대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

Borda count 방법을 이용한 다중 MPEG-7 서술자 조합에 관한 연구

A study on MPEG-7 descriptor combining method using borda count method

  • 엄민영 (연세대학교 전기전자공학과) ;
  • 최윤식 (연세대학교 전기전자공학과)
  • Eom, Min-Young (Dept. of Electrical and Electronic Engineering, Yonsei University) ;
  • Choe, Yoon-Sik (Dept. of Electrical and Electronic Engineering, Yonsei University)
  • 발행 : 2006.01.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 정지영상에 대해서 borda count 방법을 적용하여 MPEG-7 서술자기반 검색 결과 리스트의 조합에 대한 방법을 제한한다 대부분의 검색 엔진의 경우 MPEG극에서 정의하고 있는 서술자중 하나의 서술자만을 가지고 검색을 수행하고 있다. 이러한 경우 영상의 특성에 따라 검색 성능이 좋을 수도 있지만 그렇지 않을 수도 있다. 따라서 여러 가지 기술자들의 검색 결과를 조합하여 결과 리스트를 작성하는 방법이 요구되고 있다. 이에 따라 본 논문에서는 relevance feedback 알고리즘을 이용한 검색 시스템에 대하여, 여러 가지 서술자에 대한 검색 결과에 대한 결과 리스트를 borda count 방법을 이용하여 각각의 서술자에 의한 검색 결과를 조합하여 하나의 결과 리스트를 작성하는 방법을 제안한다.

In this paper, search result list synthesis method is proposed using borda count method for still image retrieval based on MPEG-7 descriptors. MPEG-7 standardizes descriptors that extract feature information from media data. In many cases, using a single descriptor lacks of correctness, it is suggested to use multiple descriptors to enhance retrieval efficiency. In this paper, retrieval efficiency enhancement is achieved by combining multiple search results which are from each descriptor. In combining search result, newly calculated borda count method is proposed. Comparing current frequency compensated calculation, rank considered frequency compensation is used to score animage in database. This combining method is considered in Content based image retrieval system with relevance feedback algorithm which uses high level information from system user. In each relevance iteration step, adoptive borda count method is used to calculate score of images.

키워드

참고문헌

  1. S. J. Yoon, D. K. Park, S. J. Park and C. S. Won, 'Image retrieval using a novel relevance feedback for edge histogram descriptor of MPEG-7,' ICCE International Conference on Consumer Electronics, June 2001, pp. 354-355 https://doi.org/10.1109/ICCE.2001.935342
  2. S. F. Chang, W. Chen, H. J. Meng, H. Sundaram and D. Zhong, 'A fully automated content-based video search engine supporting spatiotemporal queries,' IEEE Transactions on Circuits and Systems for Video Technology, Sept. 1998, vol. 8, pp. 602-615 https://doi.org/10.1109/76.718507
  3. Y. Rui, T. S. Huang and S. Mehrotra, 'Content-based image retrieval with relevance feedback in MARS,' International Conference on Image Processing, Oct. 1997, vol. 2, pp. 815-818 https://doi.org/10.1109/ICIP.1997.638621
  4. Text of ISO/IEC 15938-3/FDIS Information technology Multimedia content description interface-Part 3 Visual, 2002
  5. Information Technology Multimedia Content Description Interface-Part8: Extraction and use of MPEG7 descriptions, July, 2002
  6. B. S. Manjunath, P. Salembier and T. Sikora, 'Introduction to MPEG-7 Multimedia Content Description Interface,' Wiley, 2002
  7. D. R. Heisterkamp, J. Peng and H. K. Dai, 'Feature relevance learning with query shifting for content-based image retrieval,' International Conference on Pattern Recognition, Sept. 2000, vol. 4, pp. 250-253 https://doi.org/10.1109/ICPR.2000.902906
  8. R. Brunelli and O. Mich, 'Image retrieval by examples,' IEEE Transactions on Multimedia, Sept. 2000, vol. 2, pp. 164-171 https://doi.org/10.1109/6046.865481
  9. J. Assfalg, A. D. Bimbo and P. Pala, 'Image retrieval by positive and negative examples,' International Conference on Pattern Recognition, Sept. 2000, vol. 4, pp. 267-270 https://doi.org/10.1109/ICPR.2000.902910
  10. H. Muller, W. Muller, S. M. Marchand, T. Pun and D. M. Squire, 'Strategies for positive and negative relevance feedback in image retrieval,' International Conference on Pattern Recognition, Sept. 2000, vol. 1, pp. 1043-1046 https://doi.org/10.1109/ICPR.2000.905650
  11. S. Y. Jeong, K. H. Kim, B. T. Chun, J. Y. Lee and Y. L. Bae, 'An Effective Method For Combining Multiple Features Of Image Retrieval,' Proceedings of the IEEE Region 10 Conference, Sept. 1999, vol. 2, pp. 982-985 https://doi.org/10.1109/TENCON.1999.818585