Comparison of Performance between Different SVM Kernels for the Identification of Adult Video
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32769
Comparison of Performance between Different SVM Kernels for the Identification of Adult Video

Authors: Hajar Bouirouga, Sanaa El Fkihi , Abdeilah Jilbab, Driss Aboutajdine

Abstract:

In this paper we propose a method for recognition of adult video based on support vector machine (SVM). Different kernel features are proposed to classify adult videos. SVM has an advantage that it is insensitive to the relative number of training example in positive (adult video) and negative (non adult video) classes. This advantage is illustrated by comparing performance between different SVM kernels for the identification of adult video.

Keywords: Skin detection, Support vector machine, Pornographic videos, Feature extraction, Video filtering, Classification.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1081693

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2241

References:


[1] J. Z. Wang, J. Li, G. Wiederhold, and O. Firschein, Classifying objectionable websites based on image content, Special issue on iteractive distributed multimedia systems and telecommunication services, vol. 21/15, pp. 113-124, 1998.
[2] J.-C. Terrillon, M. N. Shirazi, H. Fukamachi, and S. Akamatsu, The Comparative of different skin chrominance models for the automatic detection of human faces in color images, Fourth International Conference On Automatic Face and gesture Recognition, pp. 54- 61,2000
[3] DAE HYUN KIM and KIM Myoung-Jun, Skin color analysis in HSV color space and rendering with fine scale skin structure, 24th Computer Graphics International Conference, CGI 2006, Hangzhou, China, June 26-28, 2006.
[4] W. Kelly, A. Donnellan, D. Molloy A Review of Skin Detection Techniques for Objectionable Images, Proc. 4th European Conf. on Computer Vision, 2007.
[5] Chai, D. Phung, S.L. Bouzerdoum, A. Sch. of Eng. & Math., Edith Cowan Univ., Perth, WA, Australia, A Bayesian skin/non-skin color classifier using non-parametric density estimation, 25-28 May 2003.
[6] S. L. Phung, A. Sr. Bouzerdoum, and D. Sr. Chai, "Skin segmentation using color pixel classification: Analysis and comparaison," IEEE Transactions On Pattern Analysis and Machine Intelligence, vol. 27, pp. 148-154, 2005.
[7] Ming hsuan Yang and Narendra Ahuja, "Gaussian mixture model for human skin color and its application in image and video databases," in Proceedings of SPIE 99 (San Jose CA ), pp. 458-466, 1999.
[8] S. Makrogiannis P. Kakumanu and N. Bourbakis, "A survey of skincolor modeling and detection methods," Pattern Recognition, vol. 40, no. 3, pp. 1106-1122, March 2007.
[9] S.L. Phung, A. Bouzerdoum, D. Chai, Skin segmentation using colour pixel classification: analysis and comparison, IEEE Trans. Pattern Anal. Mach. Intell, pages 148-154, 2005.
[10] V.Vezhnevets ,V. Sazonov, A . Andreeva, A Survey on Pixel-Based Skin Color Detection Techniques, Machine Graphics & Vision International Journal 2005.
[11] HUICHENG ZHENG, Blocking Objectionable Images: Adult Images and Harmful Symbols, January 1998.
[12] Feng Jiao, Wen Giao, Lijuan Duan, and Guoqin Cui, Detecting adult image using multiple features, IEEE conference, pp.378 - 383 vol.3, Nov. 2001.
[13] Joachims T, Making Large-Scale SVM Learning Practical. LS8-Report, University of Dortmund, LS 1998
[14] Vladimir VN, The Nature of Statistical Learning Theory. Springer, Berlin Heidelberg New York, 1995.