In this paper we face the problem of partitioning the news videos into stories, and of their classification according to a predefined set of categories. In particular, we propose to employ a multi-level probabilistic framework based on the hidden Markov models and the Bayesian networks paradigms for the segmentation and the classification phases, respectively. The whole analysis is carried out exploiting information extracted from the video and the audio tracks using techniques of superimposed text recognition, speaker identification, speech transcription, anchor detection. The system was tested on a database of Italian news videos and the results are very promising
A Probabilistic Framework for TV-News Stories Detection and Classification
COLACE, Francesco;FOGGIA, PASQUALE;PERCANNELLA, Gennaro
2005-01-01
Abstract
In this paper we face the problem of partitioning the news videos into stories, and of their classification according to a predefined set of categories. In particular, we propose to employ a multi-level probabilistic framework based on the hidden Markov models and the Bayesian networks paradigms for the segmentation and the classification phases, respectively. The whole analysis is carried out exploiting information extracted from the video and the audio tracks using techniques of superimposed text recognition, speaker identification, speech transcription, anchor detection. The system was tested on a database of Italian news videos and the results are very promisingI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.