Combinatorial Optimization of Resolution Level for 3D Scene Based on Regional Weighted Information Entropy

DOI

10.2991/icmii-15.2015.140How to use a DOI?

Keywords

3D scene; Resolution level; Visual perception; Information entropy; Particle Swarm Optimization

Abstract

With respect to the problem that traditional combination of resolution level methods for 3D scene either can easily fall into tedious and repeated experiments for interaction design or fail to provide results that conform to human visual habits. In this paper, an intelligent combination of resolution level based on visual perception driven visual quality evaluation method is proposed. Through analyzing the influence of several digital image factors on human visual characteristic, the mathematical models are established. Combined with information entropy theory, an objective image quality evaluation metric in line with visual characteristics is built. Evolution algorithm is utilized to select the resolution level automatically and intelligently. Experimental results demonstrate that the scene drawn by the proposed algorithm shares more common with the sensory choice of human beings. In comparison with existing methods, the proposed method has high efficiency and requires no user interaction.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Li Che
AU  - Fengju Kang
PY  - 2015/10
DA  - 2015/10
TI  - Combinatorial Optimization of Resolution Level for 3D Scene Based on Regional Weighted Information Entropy
BT  - Proceedings of the 3rd International Conference on Mechatronics and Industrial Informatics
PB  - Atlantis Press
SP  - 800
EP  - 807
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmii-15.2015.140
DO  - 10.2991/icmii-15.2015.140
ID  - Che2015/10
ER  -