Recently, strategies involving learning a supervised model are emerging in the field of multimedia content-based retrieval. When there are clearly identified categories, as well as, large domain-representative training data, learning can be effectively employed to construct a model of the domain.

In this paper, an adequately domain-independent approach is presented where local features can characterize multimedia data using Artificial Neural Networks (ANN) and Support Vector Machines (SVM). The classification in content-based retrieval requires non-linear mapping of feature space. This can normally be accomplished by ANN and SVM. However, they inherently lack the capability to deal with meaningful feature evaluation and large dimensional feature space in the sense that they are inaccurate and slow. We overcome these defects by employing discrete Bayesian error based meaningful feature selection. The experiments on database consisting of real video sequences show that the speed and accuracy of SVM can be improved substantially using this technique, while execution time can be substantially reduced for ANN. The comparison also shows that improved SVM turns out to be a better choice than ANN. Finally, it is shown that generalization in learning is not affected by reducing the dimension of the feature space by the proposed method.