Image primitive coding and visual quality assessment

  • Authors:
  • Jian Zhang;Siwei Ma;Ruiqin Xiong;Debin Zhao;Wen Gao

  • Affiliations:
  • School of Computer Science and Technology, Harbin Institute of Technology, Harbin, P.R. China;National Engineering Laboratory for Video Technology, Peking University, Beijing, P.R. China;National Engineering Laboratory for Video Technology, Peking University, Beijing, P.R. China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, P.R. China;National Engineering Laboratory for Video Technology, Peking University, Beijing, P.R. China

  • Venue:
  • PCM'12 Proceedings of the 13th Pacific-Rim conference on Advances in Multimedia Information Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work, we introduce a new content-adaptive compression scheme, called image primitive coding, which exploits the input image for training a dictionary. The atoms composed of the learned dictionary are named as image primitives. The coding performance between the learned image primitives and the traditional DCT basis is compared, and demonstrates the potential of image primitive coding. Furthermore, a novel concept, entropy of primitives (EoP), is proposed for measuring image visual information. Some very interesting results about EoP are achieved and analyzed, which can be further studied for visual quality assessment.