evaluate visual image quality. Despite of its high accuracy and reliability, subjective evaluation is cumbersome, expensive, time consuming, and non-reproducible, which makes it difficult to be embedded into practical applications such as real-time quality monitoring and prediction  [1], [2].