Scene identification in news video by character region segmentation

ABSTRACT

Reflecting the demand for recycling and retrieval of video, we are proposing an automatic indexing system for news video that considers correspondences between textual indices and image contents. In this paper, we focus on the background image content (i.e. scene) identification portion of the system. The analysis is performed by segmenting (human) character region from background region, and was applied to actual news video for evaluation. The overall result showed the effectiveness of the proposed method by 7 to 8%, and indicated that character existence itself is an important feature. Individual observation among various scenes indicated that multiple features should be combinatorily used according to each scene, and that the data set should be exponentially extended for higher performance.

REFERENCES

• 1: Jing Huang , S. Ravi Kumar , Mandar Mitra , Wei-Jing Zhu , Ramin Zabih, Image Indexing Using Color Correlograms, Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97), p.762, June 17-19, 1997
• 2: Ichiro Ide , Koji Yamamoto , Hidehiko Tanaka, Automatic Video Indexing Based on Shot Classification, Proceedings of the First International Conference on Advanced Multimedia Content Processing, p.87-102, November 09-11, 1998
• 3: T. Kurita and T. Kato. Learning of personal visual impression for image database systems. In Proceedings of the Second International Conference on Document Analysis and Recognition, pages 547-552, 1993.
• 4: H. Mo, S. Satoh, and M. Sakauchi. A new type of video scene classification system based on typical model database. In Proceedings of the IAPR Workshop on Machine Video Applications, pages 329-332, November 1996.
• 5: Y. Mori, H. Takahashi, and R. Oka. Image understanding based on two database composed of images and words allocated in spaces. Proceedings of the Fourth Symposium on Intelligent Information Media (Tokyo, Japan), pages 127-132, December 1998. (in Japanese).
• 6: Yuichi Nakamura , Takeo Kanade, Semantic analysis for video contents extraction—spotting by association in news video, Proceedings of the fifth ACM international conference on Multimedia, p.393-401, November 09-13, 1997, Seattle, Washington, United States [doi>10.1145/266180.266391]
• 7: Henry A. Rowley , Shumeet Baluja , Takeo Kanade, Neural Network-Based Face Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.1, p.23-38, January 1998 [doi>10.1109/34.655647]
• 8: Shin'ichi Satoh , Yuichi Nakamura , Takeo Kanade, Name-It: Naming and Detecting Faces in News Videos, IEEE MultiMedia, v.6 n.1, p.22-35, January 1999 [doi>10.1109/93.752960]
• 9: Howard D. Wactlar , Alexander G. Hauptmann , Michael G. Christel , Ricky A. Houghton , Andreas M. Olligschlaeger, Complementary video and audio analysis for broadcast news archives, Communications of the ACM, v.43 n.2, p.42-47, Feb. 2000 [doi>10.1145/328236.328144]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Image databases
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Retrieval models

  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology
          Subjects: Feature evaluation and selection

General Terms:
Design, Experimentation, Management, Measurement, Performance, Theory