Combination of parametric and neutral classifiers for analysis of multi-sensor remote sensing imagery
The classification of remotely-sensed satellite data for land surface mapping is a complex pattern recognition problem. Recent work has shown that neural networks perform better than parametric or statistical classifiers in a large number of cases. A simple method for integrating neural and statistical classifiers is proposed. The integration is achieved in a multi-stage process in which two classifiers of different types are initially trained to classify the same multi-sensor training data, and then samples for which the two classifiers are in disagreement are used to train an additional second stage neural classifier. Preliminary results show that significant improvements can be made in overall classification performance compared to using either neural or parametric classifiers alone.
Bibliographic Reference: Paper presented: Spie International Symposium on Optics Imaging and Instrumentation, San Diego (US), July 24-29, 1994
Availability: Available from (1) as Paper EN 38334 ORA
Record Number: 199410649 / Last updated on: 1994-11-28
Original language: en
Available languages: en