Combining deep convolutional neural network and SVM to SAR image target recognition

Gao, Fei and Huang, Teng and Wang, Jun and Sun, Jinping and Yang, Erfu and Hussain, Amir; (2018) Combining deep convolutional neural network and SVM to SAR image target recognition. In: 2017 IEEE International Conference on Internet of Things, IEEE Green Computing and Communications, IEEE Cyber, Physical and Social Computing, IEEE Smart Data, iThings-GreenCom-CPSCom-SmartData 2017. IEEE, GBR, pp. 1082-1085. ISBN 9781538630655

[thumbnail of Gao-etal-IEEE-2017-Combining-deep-convolutional-neural-network-and-SVM-to-SAR-image-target-recognition]
Preview
Text (Gao-etal-IEEE-2017-Combining-deep-convolutional-neural-network-and-SVM-to-SAR-image-target-recognition)
Gao_etal_IEEE_2017_Combining_deep_convolutional_neural_network_and_SVM_to_SAR_image_target_recognition.pdf
Accepted Author Manuscript

Download (9MB)| Preview

    Abstract

    To address the challenging problem on target recognition from synthetic aperture radar (SAR) images, a novel method is proposed by combining Deep Convolutional Neural Network (DCNN) and Support Vector Machine (SVM). First, an improved DCNN is employed to learn the features of SAR images. Then, a SVM is utilized to map the leant features into the output labels. To enhance the feature extraction capability of DCNN, a class of separation information is also added to the cross-entropy cost function as a regularization term. As a result, this explicitly facilitates the intra-class compactness and separability in the process of feature learning. Numerical experiments are performed on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database. The results demonstrate that the proposed method can achieve an average accuracy of 99.15% on ten types of targets.

    ORCID iDs

    Gao, Fei, Huang, Teng, Wang, Jun, Sun, Jinping, Yang, Erfu ORCID logoORCID: https://orcid.org/0000-0003-1813-5950 and Hussain, Amir;