GEOSCAN Search Results: Fastlink


TitleCommitment and typicality measures for the Self-Organizing Map
AuthorLi, Z; Eastman, J R
SourceInternational Journal of Remote Sensing vol. 31, no. 16, 2010 p. 4265-4280,
Alt SeriesNatural Resources Canada, Contribution Series 20181664
PublisherInforma UK Limited
Mediapaper; on-line; digital
File formatpdf
Subjectsgeophysics; remote sensing
ProgramCanada Centre for Remote Sensing Divsion
Released2010 09 13
AbstractSoft classification using Kohonen's Self-Organizing Map (SOM) has not been explored as thoroughly as the Multi-Layer-Perceptron (MLP) neural network. In this paper, we propose two non-parametric algorithms for theSOMto provide soft classification outputs. These algorithms, which are labelling-frequency-based, are called SOM Commitment (SOM-C) and SOM Typicality (SOM-T), expressing in the first case the degree of commitment the classifier has for each class for a specific pixel and in the second case, how typical that pixel's reflectances are of those upon which the classifier was trained. To evaluate the two proposed algorithms, soft classifications of a Satellite Pour l'Observation de la Terre (SPOT) High Resolution Visible (HRV) image and an Airborne Visible Infrared Imaging Spectrometer (AVIRIS) image were undertaken. Both traditional soft classifiers, i.e. Bayesian posterior probability and Mahalanobis typicality classifier, and the most frequently used non-parametric neural network model, i.e. MLP, were used as a comparison. Principal-components analysis (PCA) was used to explore the relationship between these measures. Results indicate that great similarities exist between the SOM-C, MLPand the Bayesian posterior probability classifiers, while the SOM-T corresponds closely with Mahalanobis typicality probabilities. However, as implemented, they have the advantage of being non-parametric. The proposed measures significantly outperformed Bayesian and Mahalanobis classifiers when using the hyperspectral AVIRIS image.

Date modified: