On Endmember Detection in Hyperspectral Images with Morphological Associative Memories

Authors:
Manuel Graña;Bogdan Raducanu;Peter Sussner;Gerhard X. Ritter
Affiliations:
-;-;-;-
Venue:
IBERAMIA 2002 Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence
Year:
2002

Citing 11
Cited 2

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Morphological bidirectional associative memories

Neural Networks
Generalizing Operations of Binary Autoassociative Morphological Memories Using Fuzzy Set Theory

Journal of Mathematical Imaging and Vision
Reconstruction of Patterns from Noisy Inputs Using Morphological Associative Memories

Journal of Mathematical Imaging and Vision
Correlation Matrix Memories

IEEE Transactions on Computers
Structuring element adaptation for morphological filters

Journal of Visual Communication and Image Representation
MRL-filters: a general class of nonlinear systems and their optimal design for image processing

IEEE Transactions on Image Processing
The min-max function differentiation and training of fuzzy neural networks

IEEE Transactions on Neural Networks
Morphological shared-weight networks with applications to automatic target recognition

IEEE Transactions on Neural Networks
Morphological associative memories

IEEE Transactions on Neural Networks
Adaptive resolution min-max classifiers

IEEE Transactions on Neural Networks

A single individual evolutionary strategy for endmember search in hyperspectral images

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: FEA 2002
A comparison of gaussian based ANNs for the classification of multidimensional hyperspectral signals

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Morphological Associative Memories (MAM) are a construct similar to Hopfield Associative Memories defined on the (R,+, 驴, 驴) algebraic system. The MAM posses excellent recall properties for undistorted patterns. However they suffer from the sensitivity to specific noise models, that can be characterized as erosive and dilative noise. We find that this sensitivity may be made of use in the task of Endmember determination for the Spectral Unmixing of Hyperspectral Images.