Evolving multi-spectral neural network classifier using a genetic algorithm

This paper will investigate the effectiveness of the genetic algorithm evolved neural network classifier and its application on the land cover classification of multi-spectral remotely sensed imagery. First, the key issues of the algorithms and the procedures are described in detail. Second, SPOT XS imagery is employed to evaluate its accuracy. Traditional classification algorithms, such as maximum likelihood classifier, back propagation neural network classifier, are also incorporated for a comparison purpose. Based on an evaluation of the user´s accuracy and kappa statistic of different classifiers, the superiority of applying the discussed genetic algorithm-based classifier for land cover classification using multi-spectral imagery data is established. Finally, some concluding remarks and suggestions are also presented.