Trademark matching and retrieval in sports video databases

ABSTRACT

In this paper we describe a system for detection and retrieval of trademarks appearing in sports videos. We propose a compact representation of trademarks and video frame content based on SIFT feature points. This representation can be used to robustly detect, localize, and retrieve trademarks as they appear in a variety of different sports video types. Classification of trademarks is performed by matching a set of SIFT feature descriptors for each trademark instance against the set of SIFT features detected in each frame of the video. Localization is performed through robust clustering of matched feature points in the video frame. Experimental results are provided, along with an analysis of the precision and recall. Results show that the our proposed technique is efficient and effectively detects and classifies trademarks.

REFERENCES

• 1: F. Aldershoff and T. Gevers. Visual tracking and localisation of billboards in streamed soccer matches. In SPIE Electronic Imaging, San Jose, CA, USA, 2004.
• 2: S. Belongie , J. Malik , J. Puzicha, Shape Matching and Object Recognition Using Shape Contexts, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.24 n.4, p.509-522, April 2002 [doi>10.1109/34.993558]
• 3: Cordelia Schmid , Roger Mohr, Local Grayvalue Invariants for Image Retrieval, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.5, p.530-535, May 1997 [doi>10.1109/34.589215]
• 4: R. J. M. Den Hollander and A. Hanjalic. Logo detection in video by string matching. In Proceedings of IEEE International Conference on Image Processing (ICIP), Barcelona, ES, 2003.
• 5: R. J. M. Den Hollander and A. Hanjalic. Logo recognition in video by line profile classification. In SPIE Electronic Imaging, San Jose, CA, USA, 2004.
• 6: J. P. Eakins, K. J. Riley, and J. D. Edwards. Shape Feature Matching for Trademark Image Retrieval. In Lecture Notes in Computer Science, volume 2728, pages 439--443, 2003.
• 7: T. Gevers and A. W. M. Smeulders. Color-based object recognition. Pattern Recognition, 32:453--464, 1999.
• 8: G. Kienast, H. Stiegler, W. Bailer, H. Rehatschek, S. Busemann, and T. Declerck. Sponsorship tracking using distributed multi-modal analysis (DIRECT-INFO). In The 2nd European Workshop on the Integration of Knowledge, Semantics and Digital Media Technology, 2005. EWIMT 2005., pages 341--348, 2005.
• 9: Yong-Sung Kim , Whoi-Yul Kim, Content-based trademark retrieval system using visually salient features, Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97), p.307, June 17-19, 1997
• 10: B. Kovar and A. Hanjalic. Logo appearance statistics in a sport video: Video indexing for sponsorship revenue control. In SPIE Electronic Imaging 2002: Storage and Retrieval for Media Databases, San Jose, CA, USA, 2002.
• 11: Y. Lamdan, J. T. Schwartz, and H. J. Wolfson. Object recognition by affine invariant matching. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 335--344, Ann Arbor, MI, USA, 1988.
• 12: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 13: F. Pelisson, D. Hall, O. Riff, and J. L. Crowley. Brand identification using gaussian derivative histograms. In Lecture Notes in Computer Science, volume 2623, pages 492--501, 2003.
• 14: Reinier H. van Leuken , M. Fatih Demirci , Victoria J. Hodge , Jim Austin , Remco C. Veltkamp, Layout indexing of trademark images, Proceedings of the 6th ACM international conference on Image and video retrieval, p.525-532, July 09-11, 2007, Amsterdam, The Netherlands [doi>10.1145/1282280.1282356]
• 15: Peng-Yeng Yin , Cheng-Chung Yeh, Content-based retrieval from trademark databases, Pattern Recognition Letters, v.23 n.1-3, p.113-126, January 2002 [doi>10.1016/S0167-8655(01)00091-5]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.7 Digital Libraries
          Subjects: Standards

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Image databases

General Terms:
Algorithms, Experimentation, Performance

Keywords:
multimedia, trademark matching, video retrieval