Evolutionary Approach to Discovery of Classification Rules from Remote Sensing Images
In this article a new method for classification of remote sensing images is described. For most applications, these images contain voluminous, complex, and sometimes noisy data. For the approach presented herein, image classification rules are discovered by an evolution-based process, rather than by applying an a priori chosen classification algorithm. During the evolution process, classification rules are created using raw remote sensing images, the expertise encoded in classified zones of images, and statistics about related thematic objects. The resultant set of evolved classification rules are simple to interpret, efficient, robust and noise resistant. This evolution-based approach is detailed and validated based on remote sensing images covering not only urban zones of Strasbourg, France, but also vegetation zones of the lagoon of Venice.
KeywordsGenetic Algorithm Hyperspectral Image Classification Rule Spectral Interval Mixed Pixel
Unable to display preview. Download preview PDF.
- 1.H. H. Bock, E. Diday, (eds.) Analysis of Symbolic Data. Exploratory Methods for Extracting Statistical Information from Complex Data, [in] Studies in Classification, Data Analysis and Knowledge Organization, vol. 15, Springer-Verlag, Heidelberg, 1999.Google Scholar
- 2.C. Weber, Images satellitaires et milieu urbain, Hermès, Paris, 1995.Google Scholar
- 3.K. A. DeJong, Learning with Genetic Algorithms: An Overview, Machine Learning, vol. 3, pp. 121–138, 1988.Google Scholar
- 4.S. W. Wilson, State of XCS Classifier System Research, [in] Proc. of IWLCS-99, Orlando,1999.Google Scholar
- 5.R. Fjørtoft, P. Marthon, A. Lopes, F. Sery, D. Ducrot-Gambart, E. Cubero-Castan, Region-Based Enhancement and Analysis of SAR Images, [in] Proc. of ICIP’96, vol. 3, Lausanne, pp. 879–882, 1996.Google Scholar
- 6.T. Kurita, N. Otsu, Texture Classification by Higher Order Local Autocorrelation Features, [in] Proc. of Asian Conf. on Computer Vision, Osaka, pp. 175–178, 1993.Google Scholar
- 7.J. Korczak, N. Louis, Synthesis of Conceptual Hierarchies Applied to Remote Sensing, [in] Proc. of SPIE, Image and Signal Processing for Remote Sensing IV, Barcelona, pp. 397–406, 1999.Google Scholar
- 8.M. V. Rendon, Reinforcement Learning in the Fuzzy Classifier System, Reporte de Investigaci No. CIA-RI-031, ITESM, Campus Monterrey, Centro de Inteligencia Artificial, 1997.Google Scholar
- 9.R. L. Riolo, Empirical Studies of Default Hierarchies and Sequences of Rules in Learning Classifier Systems, PhD Dissertation, Comp. Sc. and Eng. Dept, Univ. of Michigan, 1988.Google Scholar
- 10.R. A. Richards, Zeroth-Order Shape Optimization Utilizing A Learning Classifier System, http://www.stanford.edu/∼buc/SPHINcsX/book.html, Stanford, 1995.
- 11.T. Blickle, L. Thiele, A Comparison of Selection Schemes used in Genetic Algorithms, Computer Engineering and Communication Networks Lab, TIK-Report Nr. 11, Second Edition, Swiss Federal Institute of Technology, Zurich, 1995.Google Scholar
- 12.DAIS, M. Wooding, Proceedings of the Final Results Workshop on DAISEX (Digital AIrborne Spectrometer EXperiment), ESTEC, Noordwijk, 2001.Google Scholar
- 13.A. Quirin, Découverte de règles de classification: classifieurs évolutifs, Mémoire DEA d’Informatique, Université Louis Pasteur, LSIIT UMR-7005 CNRS, Strasbourg, 2002.Google Scholar