Terrain Classification Using Clustering Algorithms

Texture analysis has been efficiently utilized in the area of terrain classification. The widely used co-occurrence features have been reported most effective for this application. Since the number of co-occurrence features is very high, a terrain classifier based on co-occurrence features should deal with high dimensionality problem. This paper deals with how to solve high dimensionality problems by employing a conventional linear discriminant classifier and clustering algorithms based on ANN (Artificial Neural Network). A implemented linear discriminant classifier is based on dimensionality reduction by using FST (Foley-Sammon transform), and its result is compared with ANN clustering algorithm FCM (Fuzzy C-mean). Experimental results show that the overall classification accuracy using clustering algorithm is good, especially for some particular classes.