Design Software for Classify Objects for Air Photos & Satellite Images

This Book presents a method to design programming system using hybrid techniques represented soft computing to classify objects from the air photos and satellite images depending on their features with minimum acceptable error.This book concerns with classifying five kinds of objects (urban area, forests,roads, rivers and football-stadiums). Accordingly, the database which describes that objects by depending on their attributes were built.Then, the breeder genetic algorithm to procedure genetic clustering process to segment image which provides a number of clusters found in that image data set were used.To avoid the overlapping between clusters with other, one of the clustering validity measures called "Davies-Bouldin index"as fitness function and four type of Crossover are used. Then, two types of features for each cluster which are visual features including (Pattern, Shape, Texture, Shadow, Associative), and statistical features represented by spectrum features that include(Intensity, Hue, Saturation) were extracted. After that, feed forward neural network from type error back propagation neural network to determine the class under which each feature vector belongs to was used.