Feature selection for ERS-1/2 InSAR classification: high dimensionality case
- 1 January 1998
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1605-1607 vol.3
- https://doi.org/10.1109/igarss.1998.691637
Abstract
A systematic way of selection and assessment of the performance of a large number of texture features extracted from spaceborne interferometric SAR data and classified with different types of classifiers is presented. Multi-seasonal ERS-1 and ERS-2 SAR data of the Czech Republic is used to classify into four different land-cover classes. A multistage search method in the space of all possible feature subsets taken from local statistics, fractal analysis and co-occurrence matrices is proposed and tested. In the early stages of the method, features are ranked according to its discriminatory power measured by a ranking coefficient based on subset performance measured by Jeffreis-Matusita-distance. Best ranked features are chosen and a new set is formed and evaluated using the hold-out method employing maximum-likelihood, nearest neighbor and multilayer perceptron classifiers.Keywords
This publication has 8 references indexed in Scilit:
- A direct adaptive method for faster backpropagation learning: the RPROP algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Feature extraction and selection for ERS-1/2 InSAR classificationInternational Journal of Remote Sensing, 1999
- Texture fusion and feature selection applied to SAR imageryIEEE Transactions on Geoscience and Remote Sensing, 1997
- Neural Networks for Pattern RecognitionPublished by Oxford University Press (OUP) ,1995
- Image processing and neural networks for recognition of cartographic area featuresPattern Recognition, 1994
- ON AUTOMATIC FEATURE SELECTIONInternational Journal of Pattern Recognition and Artificial Intelligence, 1988
- Refined filtering of image noise using local statisticsComputer Graphics and Image Processing, 1981
- Textural Features for Image ClassificationIEEE Transactions on Systems, Man, and Cybernetics, 1973