Human Face Detection in Digital Video using SVM Ensemble

H. M. Je, D. Kim, S. Y. Bang, Sang Youn Lee, Young Sik Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

As the amount of image and video data increases greatly, it requires an effective way to index and search. Human face can play an important role in indexing for multimedia databases. This paper proposes an automatic human face detection in digital video using SVM ensemble which is combining several SVMs in the scheme of majority voting. Experimental results show that the proposed detection method using SVM ensemble outperforms the conventional method using only single SVM in terms of false alarm and missing rate.

Original languageEnglish
Title of host publicationProceedings of the 6th Joint Conference on Information Sciences, JCIS 2002
EditorsJ.H. Caulfield, S.H. Chen, H.D. Cheng, R. Duro, J.H. Caufield, S.H. Chen, H.D. Cheng, R. Duro, V. Honavar
Pages417-421
Number of pages5
Publication statusPublished - 2002 Dec 1
EventProceedings of the 6th Joint Conference on Information Sciences, JCIS 2002 - Research Triange Park, NC, United States
Duration: 2002 Mar 82002 Mar 13

Publication series

NameProceedings of the Joint Conference on Information Sciences
Volume6

Conference

ConferenceProceedings of the 6th Joint Conference on Information Sciences, JCIS 2002
CountryUnited States
CityResearch Triange Park, NC
Period02/3/802/3/13

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Human Face Detection in Digital Video using SVM Ensemble'. Together they form a unique fingerprint.

  • Cite this

    Je, H. M., Kim, D., Bang, S. Y., Lee, S. Y., & Choi, Y. S. (2002). Human Face Detection in Digital Video using SVM Ensemble. In J. H. Caulfield, S. H. Chen, H. D. Cheng, R. Duro, J. H. Caufield, S. H. Chen, H. D. Cheng, R. Duro, & V. Honavar (Eds.), Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002 (pp. 417-421). (Proceedings of the Joint Conference on Information Sciences; Vol. 6).