Automatic band selection in multispectral images using mutual information-based clustering

Authors:
Adolfo Martínez-Usó;Filiberto Pla;Pedro García-Sevilla;J. M. Sotoca
Affiliations:
LSI Department, Jaume I University, Castellón, Spain;LSI Department, Jaume I University, Castellón, Spain;LSI Department, Jaume I University, Castellón, Spain;LSI Department, Jaume I University, Castellón, Spain
Venue:
CIARP'06 Proceedings of the 11th Iberoamerican conference on Progress in Pattern Recognition, Image Analysis and Applications
Year:
2006

Citing 8
Cited 0

Algorithms for clustering data

Algorithms for clustering data
Hierarchy in Picture Segmentation: A Stepwise Optimization Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating attributes: analysis and extensions of RELIEF

ECML-94 Proceedings of the European conference on machine learning on Machine Learning
Cluster merging and splitting in hierarchical clustering algorithms

ICDM '02 Proceedings of the 2002 IEEE International Conference on Data Mining
A divisive information theoretic feature clustering algorithm for text classification

The Journal of Machine Learning Research
Dissimilarity measures for visual pattern partitioning

IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II
Supervised classification in high-dimensional space: geometrical, statistical, and asymptotical properties of multivariate data

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Image classification for content-based indexing

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.04

Visualization

Abstract

Feature selection and dimensionality reduction are crucial research fields in pattern recognition. This work presents the application of a novel technique on dimensionality reduction to deal with multispectral images. A distance based on mutual information is used to construct a hierarchical clustering structure with the multispectral bands. Moreover, a criterion function is used to choose automatically the number of final clusters. Experimental results show that the method provides a very suitable subset of multispectral bands for pixel classification purposes.