Multidimensional local spatial autocorrelation measure for integrating spatial and spectral information in hyperspectral image band selection

Authors:
Zheng Du;Young-Seon Jeong;Myong K. Jeong;Seong G. Kong
Affiliations:
Department of Electrical and Computer Engineering, The University of Tennessee, Knoxville, USA 37996-2100;Department of Industrial and Systems Engineering, Rutgers University, Piscataway, USA 08854-8003;Department of Industrial and Systems Engineering, KAIST, Daejon, Korea 305-701 and Department of Industrial and Systems Engineering & RUTCOR, Rutgers University, Piscataway, USA 08854-8003;Department of Electrical and Computer Engineering, Temple University, Philadelphia, USA 19122
Venue:
Applied Intelligence
Year:
2012

Citing 6
Cited 4

Estimating attributes: analysis and extensions of RELIEF

ECML-94 Proceedings of the European conference on machine learning on Machine Learning
Introductory Digital Image Processing: A Remote Sensing Perspective

Introductory Digital Image Processing: A Remote Sensing Perspective
Incremental Feature Selection

Applied Intelligence
Band selection of hyperspectral images based on Bhattacharyya distance

WSEAS Transactions on Information Science and Applications
Multi-scale temporal segmentation and outlier detection in sensor networks

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Recursive support vector censored regression for monitoring product quality based on degradation profiles

Applied Intelligence

Designing heterogeneous distributed GAs by efficiently self-adapting the migration period

Applied Intelligence
Image retrieval based on augmented relational graph representation

Applied Intelligence
Determining topological relationship of fuzzy spatiotemporal data integrated with XML twig pattern

Applied Intelligence
Querying fuzzy spatiotemporal data using XQuery

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hyperspectral band selection aims at the determination of an optimal subset of spectral bands for dimensionality reduction without loss of discriminability. Many conventional band selection approaches depend on the concept of "statistical distance" measure between the probability distributions characterizing sample classes. However, the maximization of separability does not necessarily guarantee that a classification process results in the best classification accuracies. This paper presents a multidimensional local spatial autocorrelation (MLSA) measure that quantifies the spatial autocorrelation of the hyperspectral image data. Based on the proposed spatial measure, a collaborative band selection strategy is developed that combines both spectral separability measure and spatial homogeneity measure for hyperspectral band selection without losing the spectral details useful in classification processes. The selected band subset by the proposed method shows both larger separability between classes and stronger spatial similarity within class. Case studies in biomedical and remote sensing applications demonstrate that the MLSA-based band selection approach improves object classification accuracies in hyperspectral imaging compared with conventional approaches.