IEICE TRANSACTIONS on Information
Extreme Learning Machine with Superpixel-Guided Composite Kernels for SAR Image Classification
Summary :
Synthetic aperture radar (SAR) image classification is a popular yet challenging research topic in the field of SAR image interpretation. This paper presents a new classification method based on extreme learning machine (ELM) and the superpixel-guided composite kernels (SGCK). By introducing the generalized likelihood ratio (GLR) similarity, a modified simple linear iterative clustering (SLIC) algorithm is firstly developed to generate superpixel for SAR image. Instead of using a fixed-size region, the shape-adaptive superpixel is used to exploit the spatial information, which is effective to classify the pixels in the detailed and near-edge regions. Following the framework of composite kernels, the SGCK is constructed base on the spatial information and backscatter intensity information. Finally, the SGCK is incorporated an ELM classifier. Experimental results on both simulated SAR image and real SAR image demonstrate that the proposed framework is superior to some traditional classification methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E101-D No.6 pp.1703-1706
- Publication Date
- 2018/06/01
- Publicized
- 2018/03/14
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017EDL8281
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Dongdong GUAN
National University of Defense Technology
Xiaoan TANG
National University of Defense Technology
Li WANG
National University of Defense Technology
Junda ZHANG
National University of Defense Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Dongdong GUAN, Xiaoan TANG, Li WANG, Junda ZHANG, "Extreme Learning Machine with Superpixel-Guided Composite Kernels for SAR Image Classification" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 6, pp. 1703-1706, June 2018, doi: 10.1587/transinf.2017EDL8281.
Abstract: Synthetic aperture radar (SAR) image classification is a popular yet challenging research topic in the field of SAR image interpretation. This paper presents a new classification method based on extreme learning machine (ELM) and the superpixel-guided composite kernels (SGCK). By introducing the generalized likelihood ratio (GLR) similarity, a modified simple linear iterative clustering (SLIC) algorithm is firstly developed to generate superpixel for SAR image. Instead of using a fixed-size region, the shape-adaptive superpixel is used to exploit the spatial information, which is effective to classify the pixels in the detailed and near-edge regions. Following the framework of composite kernels, the SGCK is constructed base on the spatial information and backscatter intensity information. Finally, the SGCK is incorporated an ELM classifier. Experimental results on both simulated SAR image and real SAR image demonstrate that the proposed framework is superior to some traditional classification methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8281/_p
Copy
@ARTICLE{e101-d_6_1703,
author={Dongdong GUAN, Xiaoan TANG, Li WANG, Junda ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Extreme Learning Machine with Superpixel-Guided Composite Kernels for SAR Image Classification},
year={2018},
volume={E101-D},
number={6},
pages={1703-1706},
abstract={Synthetic aperture radar (SAR) image classification is a popular yet challenging research topic in the field of SAR image interpretation. This paper presents a new classification method based on extreme learning machine (ELM) and the superpixel-guided composite kernels (SGCK). By introducing the generalized likelihood ratio (GLR) similarity, a modified simple linear iterative clustering (SLIC) algorithm is firstly developed to generate superpixel for SAR image. Instead of using a fixed-size region, the shape-adaptive superpixel is used to exploit the spatial information, which is effective to classify the pixels in the detailed and near-edge regions. Following the framework of composite kernels, the SGCK is constructed base on the spatial information and backscatter intensity information. Finally, the SGCK is incorporated an ELM classifier. Experimental results on both simulated SAR image and real SAR image demonstrate that the proposed framework is superior to some traditional classification methods.},
keywords={},
doi={10.1587/transinf.2017EDL8281},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Extreme Learning Machine with Superpixel-Guided Composite Kernels for SAR Image Classification
T2 - IEICE TRANSACTIONS on Information
SP - 1703
EP - 1706
AU - Dongdong GUAN
AU - Xiaoan TANG
AU - Li WANG
AU - Junda ZHANG
PY - 2018
DO - 10.1587/transinf.2017EDL8281
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2018
AB - Synthetic aperture radar (SAR) image classification is a popular yet challenging research topic in the field of SAR image interpretation. This paper presents a new classification method based on extreme learning machine (ELM) and the superpixel-guided composite kernels (SGCK). By introducing the generalized likelihood ratio (GLR) similarity, a modified simple linear iterative clustering (SLIC) algorithm is firstly developed to generate superpixel for SAR image. Instead of using a fixed-size region, the shape-adaptive superpixel is used to exploit the spatial information, which is effective to classify the pixels in the detailed and near-edge regions. Following the framework of composite kernels, the SGCK is constructed base on the spatial information and backscatter intensity information. Finally, the SGCK is incorporated an ELM classifier. Experimental results on both simulated SAR image and real SAR image demonstrate that the proposed framework is superior to some traditional classification methods.
ER -
English
