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

Research output: ResearchConference contribution

  • Fei Gao
  • Teng Huang
  • Jun Wang
  • Jinping Sun
  • Erfu Yang
  • Amir Hussain

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.

Original languageEnglish
Title of host publication2017 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
Place of PublicationPiscataway, NJ.
PublisherIEEE
Pages1082-1085
Number of pages4
Volume2018-January
ISBN (Electronic)9781538630655
DOIs
StatePublished - 30 Jan 2018
EventJoint 10th IEEE International Conference on Internet of Things, iThings 2017, 13th IEEE International Conference on Green Computing and Communications, GreenCom 2017, 10th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2017 and the 3rd IEEE International Conference on Smart Data, Smart Data 2017 - Exeter, United Kingdom
Duration: 21 Jun 201723 Jun 2017

Conference

ConferenceJoint 10th IEEE International Conference on Internet of Things, iThings 2017, 13th IEEE International Conference on Green Computing and Communications, GreenCom 2017, 10th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2017 and the 3rd IEEE International Conference on Smart Data, Smart Data 2017
CountryUnited Kingdom
CityExeter
Period21/06/1723/06/17

    Research areas

  • automatic target recognition (ATR), class separation information, deep convolutional neural network (DCNN), support vector machine (SVM), synthetic aperture radar (SAR)

Bibliographical note

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

View graph of relations