Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지

Video Sequence Matching Using Normalized Dominant Singular Values

  • Jeong, Kwang-Min (Information Communication Subdivision, Kyungnam College University of Information & Technology) ;
  • Lee, Joon-Jae (Dept. of Game Mobile Contents, Keimyung Univ.)
  • Published : 2009.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a signature using dominant singular values for video sequence matching. By considering the input image as matrix A, a partition procedure is first performed to separate the matrix into non-overlapping sub-images of a fixed size. The SVD(Singular Value Decomposition) process decomposes matrix A into a singular value-singular vector factorization. As a result, singular values are obtained for each sub-image, then k dominant singular values which are sufficient to discriminate between different images and are robust to image size variation, are chosen and normalized as the signature for each block in an image frame for matching between the reference video clip and the query one. Experimental results show that the proposed video signature has a better performance than ordinal signature in ROC curve.

Keywords

References

  1. R. Mohan, "Video sequence matching," Proceedings of International Conference on Audio, Speech and Signal Processing, Vol.6, pp. 3697-3700, Jan. 1998.
  2. A. Hampapur and R. M. Bolle, "Comparison of distance measures for video copy detection," Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 22-25, Aug. 2001.
  3. A. K. Jain, A. Vailaya, and W. Xiong, "Query by video clip," Multimedia Systems, Vol.7, No.5, pp. 369-384, 1999. https://doi.org/10.1007/s005300050139
  4. M. Naphade, M. Yeung and B. Yeo, "A novel scheme for fast and efficient video sequence matching using compact signatures," Proceedings of SPIE Storage and Retrieval for Media Database 2000, Vol.3972, pp. 564-572, Jan. 2000.
  5. D. Bhat and S. Nayar, "Ordinal measures for image correspondence," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.20, Issue 4, pp. 415-423, Apr. 1998. https://doi.org/10.1109/34.677275
  6. A. Hampapur, K. H. Hyun and R. M. Bolle, "Comparison of Sequence Matching Techniques for Video Copy Detection.," Proceedings of SPIE, Storage and Retrieval for Media Database 2002, Vol.4676, pp. 194-201, Jan. 2002.
  7. C. I. Kim, "Content-based image copy detection," Signal Processing : Image Communication, Vol.18, No.3, pp. 169-184, Mar. 2003. https://doi.org/10.1016/S0923-5965(02)00130-3
  8. C. J. Lu and D. M. Tsai, "Defect inspection of patterned thin film transistor-liquid crystal display panels using a fast sub-image-based singular value decomposition," International Journal of Production Research, Vol.42, No.20, pp. 4331-4351, Oct. 2004. https://doi.org/10.1080/00207540410001716480
  9. K. M. Jeong, J. J. Lee, and Y. H. Ha , "Video Sequence Matching Using Singular Value Decomposition", ICIAR 2006, LNCS4141, pp. 426-435, Sept. 2006.
  10. J. Gu, L. Lu, R. Cai, H. J. Zhang, and J. Yang, "Dominant Feature Vectors Based Audio Similarity Measure", Proceedings of 5th Pacific Rim Conference on Multimedia 2004, LNCS 3332, pp. 890-897, Nov. 2004.