Community Research and Development Information Service - CORDIS

Abstract

Artificial neural networks and statistical classifiers both give good performance in image classification. Since the two methods are based on significantly different mathematical approaches and have complementary capabilities, a useful solution for optimising performance is to combine them. In this method both neural network and maximum-likelihood classifiers are initially trained concurrently with the same data set. A second neural network is then trained using only pixels for which the two classifiers did not initially agree. This second network is thus trained specifically to discriminate ambiguous pixels. In the actual classification a simple procedure is adopted to decide which of the classifiers is best to use for a given pixel. In this paper the maximum-likelihood and neural network techniques are compared and a method to integrate the two types of classifier is presented.

Additional information

Authors: KANELLOPOULOS I, JRC Ispra (IT);WILKINSON G G, JRC Ispra (IT);MÉGIER J, JRC Ispra (IT)
Bibliographic Reference: Paper presented: International Geoscience and R.S. Symposium (IGARSS), Tokyo (JP), August 18-21, 1993
Availability: Available from (1) as Paper EN 37631 ORA
Record Number: 199311024 / Last updated on: 1994-11-29
Category: PUBLICATION
Original language: en
Available languages: en