Optimal decision fusion using sparse representation‐based classifiers on monogenic‐signal dictionaries for SAR ATR

2020 ◽  
Vol 56 (12) ◽  
pp. 619-621
Author(s):  
B.M. Shafie ◽  
P. Moallem ◽  
M.F. Sabahi
Keyword(s):  
Sparse Representation ◽  
Decision Fusion ◽  
Optimal Decision ◽  
Monogenic Signal

scholarly journals Rust Detection of Steel Structure via One-Class Classification and L2 Sparse Representation with Decision Fusion

2020 ◽  
Vol E103.D (2) ◽  
pp. 450-453
Author(s):  
Guizhong ZHANG ◽  
Baoxian WANG ◽  
Zhaobo YAN ◽  
Yiqiang LI ◽  
Huaizhi YANG
Keyword(s):  
Sparse Representation ◽  
Steel Structure ◽  
Decision Fusion ◽  
One Class Classification

Optimal decision fusion given sensor rules

2005 ◽  
Vol 3 (1) ◽  
pp. 47-54 ◽  
Author(s):  
Yunmin Zhu ◽  
Xiaorong Li
Keyword(s):  
Decision Fusion ◽  
Optimal Decision

scholarly journals A SAR Target Recognition Method Based on Decision Fusion of Multiple Features and Classifiers

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhengwu Lu ◽  
Guosong Jiang ◽  
Yurong Guan ◽  
Qingdong Wang ◽  
Jianbo Wu
Keyword(s):  
Sparse Representation ◽  
Target Recognition ◽  
Decision Fusion ◽  
Operating Conditions ◽  
Kernel Principal Component Analysis ◽  
Support Vector ◽  
Recognition Method ◽  
Multiple Features ◽  
Decision Variables ◽  
Sar Target Recognition

A synthetic aperture radar (SAR) target recognition method combining multiple features and multiple classifiers is proposed. The Zernike moments, kernel principal component analysis (KPCA), and monographic signals are used to describe SAR image features. The three types of features describe SAR target geometric shape features, projection features, and image decomposition features. Their combined use can effectively enhance the description of the target. In the classification stage, the support vector machine (SVM), sparse representation-based classification (SRC), and joint sparse representation (JSR) are used as the classifiers for the three types of features, respectively, and the corresponding decision variables are obtained. For the decision variables of the three types of features, multiple sets of weight vectors are used for weighted fusion to determine the target label of the test sample. In the experiment, based on the MSTAR dataset, experiments are performed under standard operating condition (SOC) and extended operating conditions (EOCs). The experimental results verify the effectiveness, robustness, and adaptability of the proposed method.

scholarly journals Optimal Decision Fusion in Multiple Sensor Systems

1987 ◽  
Vol AES-23 (5) ◽  
pp. 644-653 ◽  
Author(s):  
Stelios Thomopoulos ◽  
Ramanarayanan Viswanathan ◽  
Dimitrios Bougoulias
Keyword(s):  
Decision Fusion ◽  
Optimal Decision ◽  
Sensor Systems ◽  
Multiple Sensor
Sign in / Sign up

Export Citation Format

Share Document