Combined descriptors and classifiers for automatic image annotation

Due to the large amounts of multimedia data prevalent on the Web, researchers and industries are beginning to pay more attention to the Multimedia Semantic Web. Despite of decades of research, neither model based approaches can provide quality annotation to images. Many features extraction method and classifiers are used singly, with modest results, for automatic image annotation. The proposed approach is to select and combine together some efficient descriptors and classifiers. This document provides a semantic annotation system that combines some descriptors and classifiers in order to increase the accuracy of the annotation system. The color histograms, Texture, GIST and invariant moments, used as features extraction methods, are combined together with multiclass support vector machine, Bayesian networks, Neural networks and nearest neighbour classifiers, in order to annotate the image content with the appropriate keywords. The accuracy of the proposed approach is supported by the good experimental results obtained from ETH-80 databases.