Violence Content Classification Using Audio Features
This work studies the problem of violence detection in audio data, which can be used for automated content rating. We employ some popular frame-level audio features both from the time and frequency domain. Afterwards, several statistics of the calculated feature sequences are fed as input to a Support Vector Machine classifier, which decides about the segment content with respect to violence. The presented experimental results verify the validity of the approach and exhibit a better performance than the other known approaches.
KeywordsSupport Vector Machine Classifier Audio Signal Audio Data Audio Feature Classification Error Rate
Unable to display preview. Download preview PDF.
- 1.Vasconcelos, N., Lippman, A.: Towards semantically meaningful feature spaces for the characterization of video content. In: Proc. International Conference on Image Processing, October 1997, vol. 1, pp. 25–28 (1997)Google Scholar
- 2.Datta, A., Shah, M., Lobo, N.V.: Person-on-Person Violence Detection in Video Data. In: IEEE International Conference on Pattern Recognition, Canada (2002)Google Scholar
- 5.Cristianini, N., Shawe-Taylor, J.: Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge (2000); ISBN 0-521-78019-5Google Scholar