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.
Similar content being viewed by others
References
Alahakoon D, Halgamuge SK, Srinivasan B (2000) Dynamic self-organizing maps with controlled growth for knowledge discovery. IEEE Trans Neural Netw 11:601–614
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 216–221
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 2479–2486
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 121–126
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 397–392
Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New York
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 450–455
Brunelli R, Mich O, Modena CM (1999) A survey on the automatic indexing of video data. J Visual Commun Image Represent 10:78–112
Chen LH, Lai YC, Liao HYM (2008) Movie scene segmentation using background information. Pattern Recognit 41:1056–1065
Deboeck GJ, Kohonen T (1998) Visual explorations in finance: with self-organising maps. Springer, Berlin
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 15–19
Ellouze M, Boujemaa N, Alimi MA (2009) Scene pathfinder: unsupervised clustering techniques for movie scenes extraction. Multimedia Tools Appl 47:325–346
Ellouze M, Boujemaa N, Alimi MA (2010) Interactive movie summarization system. J Visual Commun Image Represent 21:283–294
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 workshop
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 303–308
Freeman RT, Yin H (2004) Adaptive topological tree structure for document organization and visualization. Neural Netw 17:1255–1271
Fritzke B (1994) Growing cell structures a self-organizing network for unsupervised and supervised learning. Neural Netw 7:1441–1460
Fritzke B (1995) Growing grid-a self-organizing network with constant neighborhood range and adaption strength. Neural Process Lett 2:1–5
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 3174–3180
Hamdani TM, Alimi AM, Khabou MA (2011) An iterative method for deciding SVM and single layer neural network structures. Neural Process Lett 33:171–186
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 784–787
Hanjalic A, Lagendijk RL, Biemond J (1999) Automated high-level movie segmentation for advanced video-retrieval systems. IEEE Trans Circuits Syst Video Technol 9:580–588
Hodge VJ, Austin J (2001) Hierarchical growing cell structures: treegcs. IEEE Trans Knowl Data Eng 13:207–218
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 526–529
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 254–265
Kohonen T (1982) Self organized formation of topological correct feature maps. Biol Cybern 43:59–69
Kohonen T (1984) Self-organization and associative memory. Springer, Berlin
Kohonen T (1988) Statistical pattern recognition with neural networks: benchmark studies. In: Proceedings of the second annual IEEE international conference on neural networks, vol 1
Kohonen T (2001) Self-organization map. 3rd edn. Springer, Berlin
Lebbah M, Benabdeslem K (2010) Visualization and clustering of categorical data with probabilistic self-organizing map. Neural Comput Appl 19(3):393–404
Lin T, Zhang HJ (2000) Automatic video scene extraction by shot grouping. Proc Int Conf Pattern Recognit 6:39–42
Malone J, McGarry K, Wermter S, Bowerman C (2006) Data mining using rule extraction from Kohonen self-organising maps. Neural Comput Appl 15:9–17
Rasheed Z, Shah M (2005) Detection and representation of scenes in videos. IEEE Trans Multimedia 7:1097–1105
Sundaram H, Chang SF (2000) Video scene segmentation using video and audio features. In: Proceedings of the international conference on multimedia and expo, pp 1145–1148
Tavanapong W, Zhou J (2004) Shot clustering techniques for story browsing. IEEE Trans Multimedia 6:517–527
Truong BT, Dorai C, Venkatesh S (2003) Automatic scene extraction in motion pictures. IEEE Trans Circuits Syst Video Technol 1:5–10
Wali A, Ben Aoun N, Karray H, Ben Amar C, Alimi MA (2010) A new system for event detection from video surveillance sequences. ACIVS 2:110–120
Yeung M, Yeo BL, Liu B (1998) Segmentation of video by clustering and graph analysis. Comput Vision Image Underst 71:94–109
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 commerce
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 1171–1174
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.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ayadi, T., Ellouze, M., Hamdani, T.M. et al. Movie scenes detection with MIGSOM based on shots semi-supervised clustering. Neural Comput & Applic 22, 1387–1396 (2013). https://doi.org/10.1007/s00521-012-0930-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-0930-5