Chapter 4. On Training and Evaluation of SVM for Remote Sensing Applications

  1. Dr Gustavo Camps-Valls B.Sc., Ph.D. professor member2 and
  2. Dr Lorenzo Bruzzone M.S., Ph.D. Postdoctoral Researcher Professor member Chair3
  1. Giles M. Foody

Published Online: 4 NOV 2009

DOI: 10.1002/9780470748992.ch4

Kernel Methods for Remote Sensing Data Analysis

Kernel Methods for Remote Sensing Data Analysis

How to Cite

Foody, G. M. (2009) On Training and Evaluation of SVM for Remote Sensing Applications, in Kernel Methods for Remote Sensing Data Analysis (eds G. Camps-Valls and L. Bruzzone), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9780470748992.ch4

Editor Information

  1. 2

    Image Processing Laboratory (IPL) & Dept. Enginyeria Electrónica, Universitat de Valéncia, Spain

  2. 3

    Dept. Information Engineering and Computer Science, University of Trento, Italy

Author Information

  1. School of Geography, University of Nottingham, UK

Publication History

  1. Published Online: 4 NOV 2009
  2. Published Print: 23 OCT 2009

ISBN Information

Print ISBN: 9780470722114

Online ISBN: 9780470748992

SEARCH

Keywords:

  • on training and evaluation of SVM for remote sensing applications;
  • remote sensing in application areas;
  • thematic mapping classification;
  • first (training) and third (testing) stages of supervised classification by SVM;
  • SVM approach and common multi-class classification problem;
  • nature of class allocation by SVM;
  • training stage - descriptive statistics for each class in image;
  • popular maximum likelihood classifier;
  • testing stage of supervised classification analysis and quality of class allocations;
  • training and testing stages of supervised image classification

Summary

This chapter contains sections titled:

  • Introduction

  • Classification for thematic mapping

  • Overview of classification by a SVM

  • Training stage

  • Testing stage

  • Conclusion

  • Acknowledgments

  • References