Skip to main content
SpringerLink
Log in

Parallel neural networks for multimodal video genre classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Improvements in digital technology have made possible the production and distribution of huge quantities of digital multimedia data. Tools for high-level multimedia documentation are becoming indispensable to efficiently access and retrieve desired content from such data. In this context, automatic genre classification provides a simple and effective solution to describe multimedia contents in a structured and well understandable way. We propose in this article a methodology for classifying the genre of television programmes. Features are extracted from four informative sources, which include visual-perceptual information (colour, texture and motion), structural information (shot length, shot distribution, shot rhythm, shot clusters duration and saturation), cognitive information (face properties, such as number, positions and dimensions) and aural information (transcribed text, sound characteristics). These features are used for training a parallel neural network system able to distinguish between seven video genres: football, cartoons, music, weather forecast, newscast, talk show and commercials. Experiments conducted on more than 100 h of audiovisual material confirm the effectiveness of the proposed method, which reaches a classification accuracy rate of 95%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Notes

  1. Consider, for example, the YouTube video site—http://www.youtube.com/ (last accessed: May 13th, 2008), which allows users to upload, watch and share multimedia video files.

  2. http://www.aber.ac.uk/media/Documents/intgenre/intgenre.html (last accessed: November 14th, 2007)

  3. Available online at: http://www-nlpir.nist.gov/projects/t2002v/t2002v.html (last accessed: September 14th, 2007).

  4. Richard Bellman coined the term “curse of dimensionality” to describe the difficulty of evaluating Probability Density Functions on high-dimensional feature spaces [2].

  5. Available online at: http://www.nlog-project.org (Last accessed: September 28th, 2007).

  6. See http://www.facedetection.com to find many available resources about the face detection task (last accessed: October 10th, 2007).

  7. Using the Fraunhofer IIS Real Time Face Detector tool, http://www.iis.fraunhofer.de (last accessed: March 28th, 2008).

  8. See Table 1 to recall the meaning of the acronyms for the programme surrogate features.

  9. See http://www.museum.tv/archives/etv/T/htmlT/talkshows/talkshows.htm for an introduction to the history of TV talk shows (Last accessed: September 27th, 2007).

  10. A demo version (valid for 60 days) of the RTFaceDetection library is available for download at: http://www.iis.fraunhofer.de/EN/bf/bv/kognitiv/biom/dd.jsp (last accessed: November 21st, 2007).

  11. http://www.itc.it/irst (last accessed: May 13th, 2008).

  12. http://leenissen.dk/fann (last accessed: May 13th, 2008).

References

  1. Albiol A, Fullá MJCh, Albiol A, Torres L (2004) Commercials detection using HMMs. In: International workshop on image analysis for multimedia interactive services. Lisboa, Portugal

  2. Bellman R (1961) Adaptive control processes: a guided tour. Princeton Univ. Press

  3. Blum DW (1992) Method and apparatus for identifying and eliminating specific material from video signals. US Patent no. 5151788

  4. Boggs J, Petrie DW (2006) The art of watching films with tutorial CD-ROM. McGraw-Hill

  5. Brugnara F, Cettolo M, Federico M, Giuliani D (2000) A system for the segmentation and transcription of italian radio news. In: RIAO, content-based multimedia information access. Paris, France

  6. Ćalić J (2004) Highly efficient low-level feature extraction for video representation and retrieval. PhD thesis, University of London

  7. Chellappa R, Wilson CL, Sirohey S (1995) Human and machine recognition of faces: a survey. Proc IEEE 83(5):705–740 (May)

    Article  Google Scholar 

  8. Cheng W, Liu C, Wang X (2006) A rough set approach to video genre classification. In: 8th international conference on advanced concepts for intelligent vision systems (ACIVS’06). Antwerp, Belgium, pp 1210–1220 (September)

  9. Covell M, Baluja S, Fink M (2006) Advertisement detection and replacement using acoustic and visual repetition. In: IEEE 8th workshop on multimedia signal processing (MMSP2006). Victoria, BC, pp 461–466 (October)

  10. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27

    Article  MATH  Google Scholar 

  11. Dimitrova N, Agnihotri L, Wei G (2000) Video classification based on HMM using text and faces. In: European conference on signal processing. Tampere, Finland

    Google Scholar 

  12. Dimitrova N, Jeannin S, Nesvadba J, McGee T, Agnihotri L, Mekenkam G (2002) Real time commercial detection using MPEG features. In: Proc. 9th int. conf. on information processing and management of uncertainty in knowledge-based systems (IPMU 2002). Annecy, France, pp 481–486 (Invited paper)

  13. Dinh PQ, Dorai C, Venkatesh S (2002) Video genre categorization using audio wavelet coefficients. In: ACCV2002: the 5th Asian conference on computer vision. Melbourne, Australia (January)

  14. Dorado A, Calic J, Izquierdo E (2004) A rule-based video annotation system. IEEE Trans Circuits Syst Video Technol 14(5):622–633

    Article  Google Scholar 

  15. EBU-UER (2007) Escort 2007. Technical Review 3322, EBU

  16. Fischer S, Lienhart R, Effelsberg W (1995) Automatic recognition of film genres. In: ACM multimedia 1995. San Francisco, CA, pp 295–304 (November)

  17. Glasberg R, Samour A, Elazouzi K, Sikora T (2005) Cartoon-recognition using video & audio-descriptors. In: 13th European signal processing conference (EUSIPCO2005). Antalya, Turkey (September)

  18. Goh KS, Miyahara K, Radhakrishan R, Xiong Z, Divakaran A (2004) Audio-visual event detection based on mining of semantic audio-visual labels. Technical Report 2004-008, Mitsubishi Electric Research Laboratory (MERL)

  19. Ianeva TI, de Vries AP, Rohrig H (2003) Detecting cartoons: a case study in automatic video-genre classification. In: IEEE international conference on multimedia and expo (ICME’03), pp 449–452 (July)

  20. Igel C, Hüsken M (2000) Improving the Rprop learning algorithm. In: Proceedings of the second international symposium on neural computation, NC2000

  21. Jolliffe IT (2002) Principal component analysis. Springer

  22. Liu Z, Huang J, Wang Y (1998) Classification of TV programs based on audio information using hidden Markov model. In: IEEE 2nd workshop on multimedia signal processing (MMSP ’98). Redonda Beach, CA, USA, pp 27–32 (December)

  23. Liu Z, Huang J, Wang Y, Chen T (1997) Audio feature extraction and analysis for scene classification. In: IEEE workshop on multimedia signal processing (MMSP’97), pp 343–348

  24. Lo Iacono A, Colamussi M (2005) Rai click—“I want my own TV”. Technical Review 303, EBU (July)

  25. Messina A, Montagnuolo M (2008) Fuzzy mining of multimedia genre applied to television archives. In: IEEE international conference on multimedia and expo. Hannover, Germany, 23–26 June 2008

  26. Messina A, Montagnuolo M (2008) Multimedia genre characterisation with fuzzy embedding classifiers. In: International workshop on ambient media delivery and interactive television (AMDIT2008). Quebec City, Canada (February)

  27. Messina A, Montagnuolo M, Sapino ML (2006) Characterizing multimedia objects through multimodal content analysis and fuzzy fingerprints. In: IEEE international conference on signal-image technology and internet-based systems (SITIS’06). Hammamet, Tunisia (December)

  28. Montagnuolo M, Messina A (2007) Automatic genre classification of TV programmes using Gaussian mixture models and neural networks. In: DEXA workshops. Regensurg, Germany, pp 99–103 (September)

  29. Montagnuolo M, Messina A (2007) Multimedia knowledge representation for automatic annotation of broadcast TV archives. J Digit Inf Manag 5(2):67–74

    Google Scholar 

  30. Montagnuolo M, Messina A (2008) Multimodal genre analysis applied to digital television archives. In: Second international workshop on multimedia data mining and management (DEXA-MDMM’08). Turin, Italy, 2 September 2008

  31. Novak AP (1988) Method and system for editing unwanted program material from broadcast signals. US Patent no. 4750213

  32. Parnal S, Pizzi S (2003) TV anytime: a new standard. EBU diffusion online, 2003/33, August

  33. Poli JP, Carrive J (2006) Improving program guides for reducing tv stream structuring problem to a simple alignment problem. In: CIMCA ’06: proceedings of the international conference on computational inteligence for modelling control and automation and international conference on intelligent agents web technologies and international commerce, p 31

  34. Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45

    Article  Google Scholar 

  35. Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc

  36. Rabiner LR (1989) A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286

    Article  Google Scholar 

  37. Roach M, Mason JS, Pawlewski M (2001) Motion-based classification of cartoons. In: IEEE international symposium on intelligent multimedia, video and speech processing (ISIMP2001), pp 146–149

  38. Roach MJ (2002) Video genre classification. PhD thesis, University of Wales Swansea

  39. Roach MJ, Mason JSD, Pawlewski M (2001) Video genre classification using dynamics. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP’01), pp 1557–1560

  40. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Parallel distributed processing: volume 1: foundations. The MIT Press, pp 318–362

  41. Safavian SR, Landgrebe DA (1991) A survey of decision tree classifier methodology. IEEE Trans Syst Man Cybern 21(3):660–674

    Article  MathSciNet  Google Scholar 

  42. Sánchez JM, Binefa X, Vitriá J, Radeva P (1999) Local color analysis for scene break detection applied to TV commercials recognition. In: VISUAL ’99: proceedings of the third international conference on visual information and information systems, pp 237–244

  43. Satterwhite B, Marques O (2004) Automatic detection of television commercials. IEEE Potentials 23(2):9–12

    Article  Google Scholar 

  44. Snoek C, Worring M (2005) Multimodal video indexing: a review of the state-of-the-art. Multimedia Tools and Applications 25(1):5–35

    Article  Google Scholar 

  45. Swain MJ, Ballard DH (1991) Color indexing. Int J Comput Vis 7(1):11–32 (November)

    Article  Google Scholar 

  46. Takagi S, Hattori S, Yokoyama K, Kodate A, Tominaga H (2003) Sports video categorizing method using camera motion parameters. In: IEEE 2003 international conference on multimedia and expo (ICME’03), pp 461–464 (July)

  47. Tamura H, Mori S, Yamawaki T (1978) Texture features corresponding to visual perception. IEEE Trans Syst Man Cybern 8(6):460–473

    Article  Google Scholar 

  48. Taskiran CM, Delp EJ (2001) Distribution of shot lengths for video analysis. In: Proceedings of SPIE, vol. 4676, pp 276–284

  49. Taskiran CM, Pollak I, Bouman CA, Delp EJ (2003) Stochastic models of video structure for program genre detection. In: 8th international workshop on visual content processing and representation (VLBV 2003). Madrid, Spain, pp 84–92 (September)

  50. Tekalp M (1995) Digital video processing. Prentice Hall

  51. Tomasi C (2005) Estimating Gaussian mixture densities with EM—a tutorial. Technical report, Duke University

  52. Truong BT, Venkatesh S, Dorai C (2000) Automatic genre identification for content-based video categorization. In: IEEE 15th international conference on pattern recognition (ICPP’00). IEEE Computer Society, pp 230–233

  53. Vakkalanka S, Mohan CK, Kumaraswamy R, Yegnanarayana B (2005) Combining multiple evidence for video classification. In: IEEE international conference on intelligent sensing and information processing (ICISIP’05), pp 187–192 (January)

  54. Vapnik VN (1999) The nature of statistical learning theory. Springer

  55. Vasconcelos N, Lippman A (2000) Statistical models of video structure for content analysis and characterization. IEEE Trans Image Process 9(1):3–19

    Article  Google Scholar 

  56. Vroomen JHM, Collier R, Mozziconacci S (1993) Duration and intonation in emotional speech. In: Eurospeech 1993, pp 577–580

  57. Wang J, Xu C, Chang E (2006) Automatic sports video genre classification using pseudo-2D-HMM. In: IEEE 18th international conference on pattern recognition (ICPR’06), pp 778–781

  58. Wickenberg-Bolin U, Göransson H, Fryknäs M, Gustafsson MG, Isaksson A (2006) Improved variance estimation of classification performance via reduction of bias caused by small sample size. BMC Bioinformatics 7:127

    Google Scholar 

  59. Xu LQ, Li Y (2003) Video classification using spatial-temporal features and PCA. In: IEEE international conference on multimedia and expo (ICME’03), pp 485–488 (July)

  60. Yuan X, Lai W, Mei T, Hua XS, Wu XQ, Li S (2006) Automatic video genre categorization using hierarchical SVM. In: IEEE international conference on image processing (ICIP’06). Atlanta, GA, pp 2905–2908 (October)

  61. Yuan Y, Song QB, Shen JY (2002) Automatic video classification using decision tree method. In: IEEE 1st international conference on machine learning and cybernetics, vol. 3. Beijing, pp 1153–1157

  62. Zhiwen Y, Xingshe Z, Jianhua G, Zhiyi Y (2004) Fuzzy clustering for tv program classification. In: IEEE international conference on information technology: coding and computing (ICIT’04), pp 658–662 (April)

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Turin, Corso Svizzera 185, 10149, Turin, Italy

    Maurizio Montagnuolo

  2. Centre for Research and Technological Innovation, RAI Radiotelevisione Italiana, Corso Giambone 68, 10135, Turin, Italy

    Alberto Messina

Authors
  1. Maurizio Montagnuolo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alberto Messina
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Maurizio Montagnuolo.

Additional information

Maurizio Montagnuolo is a PhD student supported by EuriX s.r.l., Turin, Italy— http://www.eurixgroup.com.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Montagnuolo, M., Messina, A. Parallel neural networks for multimodal video genre classification. Multimed Tools Appl 41, 125–159 (2009). https://doi.org/10.1007/s11042-008-0222-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-008-0222-3

Keywords

Search

Navigation