Making a “Completely Blind” Image Quality Analyzer

TLDR

Blind IQA research seeks perceptual models that predict distorted image quality with minimal prior knowledge, whereas current state‑of‑the‑art no‑reference IQA algorithms rely on training data and human opinion scores. The new IQA model, called NIQE, constructs a quality‑aware set of statistical features from a simple space‑domain natural scene statistic model, derived solely from a corpus of natural, undistorted images. Experimental results show that NIQE achieves performance comparable to top NR IQA models that require training on large human‑rated distorted image databases. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.

Abstract

An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art "general purpose" no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of training examples and corresponding human opinion scores. However we have recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed without any exposure to distorted images. Thus, it is "completely blind." The new IQA model, which we call the Natural Image Quality Evaluator (NIQE) is based on the construction of a "quality aware" collection of statistical features based on a simple and successful space domain natural scene statistic (NSS) model. These features are derived from a corpus of natural, undistorted images. Experimental results show that the new index delivers performance comparable to top performing NR IQA models that require training on large databases of human opinions of distorted images. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.