Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지

Robust Character Image Retrieval Method Using Bipartite Matching

Bipartite Matching을 이용한 강인한 캐릭터 영상 검색 방법

  • 이상엽 (삼육대학교 경영정보학과) ;
  • 김회율 (한양대학교 전자통신 전파공학과)
  • Published : 2002.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a novel approach that makes use of both shape and color information to retrieve character images in terms of similarity distance from a large-capacity image database or from a streaming image database, in particular, character image logo or trademark. In order to combine both features of completely different characteristics bipartite matching has been employed in computing similarity distance, The proposed method turned out to bealso very effective in matching natural object or human-drawn images whose shape varies substantially.

본 논문에서는 다양하게 변화되는 캐릭터 영상을 색상과 형태의 정보를 포함한 국부 색상 분포(local color histogram)를 이용하여 유사도 검색을 하는 강인한 방법을 제안한다. 국부 색상 분포의 값을 양자화 하여 특징 값을 최적화하고, 대규모 데이터베이스에 저장되어 있는 영상정보와 Bipartite matching을 이용하여 검색한다. 제안되는 방법은 다양하게 변화되는 영상의 유사도 검색, 동영상 및 정지 영상에서 유사 영상 검색에 매우 효과적인 방법이다.

Keywords

References

  1. Whoi-Yul Kim and C. Kak, '3-D Object Recognition Using Bipartite Matching Embedded in Discrete Relaxation,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 13, No. 3, pp. 224-251, Mar. 1991 https://doi.org/10.1109/34.75511
  2. Theo Gevers and Arnold W.M. Smeulders, 'PicToSeek: Combing Color and Shape Invariant Features for Image Retrieval,' IEEE Trans. Image Proc., Vol. 9, No. 1, pp. 102-119, Jan. 2000 https://doi.org/10.1109/83.817602
  3. Chiou-Shann Fuh, Shun-Wen Cho, and Kai Essig, 'Hierarchical Color Image Region Segmentation for Content-Based Image Retrieval System,' IEEE Trans. Image Proc., Vol. 9, No. 1, pp. 156-162, Jan. 2000 https://doi.org/10.1109/83.817608
  4. Nuno Vasconcelos and Andrew Lippman, “Featrue Representations for Image Retrieval: Beyond The Color Histogram," IEEE Int Conf. ICME 2000, Vol. 2, pp. 899-902, 2000
  5. Nicu Sebe and Michael S. Lew, 'Color Based Retrieval and Recognition,' IEEE Int. Conf. ICME, Vol. 1, pp. 311-314, 2000
  6. Timothy K. Shih, Ching-Sheng Wang, 'Indexing and Retrieval Schme of the Image Database Based on Color and Spatial Relations,' IEEE Int. Conf. ICME, Vol. 1, pp. 129-132, 2000
  7. Aleksandra Mojsilovic, 'A Method For Color Content Matching Of Images,' IEEE Int. Conf. ICME 2000, Vol. 2, pp. 899-902
  8. Rajiv Mehrotra, James E. Gary, 'Similar-Shape Retrieval In Shape Data Management,' Computer, vol. 28, pp 7-14, Sept. 1995
  9. Stan Sclaroff , Alex P. Pentland, 'Search by Shape Examples: Modeling Nonrigid Deformation,' Signals, Systems and Computers, Vol. 2, pp 1341-1344, 1994
  10. M.J. Swain and D.H. Ballard, 'Color indexing,' Int'l. j. Comput. Vision, Vol. 7(1), pp. 11-32, 1991
  11. Brian V. Funt and Graham D. Finlayson, 'Color Constant Color Indexing,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 17, No. 5, pp. 522-529, May. 1995 https://doi.org/10.1109/34.391390
  12. James Hafner and Harpreet S. Sawhney, 'Efficient Color Histogram Indexing for Quadratic Form Distance Functions,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 17, No. 7, pp. 729-736, Jul. 1995 https://doi.org/10.1109/34.391417
  13. Andrew D.J. Coross and Edwin R. Hancock, 'Graph Matching With a Dual-Step EM Algorithm,' IEEE Trans. Pattern Anal. Machine Intell., Vol. 20, No. 11, pp. 1236-1253, Nov. 1998 https://doi.org/10.1109/34.730557
  14. Dennis Shasha, Jason Tsong-Li Wang, Kaizhong Zhang and Frank Y. Shih, 'Exact and Approximate Algorithms for Unordered Tree Matching,' IEEE Trans. System, Man, and Cybernetics, Vol. 24, No. 4, pp. 668-678, Apr. 1994 https://doi.org/10.1109/21.286387
  15. M. Goldstein, N. Toomarian and J. Barhen, 'A Comparison Study of Optimization Methods for The Bipartite Matching Problem (BMP)', IEEE Int. Conf. Neural Networks, Vol. 2, pp 267-273, 1988
  16. Edith Cohen, 'Approximate max flow on small depth networks,' Foundations of computer Science, Proceedings, 33rd Annual Symposium on, pp. 648-658, 1992
  17. Kenneth P. Bogart, 'Introductory Combinatorics,' A Harcourt Science and Technology Company, pp 291-358, 2000
  18. Douglas B. West, 'Introduction to Graph Theory,' Prentice Hall, pp. 98-132,1996
  19. H. W. Huhn. 'The Hungarian method for the assignment problem,' Noval Research Logistics Quartely, pp. 83-97, 1955
  20. Pravin M. Vaidya, 'Geometry helps in matching,' Proceed. Twentieth Annual ACM Symposium on Theory of Computing, pp. 422-425, 1988
  21. 서창덕, 김회율, '영상 데이터 베이스에서의 의미 기반 유사 상표 검 색 및 새로운 검색 효율 평가 척도', 한국방송공학회 논문지, 제5권 제1호, pp. 68-81, 2000
  22. Yongsung Kim and Whoiyul Kim, 'A region-based descriptor using Zernike moments,' Signal Processing: Image Communication, Vol. 16 pp. 95-102 Sep. 2000
  23. Richard O. Duda, Peter E. Hart and Davie G. Stork, 'Pattern Classification Second Edition,' A Wiley-Interscience Publication, pp. 164-174 2001