Journal of Real-Time Image Processing

, Volume 1, Issue 1, pp 69–88 | Cite as

An innovative algorithm for key frame extraction in video summarization

  • Ciocca GianluigiEmail author
  • Schettini Raimondo
Original Research Paper


Video summarization, aimed at reducing the amount of data that must be examined in order to retrieve the information desired from information in a video, is an essential task in video analysis and indexing applications. We propose an innovative approach for the selection of representative (key) frames of a video sequence for video summarization. By analyzing the differences between two consecutive frames of a video sequence, the algorithm determines the complexity of the sequence in terms of changes in the visual content expressed by different frame descriptors. The algorithm, which escapes the complexity of existing methods based, for example, on clustering or optimization strategies, dynamically and rapidly selects a variable number of key frames within each sequence. The key frames are extracted by detecting curvature points within the curve of the cumulative frame differences. Another advantage is that it can extract the key frames on the fly: curvature points can be determined while computing the frame differences and the key frames can be extracted as soon as a second high curvature point has been detected. We compare the performance of this algorithm with that of other key frame extraction algorithms based on different approaches. The summaries obtained have been objectively evaluated by three quality measures: the Fidelity measure, the Shot Reconstruction Degree measure and the Compression Ratio measure.


Video summarization Visual summary evaluation Dynamic key frames extraction Frame content description 



The video indexing and analysis presented here was supported by the Italian MURST FIRB Project MAIS (Multi-channel Adaptive Information Systems) [40] and by the Regione Lombardia (Italy) within the INTERNUM project aimed at facilitating access to the cultural video documentaries of the AESS (Archivio di Etnografia e Storia Sociale).


  1. 1.
    Agraim, P., Zhang, H., Petkovic, D.: Content-based representation and retrieval of visual media: a state of the art review. Multimed. Tools Appl. 3, 179–202 (1996)CrossRefGoogle Scholar
  2. 2.
    Dimitrova, N., Zhang, H., Shahraray, B., Sezan, M., Huang, T., Zakhor, A.: Applications of video-content analysis and retrieval. IEEE MultiMed. 9(3), 44–55 (2002)CrossRefGoogle Scholar
  3. 3.
    Antani, S., Kasturi, R., Jain, R.: A survey on the use of pattern recognition methods for abstraction, indexing and retrieval of images and video. Pattern Recognit. 35, 945–965 (2002)zbMATHCrossRefGoogle Scholar
  4. 4.
    Schettini, R., Brambilla, C., Cusano, C., Ciocca, G.: Automatic classification of digital photographs based on decision forests. Int. J. Pattern Recognit. Artif. Intell. 18(5), 819–846 (2004)CrossRefGoogle Scholar
  5. 5.
    Fredembach, C., Schröder, M., Süsstrunk, S.: Eigenregions for image classification. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 26(12), 1645–1649 (2004)CrossRefGoogle Scholar
  6. 6.
    Hauptmann, A.G., Jin, R., Tobun, D.N.: Video retrieval using speech and image information. In: Proceedings of Electronic Imaging Conference (EI’03), Storage Retrieval for Multimedia Databases, Santa Clara, CA, USA, vol. 5021, pp. 148–159 (2003)Google Scholar
  7. 7.
    Tonomura, Y., Akutsu, A., Otsugi, K., Sadakata, T.: VideoMAP and VideoSpaceIcon: tools for automatizing video content. In: Proceedings of ACM INTERCHI ’93 Conference, pp. 131–141 (1993)Google Scholar
  8. 8.
    Ueda, H., Miyatake, T., Yoshizawa, S.: IMPACT: an interactive natural-motion-picture dedicated multimedia authoring system. In: Proceedings of ACM CHI ’91 Conference, pp. 343–350 (1991)Google Scholar
  9. 9.
    Rui, Y., Huang, T.S., Mehrotra, S.: Exploring video structure beyond the shots. In: Proceedings of IEEE International Conference on Multimedia Computing and Systems (ICMCS), Texas, USA, pp. 237–240 (1998)Google Scholar
  10. 10.
    Pentland, A., Picard, R., Davenport, G., Haase, K.: Video and image semantics: advanced tools for telecommunications. IEEE MultiMed. 1(2), 73–75 (1994)Google Scholar
  11. 11.
    Sun, Z., Ping, F.: Combination of color and object outline based method in video segmentation. Proc. SPIE Storage Retr. Methods Appl. Multimed. 5307, 61–69 (2004)Google Scholar
  12. 12.
    Arman, F., Hsu, A., Chiu, M.Y.: Image processing on compressed data for large video databases. In: Proceedings of ACM Multimedia ’93, Annaheim, CA, USA, pp. 267–272 (1993)Google Scholar
  13. 13.
    Zhuang, Y., Rui, Y., Huang, T.S., Mehrotra, S.: Key frame extraction using unsupervised clustering. In: Proceedings of ICIP’98, Chicago, USA, vol. 1, pp. 866–870 (1998)Google Scholar
  14. 14.
    Girgensohn, A., Boreczky, J.: Time-constrained keyframe selection technique. Multimed. Tools Appl. 11, 347–358 (2000)zbMATHCrossRefGoogle Scholar
  15. 15.
    Gong, Y., Liu, X.: Generating optimal video summaries. In: Proceedings of IEEE International Conference on Multimedia and Expo, vol. 3, pp. 1559–1562 (2000)Google Scholar
  16. 16.
    Zhao, L., Qi, W., Li, S.Z., Yang, S.Q., Zhang, H.J.: Key-frame extraction and shot retrieval using nearest feature line (NFL). In: Proceedings of ACM International Workshops on Multimedia Information Retrieval, pp. 217–220 (2000)Google Scholar
  17. 17.
    Hanjalic, A., Lagendijk, R.L., Biemond, J.: A new method for key frame based video content representation. In: Image Databases and Multimedia Search. World Scientific, Singapore (1998)Google Scholar
  18. 18.
    Hoon, S.H., Yoon, K., Kweon, I.: A new technique for shot detection and key frames selection in histogram space. In: Proceedings of the 12th Workshop on Image Processing and Image Understanding, pp. 475–479 (2000)Google Scholar
  19. 19.
    Narasimha, R., Savakis, A., Rao, R.M., De Queiroz, R.: A neural network approach to key frame extraction. In: Proceedings of SPIE-IS & T Electronic Imaging Storage and Retrieval Methods and Applications for Multimedia, vol. 5307, pp. 439–447 (2004)Google Scholar
  20. 20.
    Calic, J., Izquierdo, E.: Efficient key-frame extraction and video analysis. In: Proceedings of IEEE ITCC2002, Multimedia Web Retrieval Section, pp. 28–33 (2002)Google Scholar
  21. 21.
    Liu Tianming, M., Zhang, H.J., Qi, F.H.: A novel video key-frame-extraction algorithm based on perceived motion energy model. IEEE Trans. Circuits Syst. Video Technol. 13(10), 1006–1013 (2003)CrossRefGoogle Scholar
  22. 22.
    Zhang, H.J., Wu, J., Zhong, D., Smoliar, S.W.: An integrated system for contentbased video retrieval and browsing. Pattern Recognit. 30(4), 643–658 (1997)CrossRefGoogle Scholar
  23. 23.
    Fayzullin, M., Subrahmanian, V.S., Picarello, A., Sapino, M.L.: The CPR model for summarizing video. In: Proceedings of the 1st ACM International Workshop on Multimedia Databases, New Orleans, LA, USA, pp. 2–9 (2002)Google Scholar
  24. 24.
    Lagendijk, R.L., Hanjalic, A., Ceccarelli, M.P., Soletic, M., Persoon, E.H.: Visual search in a SMASH system. In: Proceedings of ICIP’96, pp. 671–674 (1995)Google Scholar
  25. 25.
    Ngo, C.-W., Ma, Y.-F., Zhang, H.-J.: Video summarization and scene detection by graph modeling. IEEE Trans. Circuits Syst. Video Technol. 15(2), 196–305 (2005)Google Scholar
  26. 26.
    Chang, H.S., Sull, S., Lee, S.U.: Efficient Video Indexing Scheme for Content-Based Retrieval. IEEE Trans. Circuits Syst. Video Technol. 9(8), 1269–1279 (1999)CrossRefGoogle Scholar
  27. 27.
    Tieyan, L., Zhang, X., Feng, J., Lo, K.T.: Shot reconstruction degree: a novel criterion for key frame selection. Pattern Recognit. Lett. 25, 1451–1457 (2004)CrossRefGoogle Scholar
  28. 28.
    Fernando, A.C., Canaharajah, C.N., Bull, D.R.: Fade-in and fade-out detection in video sequences using histograms. In: Proceedings of ISCAS 2000—IEEE International Symposium on Circuits and System, vol. IV, pp. 709–712 (2000)Google Scholar
  29. 29.
    Swain, M., Ballard, D.: Color indexing. Int. J. Comput. Vis. 7(1), 11–32 (1991)CrossRefGoogle Scholar
  30. 30.
    Smith, J.R., Chang, S.F.: Tools and techniques for color image retrieval. In: IST/SPIE Storage and Retrieval for Image and Video Databases IV, vol. 2670, pp. 426–437 (1996)Google Scholar
  31. 31.
    Ciocca, G., Gagliardi, I., Schettini, R.: Quicklook2 : an integrated multimedia system. Int. J. Vis. Lang. Comput. 12, 81–103 (Special issue on querying multiple data sources) (2001)Google Scholar
  32. 32.
    Gonzalez, R., Woods, R.: Digital image processing. Addison Wesley, Reading, pp. 414–428 (1992)Google Scholar
  33. 33.
    Idris, F., Panchanathan, S.: Storage and retrieval of compressed images using wavelet vector quantization. J. Vis. Lang. Comput. 8, 289–301 (1997)CrossRefGoogle Scholar
  34. 34.
    Scheunders, P., Livens, S., Van de Wouwer, G., Vautrot, P., Van Dyck, D.: Wavelet-based texture analysis. Int. J. Comput. Sci. Inf. Manage. 1(2), 22–34 (1998)Google Scholar
  35. 35.
    Chetverikov, D., Szabo, Zs.: A simple and efficient algorithm for detection of high curvature points in planar curves. In: Proceedings of the 23rd Workshop of the Austrian Pattern Recognition Group, pp. 175–184 (1999)Google Scholar
  36. 36.
    Latecki, L., DeMenthon, D., Rosenfeld, A.: Extraction of key frames from videos by polygon simplification. In: International Symposium on Signal Processing and its Applications, pp. 643–646 (2001)Google Scholar
  37. 37.
    Lefevre, S., Holler, J., Vincent, N.: A review of real time segmentation of uncompressed video sequences for content-based search and retrieval. Real Time Imaging 9, 73–98 (2003)CrossRefGoogle Scholar
  38. 38.
    Daubechies, I., Sweldens, W.: Factoring wavelet transforms into lifting steps. J. Fourier Anal. Appl. 4(3), 247–269 (1998)MathSciNetzbMATHCrossRefGoogle Scholar
  39. 39.
  40. 40.
    MAIS Consortium, Mais: Multichannel Adaptive Information Systems.

Copyright information

© Springer-Verlag 2006

Authors and Affiliations

  1. 1.Dipartimento di Informatica Sistemistica e Comunicazione (DISCo)Università degli studi di Milano-BicoccaMilanoItaly

Personalised recommendations