Title :
Story Segmentation in News video
Author :
Feng, Huamin ; Zhai, Xiaofei ; Fan, Jingwang ; Fang, Yong
Author_Institution :
Key Lab. of Security & Secrecy of Inf., BESTI, Beijing
Abstract :
This paper presents a two-level framework for news video segmentation. Our system is established based upon a similar framework as in [Chaisorn et al. 2002]. We extended the original framework by adding rule-based pre-segmentation module and new features. We perform decision trees at the shot level and HMM (hidden Markov models) analysis at the story level respectively. Experimental result with 24 hours (967 story units) training and 18 hours (718 story units) testing CCTV-9 (China Central TV-International) news videos show that our framework can achieve 96.3% in terms of F1 based on our ground truth which have been correctly tagged
Keywords :
decision trees; hidden Markov models; image segmentation; video signal processing; decision trees; hidden Markov models analysis; news video segmentation; story segmentation; Decision trees; Educational institutions; Feature extraction; Hidden Markov models; Information security; Laboratories; Layout; Logic; Performance analysis; Weather forecasting;
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
DOI :
10.1109/ICNNB.2005.1614751
