A new approach for spectral feature extraction and for unsupervised classification of hyperspectral data based on the Gaussian mixture model

Remote Sensing Reviews

Volumn 20, Issue 2, 2001, Pages 123-167

  Koltunov, A ^a   Ben Dor, E ^a  

^a TEL AVIV UNIVERSITY   (Israel)

Author keywords

Feature extraction; Gaussian mixture; Hyperspectral remote sensing; Lower confidence bound; Unsupervised classification

Indexed keywords

ALGORITHMS; CLASSIFICATION (OF INFORMATION); COMPUTER SIMULATION; DECISION THEORY; FEATURE EXTRACTION; LEARNING SYSTEMS; PROBABILITY;

GAUSSIAN MIXTURE MODEL;

REMOTE SENSING;

IMAGE CLASSIFICATION; PIXEL; REMOTE SENSING; SPECTRAL ANALYSIS;

ISRAEL; NAAN;

EID: 0035342809     PISSN: 02757257     EISSN: None     Source Type: Journal    
DOI: 10.1080/02757250109532431     Document Type: Article

References (64)

1. A new look at the statistical identification model
2. A study of the classification capabilities of several neural networks using unsupervised learning: A comparison with k-means clustering
3. Model-based Gaussian and non-Gaussian clustering
4. The reflectance spectra organic matter in the visible, near infrared, and short wave infrared region (400-2.500 nm) during a control decomposition process
5. Determination of surface reflectance from raw hyperspectral data without simultaneous ground data measurements: A case study of the GER-63 channel sensor data acquired over Naan, Israel
6. Automating spectral unmixing of AVIRIS data using convex geometry concepts
7. Automated spectral analysis: A geological example using AVIRIS data, North Grapevine Mountains, Nevada
8. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system
9. Probabilities vs fuzzy reasoning
10. Bayesian classification (AutoClass): Theory and results
11. Neural networks: A review from a. statistical perspective
12. Training set and a priori probabilities with the nearest neighbour method of pattern recognition
13. Maximum likelihood from incomplete data via the EM-algorithm
14. Nonparametric estimates of standard error: The jackknife, the boot-strap and other methods
15. Unsupervised segmentation of spaceborne passive radar images
16. Sharpening fuzzy classification output to refine the representation of subpixel land cover distribution
17. Estimation of sub-pixel land cover composition in the presence of untrained classes
18. Sub-pixel land cover composition estimation using a linear mixture model and fuzzy membership functions
19. How many clusters? Which clustering method? Answers via model-based cluster analysis
20. MCLUST: Software for model-based cluster analysis
21. Error rate estimation on the basis of posterior probabilities
22. An operational method for estimating signal to noise ratios from data acquired with imaging spectrometers
23. Imaging spectroscopy for earth remote sensing
24. Topics in the statistical analysis of remotely sensed data
25. Covariance matrix estimation and classification with limited training data
26. A review of mixture modeling techniques for sub-pixel land cover estimation
27. An information-theoretic analysis of hard and soft assignment methods for clustering
28. New spectral features and Gaussian mixture technique (SFGM) for landscape classification of hyperspectral data
29. Spectral identification (1.2-2.5 μm) and characterization of Paris basin kaolinite/smectite clays using a field spectrometer
30. Fuzzy classification of spatially degraded thematic mapper data for the estimation of sub-pixel components
31. SEM algorithm and unsupervised statistical segmentation of satellite images
32. On bootstrapping the likelihood ratio test statistics for the number of components in a normal mixture
33. An algorithm for unsupervised learning via normal mixture models
34. MIJFIT: An algorithm for the automatic fitting and testing of normal mixture models
35. ART I and pattern clustering
36. Floating search methods in feature selection
37. Mixture densities, maximum likelihood and EM algorithm
38. Correction of atmospheric and topographic effects for high resolution satellite imagery
39. Statistical aspects of neural networks
40. Neural networks and related methods for classification
41. Stochastic complexity
42. Neural networks and statistical models
43. Estimation the dimension of a model
44. Clustering criteria, and multivariate normal mixtures
45. Covariance matrix estimation with limited samples
46. An information measure for classification
47. Fuzzy supervised classification of remote sensing images
48. Forest mapping from multi-source satellite data using neural network classifiers - An experiment in portugal
49. Fuzzy sets