Classifying images collected on the World Wide Web

Abstract

This work presents the classification of images collected on the World Wide Web, using a supervised classification method, called ID3 (Itemized Dichotomizer 3). The classification consists in separating the images into two semantic classes: graphics and photographs. Photographs include natural scenes, like people, faces, animals, flowers, landscapes and cities. Graphics are logos, drawings, icons, maps, and backgrounds, usually generated by computer. To validate the classifier we used the k-fold cross-validation method. In the experimental tests 95.6% of the images were correctly classified.