An Innovative Method to Classify Remote-Sensing Images Using Ant Colony Optimization

This paper presents a new method to improve the classification performance for remote-sensing applications based on swarm intelligence. Traditional statistical classifiers have limitations in solving complex classification problems because of their strict assumptions. For example, data correlation between bands of remote-sensing imagery has caused problems in generating satisfactory classification using statistical methods. In this paper, ant colony optimization (ACO), based upon swarm intelligence, is used to improve the classification performance. Due to the positive feedback mechanism, ACO takes into account the correlation between attribute variables, thus avoiding issues related to band correlation. A discretization technique is incorporated in this ACO method so that classification rules can be induced from large data sets of remote-sensing images. Experiments of this ACO algorithm in the Guangzhou area reveal that it yields simpler rule sets and better accuracy than the See 5.0 decision tree method.