Abstract
This paper addresses the automatic classification of X-rated videos by analyzing its obscene sounds. In this paper, we propose the optimized repeated curve-like spectrum feature for classifying obscene sounds and the skip-and-analysis processing for classifying videos. The optimized repeated curve-like spectrum feature uses the longer frame size for stationary frequency region based on the fact that most of obscene sounds, such as sexual moans and screams, consist of mostly vowels and the variation of syllables occurs slowly compared to general speech. It also uses the customized mel-scaled bandpass filter for the valid frequency regions of obscene sounds with the frequency contents mainly under 5 kHz. The skip-and-analysis processing is based on the video playback characteristics that a harmful or normal scene continues to be played at least for certain duration of time during a playback. When the skip-and-analysis processing is applied, clips to be analyzed are selected by skip interval values and only these selected clips are used to classify videos. The processing performances of the optimized repeated curve-like spectrum feature have improvements from 21 % to 25.6 % compared to the repeated curve-like spectrum feature without degradation of classification performance in clip-level classification. Furthermore, when the skip-and-analysis processing is applied, the processing performance of classifying is improved significantly by from 82.59 % to 95.03 % maintaining the classification performance of more than 90 % at F1-score.
Similar content being viewed by others
References
Bosson A, Cawley GC, Chan Y, Harvey R (2002) Non-retrieval: Blocking pornographic images. Proc. ACM International Conf. on Image and Video Retrieval, pp 50–60
Brezeale D, Cook DJ (2008) Automatic video classification: a survey of the literature. IEEE Trans Syst Man Cybern Part C Appl Rev 38(3):416–430
Cho DU (2004) Blocking of internet harmful pronographic sites by contents-based method. J Korea Info Commun Soc 29(6B):554–562
Coopersmith J (2000) Pornography, videotape, and the internet. IEEE Technol Soc Mag 19:27–34
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20:273–297
Google Sage Search (2010) http://www.google.com. Accessed 15 March 2010
Guo G, Li SZ (2003) Content-based audio classification and retrieval by support vector machine. IEEE Trans Neural Netw 14(1):209–215
Hsu CW, Chang CC, Lin CJ (2009) A practical guide to support vector classification. http://www.csie.ntu.edu.tw/~cjlin/libsvm/ Accessed 30 Oct 2009
Jansohn C, Ulges A, Breuel TM (2009) Detecting pornographic video content by combining image features with motion information. Proc. ACM International Conference on Multimedia
Kamde PM, Algur SP (2011) A survey on web multimedia mining. Int J Multimed Appl 3(3):72–84
Kim CY, Kwon OJ, Kim WG, Choi SR (2008) Automatic system for filtering obscene video. Proc. 10th International Conference on Advanced Communication Technology (ICACT2008). Pp 1435–1438
Lee CH, Han CC, Chuang CC (2008) Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients. IEEE Trans Audio Speech Lang Process 16(8):1541–1550
Lee JS, Kuo YM, Chung PC, Chen EL (2007) Naked image detection based on adaptive and extensible skin color model. J Pattern Recognit 40:2261–2270
Lim JD, Choi BC, Han SW, Chung BH, Lee CH (2011) Classification and detection of objectionable sounds using repeated curve-like spectrum feature. Proc. International Conf. on Information Science and Applications (ICISA2011), On-line Proceedings
Lim JD, Choi BC, Han SW, Lee CH (2011) Automatic classification of x-rated videos using obscene sound analysis based on a repeated curve-like spectrum feature. Int J Multimed Appl 3(4):1–17
Lim JD, Han SW, Choi BC, Chung BH (2009) A study of classifying the objectionable contents by using the MFCCs-based audio feature set. Proc. 10th International Conf. on Computers, Communications, and Systems (ICCCS’09), pp 255–258
Liu Z, Wang Y, Chen T (1998) Audio feature extraction and analysis for scene segmentation and classification. J VLSI Signal Proc Syst 20(1/2):61–79
Lu L, Zhang HJ (2002) Content analysis for audio classification and segmentation. IEEE Transactions on speech and audio processing, Vol.10, pp 504–516. Vetro A, Sun H, DaGraca P, Poon T. Minimum drift architectures for three-layer scalable DTV decoding. IEEE Trans. Consumer Electron., vol. 44, no. 3, pp 527–536, Aug. 1998
Lu L, Zhang HJ, Li SZ (2003) Content-based audio classification and segmentation by using support vector machines. ACM Multimedia Systems J 8(6):482–492
Rao CS, Kumar SS, Mohan BC (2010) Content based image retrieval using exact legendre moments and support vector machine. Int J Multimed Appl 2(2):69–79
Rea N, Lacey G, Lambe C, Dahyot R (2006) Multimodal periodicity analysis for illicit content detection in videos. Proc. IET Conference on Visual Media Production(CVMP2006), pp 106–114
Rowley HA, Jing Y, Baluja S (2006) Large scale image-based adult content filtering. Proc. International Conf. on Computer Vision Theory and Applications (VISAPP), pp 290–296
Secret Rabbit Code (2011) http://www.mega-nerd.com/SRC/ Accessed 1 June 2011
Shigeo A (2005) Support vector machines for pattern classification. Springer, London
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Wang JZ, Li J, Wiederhold G, Firschein O (1998) System for screening objectionable images. J Image Comput Commun 21:1355–1360
Wang JC, Wang JF, Lin CB, Jian KT, Kuok WH (2006) Content-based audio classification using support vector machines and independent component analysis. Proc. 18th International Conf. on Pattern Recognition (ICPR06), Vol.4, pp 157–160
Acknowledgments
This research was supported by the KCC (Korea Communications Commission), Korea; under the ETRI R&D support program supervised by the KCA (Korea Communications Agency).” (KCA-11921-05001)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lim, JD., Kim, JN., Jung, YG. et al. Improving performance of X-rated video classification with the optimized repeated curve-like spectrum feature and the skip-and-analysis processing. Multimed Tools Appl 71, 717–740 (2014). https://doi.org/10.1007/s11042-013-1401-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1401-4