An application of support vector machines for image retrieval

Various methods including artificial neural networks have been used to classify a large image database efficiently and shown to be highly successful in this application area. This paper presents a new, scaling and rotation invariant encoding scheme for shapes. Support vector machines (SVMs) are used for the classifications of shapes encoded by the new method. In order to evaluate one-class SVMs, this paper examines the performance of the proposed method by comparing it with that of multilayer perception, one of the artificial neural network (ANNs) techniques, based on real real-world image data. The experiment shows that the results of one-class SVMs outperform those of ANNs.