SAR Images Target Recognition Based on Wavelet and KSVD

DOI

10.2991/icwcsn-16.2017.70How to use a DOI?

Keywords

synthetic aperture radar(SAR); feature extraction; target recognition; kernel singular value decomposition(KSVD); wavelet

Abstract

Ship targets recognition algorithm based on wavelet domain Kernel Singular Value Decomposition(KSVD) feature extraction was proposed to deal with the problem of ship targets recognition in SAR images. Low-frequency sub-band image is obtained by two-dimension discrete wavelet decomposition of a SAR image. Then it acquires the nonlinear algebraic feature of SAR images by performing KSVD. Support vector machine is used to perform target recognition.The method is applied for recognizing three-class ship targets and the average recognition arrives at 93.89%. It is concluded that the method proposed in this paper is an effective method for SAR images feature extraction and target recognition.

Copyright

© 2017, 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  - Lei Liu
AU  - Xiang-Wei Meng
AU  - Zhao-Gen Zhong
AU  - Ke-Yuan Yu
PY  - 2016/12
DA  - 2016/12
TI  - SAR Images Target Recognition Based on Wavelet and KSVD
BT  - Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)
PB  - Atlantis Press
SP  - 323
EP  - 326
SN  - 2352-538X
UR  - https://doi.org/10.2991/icwcsn-16.2017.70
DO  - 10.2991/icwcsn-16.2017.70
ID  - Liu2016/12
ER  -