Advertisement

Neural Computing and Applications

, Volume 22, Issue 7–8, pp 1387–1396 | Cite as

Movie scenes detection with MIGSOM based on shots semi-supervised clustering

  • Thouraya Ayadi
  • Mehdi Ellouze
  • Tarek M. Hamdani
  • Adel M. Alimi
Original Article

Abstract

The segmentation into scenes helps users to browse movie archives and to select the interesting ones. In a given movie, we have two kinds of scenes: action scenes and non-action scenes. To detect action scenes, we rely on tempo features as motion and audio energy. However, to detect non-action scenes, we have to use the content information. In this paper, we present a new approach to detect non-action movie scenes. The main idea is the use of a new dynamic variant of the self-organizing maps called MIGSOM (Multilevel Interior Growing self-organizing maps) to detect agglomerations of shots in movie scenes. The originality of MIGSOM model lies in its architecture for evolving the structure of the network. The MIGSOM algorithm is generated by a growth process by adding nodes where it is necessary, whether from the boundaries or the interior of the map. In addition, the advantage of the proposed MIGSOM algorithm is their ability to find the best structure of the output space through the training process and to represent better the semantics of the data. Our system is tested on a varied database and compared to the classical SOM and others works. The obtained results show the merit of our approach in term of recall and precision rates and that our assumptions are well founded.

Keywords

Unsupervised learning Multilevel interior growing self-organizing map Movie scenes detection Video browsing 

Notes

Acknowledgments

The authors would like to acknowledge the financial support of this work by grants from General Direction of Scientific Research (DGRST), Tunisia, under the ARUB program.

References

  1. 1.
    Alahakoon D, Halgamuge SK, Srinivasan B (2000) Dynamic self-organizing maps with controlled growth for knowledge discovery. IEEE Trans Neural Netw 11:601–614CrossRefGoogle Scholar
  2. 2.
    Amarasiri R, Alahakoon D, Smith KA (2004) HDGSOM: a modified growing self-organizing map for high dimensional data clustering. In: Fourth international conference on hybrid intelligent systems, pp 216–221Google Scholar
  3. 3.
    Ayadi T, Hamdani TM, Alimi AM (2010) A new data topology matching technique with multilevel interior growing self-organizing maps. In: IEEE international conference on systems, man, and cybernetics, pp 2479–2486Google Scholar
  4. 4.
    Ayadi T, Hamdani TM, Alimi MA (2011) On the use of cluster validity for evaluation of migsom clustering. In: ISCIII: 5th international symposium on computational intelligence and intelligent informatics, pp 121–126Google Scholar
  5. 5.
    Ayadi T, Hamdani TM, Alimi MA, Khabou MA (2007) 2IBGSOM: interior and irregular boundaries growing self-organizing maps. In: IEEE sixth international conference on machine learning and applications, pp 397–392Google Scholar
  6. 6.
    Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New YorkzbMATHCrossRefGoogle Scholar
  7. 7.
    Blackmore J, Miikkulainen R (1993) Incremental grid growing: encoding high-dimensional structure into a two-dimensional feature map. In: IEEE (ed) ICNN: Proceedings of the international conference on neural networks, New York, 1, pp 450–455Google Scholar
  8. 8.
    Brunelli R, Mich O, Modena CM (1999) A survey on the automatic indexing of video data. J Visual Commun Image Represent 10:78–112CrossRefGoogle Scholar
  9. 9.
    Chen LH, Lai YC, Liao HYM (2008) Movie scene segmentation using background information. Pattern Recognit 41:1056–1065zbMATHCrossRefGoogle Scholar
  10. 10.
    Deboeck GJ, Kohonen T (1998) Visual explorations in finance: with self-organising maps. Springer, BerlinGoogle Scholar
  11. 11.
    Dittenbach M, Merkl D, Rauber A (2000) The growing hierarchical self-organizing map. In: Proceeding of IJCNN-00, 11th international joint conference on neural networks, IEEE Computer Society, Como, Italy, vol 6, pp 15–19Google Scholar
  12. 12.
    Ellouze M, Boujemaa N, Alimi MA (2009) Scene pathfinder: unsupervised clustering techniques for movie scenes extraction. Multimedia Tools Appl 47:325–346CrossRefGoogle Scholar
  13. 13.
    Ellouze M, Boujemaa N, Alimi MA (2010) Interactive movie summarization system. J Visual Commun Image Represent 21:283–294CrossRefGoogle Scholar
  14. 14.
    Ellouze M, Karray H, Alimi M, Regim A (2008) Research group on intelligent machines, tunisia, at Trecvid 2008, BBC rushes summarization. In: Proceedings of international conference ACM multimedia, TRECVID BBC rushes summarization workshopGoogle Scholar
  15. 15.
    Ellouze M, Karray H, Alimi MA (2007) Genetic algorithm for summarizing news stories. In: The 2nd international conference on computer vision theory and applications, pp 303–308Google Scholar
  16. 16.
    Freeman RT, Yin H (2004) Adaptive topological tree structure for document organization and visualization. Neural Netw 17:1255–1271zbMATHCrossRefGoogle Scholar
  17. 17.
    Fritzke B (1994) Growing cell structures a self-organizing network for unsupervised and supervised learning. Neural Netw 7:1441–1460CrossRefGoogle Scholar
  18. 18.
    Fritzke B (1995) Growing grid-a self-organizing network with constant neighborhood range and adaption strength. Neural Process Lett 2:1–5CrossRefGoogle Scholar
  19. 19.
    Hamdani TM, Alimi MA, Karray F (2008) Enhancing the structure and parameters of the centers for BBF fuzzy neural network classifier construction based on data structure. In: IEEE international join conference on neural networks, pp 3174–3180Google Scholar
  20. 20.
    Hamdani TM, Alimi AM, Khabou MA (2011) An iterative method for deciding SVM and single layer neural network structures. Neural Process Lett 33:171–186CrossRefGoogle Scholar
  21. 21.
    Hamdani TM, Khabou MA, Alimi AM (2010) Conflict negotiation process with stress parameters control for new classifier decision fusion scheme. In: International conference IP, comp vision and pattern recognition, IPCV, pp 784–787Google Scholar
  22. 22.
    Hanjalic A, Lagendijk RL, Biemond J (1999) Automated high-level movie segmentation for advanced video-retrieval systems. IEEE Trans Circuits Syst Video Technol 9:580–588CrossRefGoogle Scholar
  23. 23.
    Hodge VJ, Austin J (2001) Hierarchical growing cell structures: treegcs. IEEE Trans Knowl Data Eng 13:207–218CrossRefGoogle Scholar
  24. 24.
    Huang J, Liu Z, Wang Y (1998) Integration of audio and visual information for content-based video segmentation. In: Proceedings of IEEE international conference on image processing, pp 526–529Google Scholar
  25. 25.
    Hua KA, Oh J, Liang N (2000) A content-based scene change detection and classification technique using background tracking. In: Proc of conf on multimedia computing and networking, pp 254–265Google Scholar
  26. 26.
    Kohonen T (1982) Self organized formation of topological correct feature maps. Biol Cybern 43:59–69MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    Kohonen T (1984) Self-organization and associative memory. Springer, BerlinzbMATHGoogle Scholar
  28. 28.
    Kohonen T (1988) Statistical pattern recognition with neural networks: benchmark studies. In: Proceedings of the second annual IEEE international conference on neural networks, vol 1Google Scholar
  29. 29.
    Kohonen T (2001) Self-organization map. 3rd edn. Springer, BerlinCrossRefGoogle Scholar
  30. 30.
    Lebbah M, Benabdeslem K (2010) Visualization and clustering of categorical data with probabilistic self-organizing map. Neural Comput Appl 19(3):393–404CrossRefGoogle Scholar
  31. 31.
    Lin T, Zhang HJ (2000) Automatic video scene extraction by shot grouping. Proc Int Conf Pattern Recognit 6:39–42MathSciNetGoogle Scholar
  32. 32.
    Malone J, McGarry K, Wermter S, Bowerman C (2006) Data mining using rule extraction from Kohonen self-organising maps. Neural Comput Appl 15:9–17CrossRefGoogle Scholar
  33. 33.
    Rasheed Z, Shah M (2005) Detection and representation of scenes in videos. IEEE Trans Multimedia 7:1097–1105CrossRefGoogle Scholar
  34. 34.
    Sundaram H, Chang SF (2000) Video scene segmentation using video and audio features. In: Proceedings of the international conference on multimedia and expo, pp 1145–1148Google Scholar
  35. 35.
    Tavanapong W, Zhou J (2004) Shot clustering techniques for story browsing. IEEE Trans Multimedia 6:517–527CrossRefGoogle Scholar
  36. 36.
    Truong BT, Dorai C, Venkatesh S (2003) Automatic scene extraction in motion pictures. IEEE Trans Circuits Syst Video Technol 1:5–10CrossRefGoogle Scholar
  37. 37.
    Wali A, Ben Aoun N, Karray H, Ben Amar C, Alimi MA (2010) A new system for event detection from video surveillance sequences. ACIVS 2:110–120Google Scholar
  38. 38.
    Yeung M, Yeo BL, Liu B (1998) Segmentation of video by clustering and graph analysis. Comput Vision Image Underst 71:94–109CrossRefGoogle Scholar
  39. 39.
    Yu Y, Alahakoon D (2006) Batch implementation of growing self-organizing map. In: International conference on computational intelligence for modelling control and automation, and international conference on intelligent agents, web technologies and internet commerceGoogle Scholar
  40. 40.
    Zhao LQ, Yang S, Feng B (2001) Video scene detection using slide windows method based on temporal constrain shot similarity. In: Proceedings of international conference on multimedia and expo, pp 1171–1174Google Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  • Thouraya Ayadi
    • 1
  • Mehdi Ellouze
    • 1
  • Tarek M. Hamdani
    • 1
  • Adel M. Alimi
    • 1
  1. 1.REGIM, Research Group on Intelligent MachinesNational Engineering School of Sfax (ENIS), University of SfaxSfaxTunisia

Personalised recommendations