Sparse representation-based image quality assessment

Abstract

Abstract-A successful approach to image quality assessment involves comparing the structural information between a distorted and its reference image. However, extracting structural information that is perceptually important to our visual system is a challenging task. This paper addresses this issue by employing a sparse representation-based approach and proposes a new metric called the sparse representation-based quality (SPARQ) index. The proposed method learns the inherent structures of the reference image as a set of basis vectors, such that any structure in the image can be represented by a linear combination of only a few of those basis vectors. This sparse strategy is employed because it is known to generate basis vectors that are qualitatively similar to the receptive field of the simple cells present in the mammalian primary visual cortex [1]. The visual quality of the distorted image is estimated by comparing the structures of the reference and the distorted images in terms of the learnt basis vectors resembling cortical cells. Our approach is evaluated on six publicly available subject-rated image quality assessment datasets. The proposed SPARQ index consistently exhibits high correlation with the subjective ratings on all datasets and performs better or at par with the state-ofthe-art.

Flexible Actuator With Variable Stiffness and Its Decoupling Control Algorithm: Principle Prototype Design and Experimental Verification

“…The main idea on sparse representation is to express the signals simply and effectively [35] with the linear combination of a small number of elementary signals [36]. The theory about sparse representation also conforms to the human eyes' visual characteristic [37].…”

Supervised dictionary learning for blind image quality assessment using quality-constraint sparse coding

“…We term the output of the sparse coding model with a learnt dictionary as sparse feature which is generally considered to be highly correlated with visual perception. Based on this fact, some sparse coding-based FR-IQA models have been developed to evaluate the perceived quality by measuring the fidelity relative to the reference image (distortion free) in terms of the sparse features [33,34]. However, although the sparse feature fidelity (SFF) metric can well reflect the perceived quality, how to utilize these sparse features for OF-BIQA still remains a quite challenging problem thus far.…”

A Sparse Representation Image Denoising Method Based on Orthogonal Matching Pursuit

“…In recent years, along with the development of compressed sensing technology, sparse representation theory has become a new research direction in the field of image denoising. Sparse model refers to describe the exist signal only with very little linear set in basic dictionary [3]. It is well known that ordinary images can be sparse representation in certain transform domain, thus to transfer the image to this transform domain.…”