In this work, we analyze the effectiveness of perceptual features to automatically annotate video clips in domain-specific video digital libraries. Typically, automatic annotation is provided by computing clip similarity with respect to given examples, which constitute the knowledgebase, in accordance with a given ontology or a classification scheme. Since the amount of training clips is normally very large, we propose to automatically extract some prototypes, or visual concepts, for each class instead of using the whole knowledge base. The prototypes are generated after a Complete Link clustering based on perceptual features with an automatic selection of the number of clusters. Context based information are used in an intra-class clustering framework to provide selection of more discriminative clips. Reducing the number of samples makes the matching process faster and lessens the storage requirements. Clips are annotated following the MPEG-7 directives to provide easier portability. Results are provided on videos taken from sports and news digital libraries.
Prototypes Selection with Context Based Intra-class Clustering for Video Annotation with Mpeg7 Features / Grana, Costantino; Vezzani, Roberto; Cucchiara, Rita. - STAMPA. - 4877:(2007), pp. 268-277. (Intervento presentato al convegno 1st International DELOS Conference tenutosi a Pisa, ita nel Feb 13-14) [10.1007/978-3-540-77088-6_26].