Image quality assessment using BSIF, CLBP, LCP, and LPQ operators

Abstract

The pervasiveness of digital devices like mobile phones, tablets, and personal computers established the presence of image contents as an essential media in several communication applications. In this scenario, the quality of the displayed images is directly correlated with the sense of communication excellence experienced by the users of these applications. Therefore, the development of techniques for assessing the quality of images, as perceived by human observers, is crucial for current multimedia applications. These techniques can either utilize the full prior information from a reference image (full-reference metrics), partial features of the reference (reduced-reference metrics) or exclusively the test image (no-reference metrics). In this paper, an effective no-reference image quality assessment approach is proposed based on the binarized statistical image features (BSIF), the completed local binary patterns (CLBP), the local configuration patterns (LCP), and the local phase quantization (LPQ) descriptors. The statistics of these descriptors is thoroughly evaluated using three popular databases: LIVE, TID2013, and CSIQ. Experimental results evince the correlation of quality scores provided by the observer with the proposed metrics, that indicate a fine performance when compared with several state-of-the-art image quality assessment methods.