A Two-Step Framework for Constructing Blind Image Quality Indices

Present day no-reference/no-reference image quality assessment (NR IQA) algorithms usually assume that the distortion affecting the image is known. This is a limiting assumption for practical applications, since in a majority of cases the distortions in the image are unknown. We propose a new two-step framework for no-reference image quality assessment based on natural scene statistics (NSS). Once trained, the framework does not require any knowledge of the distorting process and the framework is modular in that it can be extended to any number of distortions. We describe the framework for blind image quality assessment and a version of this framework-the blind image quality index (BIQI) is evaluated on the LIVE image quality assessment database. A software release of BIQI has been made available online: http://live.ece.utexas.edu/research/quality/BIQI_release.zip.

I. Introduction

Objective blind/no-reference (NR) image quality assessment (IQA) refers to algorithms that seek to predict the quality of distorted images without any knowledge of pristine reference images and that correlate well with human perception of quality. Recently, the field of NR IQA has seen a significant rise in activity [1]–[4]; however there is considerable room for improvement. This is largely due to the fact that NR IQA is an extremely difficult problem to solve. In fact, only recently has the field of the ‘easier’ full-reference (FR) IQA matured to produce algorithms that correlate well with human perception of quality [5].