Screen content video quality assessment based on spatiotemporal sparse feature

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Rui Ding
  • Huanqiang Zeng
  • Hao Wen
  • Hailiang Huang
  • Shan Cheng

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number103912
Journal / PublicationJournal of Visual Communication and Image Representation
Volume96
Online published9 Aug 2023
Publication statusPublished - Oct 2023

Abstract

In recent years, the explosive growth of application scenarios have occurred in screen content videos (SCVs), in which the SCVs are unavoidably suffered from the quality degradation and the video quality assessment (VQA) of the SCVs becomes very essential. In view of this, a full-reference VQA algorithm, called the spatiotemporal sparse feature-based model (SSFM) is proposed in this paper, aiming to give a precise and efficient quality evaluation about the distorted SCVs. Note that the SCVs are full of edge information which the human eyes are highly sensitive to, and the sparse coding can provide accurate quantitative predictions which are consistent with the perception resulted from the cerebral cortex in various receptive field models of the visual cortex. With these considerations, three dimensional Difference of Gaussian (3D-DOG) filter and 3D Sparse Dictionary are developed to extract multi-scale spatiotemporal features and obtain spatiotemporal sparse features respectively, from the reference and distorted SCVs. Based on these features, the spatiotemporal sparse feature similarity can be measured and followed by generating the quality scores of the distorted SCVs under evaluation. Compared to other classic and state-of-the-art image/video quality evaluation metrics, the experimental results of the proposed SSFM on the screen content video database (SCVD) are more consistent with the perceived evaluation of SCVs according to the human visual system (HVS). © 2023 Elsevier Inc.

Research Area(s)

  • Dictionary learning, Screen content video, Spatiotemporal sparse feature, Three dimensional Difference of Gaussian

Citation Format(s)

Screen content video quality assessment based on spatiotemporal sparse feature. / Ding, Rui; Zeng, Huanqiang; Wen, Hao et al.
In: Journal of Visual Communication and Image Representation, Vol. 96, 103912, 10.2023.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review