Classification of TV sports news by DCT features using multiple subspace method

This paper proposes a method to classify automatically TV sports news articles using image processing and classification techniques. The classification algorithm of TV sports news articles is based on a multiple subspace method that provides a sports category with more than one subspaces corresponding to the typical scenes. The classification is performed without recognizing any objects in an image. Discrete cosine transformation (DCT) components are used as the classification features of the whole image. The classification is performed at first on the scene cut frames and then they are integrated into the article classification.