Affiliations: [a] Computer Engineering Department, Yeungnam University, Gyeongsan, Korea
| [b] Computer Engineering Department, Chung-Ang University, Seoul, Korea
Correspondence:
[*]
Corresponding author. Jason J. Jung, Computer Engineering Department, Chung-Ang University, Seoul 756-156, Korea. Tel.: +8228205136; E-mail: j3ung@cau.ac.kr.
Note: [1] This paper is extended from an earlier version presented at The 7th International Conference on Computational Collective Intelligence Technologies and Applications (ICCCI’2015) in September 2015.
Abstract: Various content-based methods (e.g., audio-visual feature recognition and dialogs analysis) have been proposed for analyzing, indexing and understanding movies. Our previous approach introduced a method for character indexing based on manual annotation. However, this method has shown several unsatisfactoriness on performing of indexing. For addressing this issue, in this work, we take into account using image processing techniques for semi-automatically character-based indexing. Besides, a movie ontological model is created for connecting character appearances and character’s roles in the movie. Moreover, we propose a system for assist user indexing manually. On the other hand, a searching and browsing tool is also introduced. Using this tool, user can query character-based semantic indexing. Experimental results are shown that our proposed method is able to assist user in consuming index time and providing a method for automatic indexing, searching and browsing based on semantic queries.
Keywords: Video analysis, video indexing, character network, character-based analysis, social network, ontology
