Proceedings Article | 24 November 2014
KEYWORDS: Image quality, Visual process modeling, Visualization, Databases, Image processing, Single mode fibers, Visual system, Image compression, Machine learning, Visual cortex
The visual quality assessment of images/videos is an ongoing hot research topic, which has become
more and more important for numerous image and video processing applications with the rapid development of digital
imaging and communication technologies. The goal of image quality assessment (IQA) algorithms is to automatically
assess the quality of images/videos in agreement with human quality judgments. Up to now, two kinds of models have
been used for IQA, namely full-reference (FR) and no-reference (NR) models. For FR models, IQA algorithms interpret
image quality as fidelity or similarity with a perfect image in some perceptual space. However, the reference image is not
available in many practical applications, and a NR IQA approach is desired. Considering natural vision as optimized by
the millions of years of evolutionary pressure, many methods attempt to achieve consistency in quality prediction by
modeling salient physiological and psychological features of the human visual system (HVS). To reach this goal,
researchers try to simulate HVS with image sparsity coding and supervised machine learning, which are two main
features of HVS. A typical HVS captures the scenes by sparsity coding, and uses experienced knowledge to apperceive
objects. In this paper, we propose a novel IQA approach based on visual perception. Firstly, a standard model of HVS is
studied and analyzed, and the sparse representation of image is accomplished with the model; and then, the mapping
correlation between sparse codes and subjective quality scores is trained with the regression technique of least squaresupport
vector machine (LS-SVM), which gains the regressor that can predict the image quality; the visual metric of
image is predicted with the trained regressor at last. We validate the performance of proposed approach on Laboratory
for Image and Video Engineering (LIVE) database, the specific contents of the type of distortions present in the database
are: 227 images of JPEG2000, 233 images of JPEG, 174 images of White Noise, 174 images of Gaussian Blur, 174
images of Fast Fading. The database includes subjective differential mean opinion score (DMOS) for each image. The
experimental results show that the proposed approach not only can assess many kinds of distorted images quality, but
also exhibits a superior accuracy and monotonicity.
