A New Salient Region Detection Based on Biomimetic Information

DOI

10.2991/3ca-13.2013.19How to use a DOI?

Keywords

salient object detection, biomimetic information, image features, multi-scale saliency

Abstract

In our paper, we develop a new method of detecting salient region. It outputs full resolution saliency maps with uniformly highlighted the entire salient region. In our proposed method , we incorporate the traditional low-level features with high dimension biomimetic information geometry theory and priori knowledge. Extensive experiments on one of the largest public salient object detection benchmark have demonstrated that our method can effectively achieve good performance to the exiting methods. Our method has obtained higher precision and better recall rates on the segmentation task comparing to the five advanced salient region detection algorithms.

Copyright

© 2013, 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  - Zongmin Li
AU  - Jinfeng Chen
PY  - 2013/04
DA  - 2013/04
TI  - A New Salient Region Detection Based on Biomimetic Information
BT  - Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation
PB  - Atlantis Press
SP  - 74
EP  - 77
SN  - 1951-6851
UR  - https://doi.org/10.2991/3ca-13.2013.19
DO  - 10.2991/3ca-13.2013.19
ID  - Li2013/04
ER  -