SAR Image Segmentation by Cooperative Populations and Multi-objective Kernel Clustering Indices

DOI

10.2991/isci-15.2015.238How to use a DOI?

Keywords

image segmentation and recognition; cooperative learning; multi-objective clustering.

Abstract

This paper contributes two novel techniques in the context of synthetic aperture radar (SAR) image segmentation by cooperative learning and multi-objective clustering in kernel mapping thereof. First, we introduce an efficient implementation of cooperative evolution by using two parallel implemented populations, which are divided by the Pareto domination and local density dynamic information. Second, in order to obtain the better performance of algorithm in suppressing speckle noise in SAR image, another novelty of the study is introducing the kernel distance measure to the two objective functions. Finally, the proposed algorithm is tested on two complicated SAR images. Compared with four other state-of-the-art algorithms and our method achieve comparable results in terms of convergence, diversity metrics, and computational time.

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  - Dongdong Yang
AU  - Hui Yang
AU  - Yuanyuan Liu
PY  - 2015/01
DA  - 2015/01
TI  - SAR Image Segmentation by Cooperative Populations and Multi-objective Kernel Clustering Indices
BT  - Proceedings of the 2015 International Symposium on Computers & Informatics
PB  - Atlantis Press
SP  - 1795
EP  - 1802
SN  - 2352-538X
UR  - https://doi.org/10.2991/isci-15.2015.238
DO  - 10.2991/isci-15.2015.238
ID  - Yang2015/01
ER  -