In this paper, we first propose ten new discrimination features of SAR images in the moving and stationary target acquisition and recognition (MSTAR) database. The Ada_MCBoost algorithm is then proposed to classify multiclass SAR targets. In the new algorithm, we introduce a novel large-margin loss function to design a multiclass classifier directly instead of decomposing the multiclass problem into a set of binary ones through the error-correcting output codes (ECOC) method. Finally, experiments show that the new features are helpful for SAR targets discrimination; the new algorithm had better recognition performance than three other contrast methods.
Kun CHEN
Nanjing University of Science and Technology
Yuehua LI
Nanjing University of Science and Technology
Xingjian XU
Nanjing University of Science and Technology
Yuanjiang LI
Jiangsu University of Science and Technology
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.
Copy
Kun CHEN, Yuehua LI, Xingjian XU, Yuanjiang LI, "A Modified AdaBoost Algorithm with New Discrimination Features for High-Resolution SAR Targets Recognition" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 10, pp. 1871-1874, October 2015, doi: 10.1587/transinf.2015EDL8090.
Abstract: In this paper, we first propose ten new discrimination features of SAR images in the moving and stationary target acquisition and recognition (MSTAR) database. The Ada_MCBoost algorithm is then proposed to classify multiclass SAR targets. In the new algorithm, we introduce a novel large-margin loss function to design a multiclass classifier directly instead of decomposing the multiclass problem into a set of binary ones through the error-correcting output codes (ECOC) method. Finally, experiments show that the new features are helpful for SAR targets discrimination; the new algorithm had better recognition performance than three other contrast methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8090/_p
Copy
@ARTICLE{e98-d_10_1871,
author={Kun CHEN, Yuehua LI, Xingjian XU, Yuanjiang LI, },
journal={IEICE TRANSACTIONS on Information},
title={A Modified AdaBoost Algorithm with New Discrimination Features for High-Resolution SAR Targets Recognition},
year={2015},
volume={E98-D},
number={10},
pages={1871-1874},
abstract={In this paper, we first propose ten new discrimination features of SAR images in the moving and stationary target acquisition and recognition (MSTAR) database. The Ada_MCBoost algorithm is then proposed to classify multiclass SAR targets. In the new algorithm, we introduce a novel large-margin loss function to design a multiclass classifier directly instead of decomposing the multiclass problem into a set of binary ones through the error-correcting output codes (ECOC) method. Finally, experiments show that the new features are helpful for SAR targets discrimination; the new algorithm had better recognition performance than three other contrast methods.},
keywords={},
doi={10.1587/transinf.2015EDL8090},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - A Modified AdaBoost Algorithm with New Discrimination Features for High-Resolution SAR Targets Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1871
EP - 1874
AU - Kun CHEN
AU - Yuehua LI
AU - Xingjian XU
AU - Yuanjiang LI
PY - 2015
DO - 10.1587/transinf.2015EDL8090
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2015
AB - In this paper, we first propose ten new discrimination features of SAR images in the moving and stationary target acquisition and recognition (MSTAR) database. The Ada_MCBoost algorithm is then proposed to classify multiclass SAR targets. In the new algorithm, we introduce a novel large-margin loss function to design a multiclass classifier directly instead of decomposing the multiclass problem into a set of binary ones through the error-correcting output codes (ECOC) method. Finally, experiments show that the new features are helpful for SAR targets discrimination; the new algorithm had better recognition performance than three other contrast methods.
ER -