Multi-class SVMs for Image Classification using Feature Tracking
Aba Graf, Christian Wallraven · MPG.PuRe (Max Planck Society) · 2002
In this paper a novel representation for image classification is proposed which exploits the temporal information inherent in natural visual input. Image sequences are represented by a set of salient features which are found by tracking of visual features. In the context of a multi-class classification problem this representation is compared against a representation using only raw image data. The dataset consists of image sequences generated from a processed version of the MPI face database. We consider two types of multi-class SVMs and benchmark them against nearest-neighbor classifiers. By introducing a new set of SVM kernel functions we show that the feature representation significantly outperforms the view representation.