Open AccessA Novel Separability Objective Function in CNN for Feature Extraction of SAR Images
Author(s) -
Gao Fei,
Wang Meng,
Wang Jun,
Yang Erfu,
Zhou Huiyu
Publication year - 2019
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2018.12.001
Subject(s) - pattern recognition (psychology) , artificial intelligence , feature extraction , computer science , function (biology) , extraction (chemistry) , feature (linguistics) , image (mathematics) , computer vision , linguistics , philosophy , evolutionary biology , biology , chemistry , chromatography
Convolutional neural network (CNN) has become a promising method for Synthetic aperture radar (SAR) target recognition. Existing CNN models aim at seeking the best separation between classes, but rarely care about the separability of them. We performs a separability measure by analyzing the property of linear separability, and proposes an objective function for CNN to extract linearly separable features. The experimental results indicate the output features are linearly separable, and the classification results are comparable with the other state of the art techniques.