Video Key Frame Extraction through Canonical Correlation Analysis and Graph Modularity

  • Rameswar Panda
  • Sanjay K. Kuanar
  • Ananda S. Chowdhury
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


Key frame based video summarization has emerged as an important area of multimedia research in recent times. In this paper, we propose a novel automated approach for video key frame extraction in compressed domain using canonical correlation analysis (CCA) and graph modularity. We prune certain edges from the Video Similarity Graph (VSG) using an iterative strategy until there is no improvement in graph modularity. Resulting connected components in the final VSG correspond to separate clusters. The proposed algorithm also uses multi-feature fusion using canonical correlation analysis to achieve higher semantic dependency between different video frames. Experimental results on some standard videos of different genre clearly indicate the superiority of the proposed method in terms of the F 1 measure.


Key frames Video Summarization Canonical Correlation Analysis Graph modularity 


  1. 1.
    Ejaz, N., Mehmood, I., Baik, S.W.: Efficient visual attention based framework for extracting key frames from videos. Signal Processing: Image Communication 28, 34–44 (2013)Google Scholar
  2. 2.
    Cong, Y., Yuan, J., Luo, J.: Towards Scalable Summarization of Consumer Videos Via Sparse Dictionary Selection. IEEE Transactions on Multimedia 14, 66–75 (2012)CrossRefGoogle Scholar
  3. 3.
    Ejaz, N., Tariq, T.B., Baik, S.W.: Adaptive key frame extraction for video summarization using an aggregation mechanism. J. Visual Communication and Image Representation 23, 1031–1040 (2012)CrossRefGoogle Scholar
  4. 4.
    Chowdhury, A.S., Kuanar, S.K., Panda, R., Das, M.N.: Video Storyboard Design using Delaunay Graphs. In: 21st IEEE International Conference on Pattern Recognition, pp. 3108–3111 (2012)Google Scholar
  5. 5.
    Avila, S.E.F., Lopes, A.P.B., Luz Jr., A., Araujo, A.A.: VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recognition Letters 32, 56–68 (2011)CrossRefGoogle Scholar
  6. 6.
    Almeida, J., Leite, N.J., Torres, R.S.: VISON: Video Summarization for Online applications. Pattern Recognition Letters 33, 397–409 (2012)CrossRefGoogle Scholar
  7. 7.
    Sun, Q.S., Zeng, S.G., Liu, Y., Heng, P.A., Xia, D.S.: A new method of feature fusion and its application in image recognition. Pattern Recognition Letters 38, 2437–2448 (2005)CrossRefGoogle Scholar
  8. 8.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transaction on Pattern Analysis and Machine Intelligence 22, 888–905 (2000)CrossRefGoogle Scholar
  9. 9.
    Ciocca, G., Schettini, R.: A innovative algorithm for key frame extraction in video summarization. J. of Real-time Image Processing 1, 69–88 (2006)CrossRefGoogle Scholar
  10. 10.
    Panda, R., Kuanar, S.K., Chowdhury, A.S.: VISUC: Video Summarization With User Customization. In: IEEE International Conference on Communications, Devices and Intelligent Systems, pp. 89–92 (2012)Google Scholar
  11. 11.
    Schaeffer, S.E.: Graph clustering. Computer Science Review 1, 27–64 (2007)CrossRefGoogle Scholar
  12. 12.
    The Open Video Project,
  13. 13.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Rameswar Panda
    • 1
  • Sanjay K. Kuanar
    • 1
  • Ananda S. Chowdhury
    • 1
  1. 1.Department of Electronics and Telecommunication EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations