Multimedia Tools and Applications

, Volume 78, Issue 2, pp 1441–1456 | Cite as

From local to global key-frame extraction based on important scenes using SVD of centrist features

  • Youssef BendraouEmail author
  • Fedwa Essannouni
  • Ahmed Salam


The wide spread of multimedia applications and the rapid growth of digital video data require efficient video summarization methods. Extracting brief and pertinent information allows users to quickly browse, recognize and understand a large amount of video content. In this paper, a video summarization method based on important scenes is proposed. A local selection of potential candidate key-frames (PCK) is first performed using only one iteration of the k-means algorithm, where its initialization is achieved using a dictionary selection. Scores of importance are calculated for each PCK to accomplish the global selection. While some approaches remove redundant key-frames to share unique information, this can be used to classify scenes by duration and temporal position. Following such classification, the scene with the longest duration can be considered as the most important one. Therefore, rules of insertion are defined to allow redundancy when the information is considered important. In our contribution, to represent a frame, the singular value decomposition (SVD) of centrist are used as features. The SVD of Centrist allows to better measure the similarity between adjacent frames than other features, and thus to enhance the performance. Experimental results over two different databases show the diversity of our summary and the effectiveness of our method compared to related state of the art methods.


Static video summary Key-frame extraction Singular value decomposition Centrist features 



  1. 1.
    Avila SF, Lopes AP, Luz A, Araujo AA (2011) Vsumm: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recogn Lett 32(1):56–68CrossRefGoogle Scholar
  2. 2.
    Chang IC, Cheng KY (2007) Content-selection based video summarization. In: IEEE international conference on consumer electronics. Las Vegas, pp 11–14Google Scholar
  3. 3.
    Chang HS, Sull S, Lee SU (1999) Efficient video indexing scheme for content based retrieval. IEEE Trans Circ Syst Vid Technol 9(8):1269–1279CrossRefGoogle Scholar
  4. 4.
    Ciocca G, Schettini R (2006) An innovative algorithm for keyframe extraction in video summarization. J Real-Time Image Proc 1(1):69–88CrossRefGoogle Scholar
  5. 5.
    Cong Y, Yuan J, Liu J (2011) Sparse reconstrction cost for abnormal event detection. In: Proceeding of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3449–3456Google Scholar
  6. 6.
    Cong Y, Yuan J, Luo J (2012) Towards scalable summarization of consumer videos via sparse dictionary selection. IEEE Trans Multimed 14(1):66–75CrossRefGoogle Scholar
  7. 7.
    Doulamis AD, Doulamis ND, Kollias SD (2000) A fuzzy video content representation for video summarization and content-based retrieval. Signal Process 80 (6):1049–1067CrossRefGoogle Scholar
  8. 8.
    Furini M, Geraci F, Montangero M, Pellegrini M (2010) Stimo: still and moving video storyboard for the web scenario. Multimed Tools Appl 46(1):47–69CrossRefGoogle Scholar
  9. 9.
    Gong Y, Liu X (2000) Video summarization using singular value decomposition. In: IEEE conference on computer vision and pattern recognition, vol 2, pp 174–180Google Scholar
  10. 10.
    Hadi Y, Essannouni F, Thami RO (2006) Video summarization by k-medoid clustering. in: Proceedings of the 2006 ACM symposium on applied computing (SAC). Dijon, pp 1400–1401Google Scholar
  11. 11.
    Hanjalic A, Zhang HJ (1999) An integrated scheme for automated video abstraction based on unsupervised cluster validity analysis. IEEE Trans Circ Syst Vid Technol 9(8):1280–1289CrossRefGoogle Scholar
  12. 12.
    Huang C, Liao B (2001) A robust scene-change detection method for video segmentation. IEEE Trans Circ Syst Vid Technol 11:12Google Scholar
  13. 13.
    Jain AK (2010) Data clustering: 50 years beyond K-means. Pattern Recogn Lett 31(8):651–666CrossRefGoogle Scholar
  14. 14.
    Jianxin W, James MR (2011) CENTRIST: a visual descriptor for scene categorization. IEEE Trans Pattern Anal Mach Intell 33:8CrossRefGoogle Scholar
  15. 15.
    Ju J, Song T, Ku B, Ko H (2016) Key frame extraction based on chaos theory and color information for video summarization. IEICE Trans Inf Syst 99(6):1698–1701CrossRefGoogle Scholar
  16. 16.
    Liu T, Zhang HJ, Qi F (2003) A novel video key-frame extraction algorithm based on percived motion energy model. IEEE Trans Circ Syst Video Technol 13:10Google Scholar
  17. 17.
    Luo J, Papin C, Costello K (2009) Towards extracting semantically meaningful key frames from personal video clips: from humans to computers. IEEE Trans Circ Syst Vid Technol 19:289–301CrossRefGoogle Scholar
  18. 18.
    Ma M, Mei S, Wan S, Hou J, Wang Z, Feng D (2017) Exploring the influence of feature representation for dictionary selection based video summarization. In: IEEE international conference on image processing (ICIP). BeijingGoogle Scholar
  19. 19.
    Ma M, Mei S, Wan S, Hou J, Wang Z, Feng D (2017) Video summarization via simultaneous block sparse representation. In: International conference on digital image computing: techniques and applications (ICTA) 2017. SydneyGoogle Scholar
  20. 20.
    Marchionini G, Geisler G (2002) The open video digital library. D-Lib Mag 8(12):1082–9873Google Scholar
  21. 21.
    Meia S, Guanb G, Wangb Z, Wana S, Hea M, Fengb DD (2015) Video summarization via minimum sparse reconstruction. Pattern Recogn 48(2):522–533CrossRefGoogle Scholar
  22. 22.
    Money A, Agius H (2008) Video summarisation: a conceptual framework and survey of the state of the art. J Vis Commun Image Represent 19:121–143CrossRefGoogle Scholar
  23. 23.
    Mundur P, Rao Y, Yesha Y (2006) Keyframe-based video summarization using Delaunay clustering. Int J Digit Libr 6(2):219–232CrossRefGoogle Scholar
  24. 24.
    Nagasaka YTA (1991) Automatic video indexing and full-video search for object appearances. In: Working conference vision on database system, pp 119–133Google Scholar
  25. 25.
    Ngo C, Ma Y, Zhang H (2005) Video summarization and scene detection by graph modeling. IEEE Trans Circ Syst Vid Technol 15(2):296–305CrossRefGoogle Scholar
  26. 26.
    Open Video Project,
  27. 27.
    Panagiotakis C, Doulamis A, Tziritas G (2009) Equivalent key frames selection based on iso-content principles. IEEE Trans Circ Syst Vid Technol 19(3):447–451CrossRefGoogle Scholar
  28. 28.
    Panda R, Das A, Roy-Chowdhury AK (2016) Embedded sparse coding for summarizing multi-view videos. In: 2016 IEEE international conference on image processing (ICIP), pp 191–195Google Scholar
  29. 29.
    Parry ML, Legg PA, Chung DH, Grifths IW, Chen M (2011) Hierarchical event selection for video storyboards with a case study on snooker video visualization. IEEE Trans Vis Comput Graph 17(12):1747–1756CrossRefGoogle Scholar
  30. 30.
    Shahraray B, Gibbon DC (1995) Automatic generation of pictorial tanscripts of video programs. In: Proc. SPIE, vol 2417, pp 512–518Google Scholar
  31. 31.
    Tavassolipour M, Karimian M, Kasaei S (2014) Event detection and summarization in soccer videos using bayesian network and copula. IEEE Trans Circ Syst Vid Technol 24(2):291–304CrossRefGoogle Scholar
  32. 32.
    Truong BT, Venkatesh S (2007) Video abstraction: a systematic review and classification. ACM Trans Multimed Comput Commun Appl 3(1):1–37CrossRefGoogle Scholar
  33. 33.
    Yeung MM, Liu B (1995) Efficient matching and clusering of video shots. In: IEEE international conference on image processing (ICIP), vol 1, pp 338–341Google Scholar
  34. 34.
    Zhang HJ, Kankanhalli A, Smoliar S (1993) Automatic partitioning of full-motion video. ACM Multimed Syst 1(1):10–28CrossRefGoogle Scholar
  35. 35.
    Zhang HJ, Wu J, Zhong D, Smoliar SW (1997) An integrated system for content-based video retrieval and borwsing. Pattern Recogn 30(4):643–658CrossRefGoogle Scholar
  36. 36.
    Zhuang Y, Rui Y, Huang TS, Mehrotra S (1998) Adaptive key frame extraction using unsupervised clustering. In: Proceedings of international conference on image processing, vol 1, pp 866–870Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Youssef Bendraou
    • 1
    • 2
    Email author
  • Fedwa Essannouni
    • 2
  • Ahmed Salam
    • 1
  1. 1.LMPA LaboratoryUniversity Littoral Cote Opale (ULCO)CalaisFrance
  2. 2.Faculty of Sciences, LRIT LaboratoryUniversity Mohammed VRabatMorocco

Personalised recommendations