Enhancing the robustness of skin-based face detection schemes through a visual attention architecture

Rapantzikos, K; Tsapatsoulis, N

dc.contributor.author	Rapantzikos, K	en
dc.contributor.author	Tsapatsoulis, N	en
dc.date.accessioned	2014-03-01T02:43:15Z
dc.date.available	2014-03-01T02:43:15Z
dc.date.issued	2005	en
dc.identifier.issn	15224880	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31324
dc.subject	Dynamic Change	en
dc.subject	Face Detection	en
dc.subject	Human Performance	en
dc.subject	Video Segmentation	en
dc.subject	Visual Attention	en
dc.subject	Bottom Up	en
dc.subject	Confidence Level	en
dc.subject.other	Domain information	en
dc.subject.other	Visual Attention (VA)	en
dc.subject.other	Image segmentation	en
dc.subject.other	Information analysis	en
dc.subject.other	Motion compensation	en
dc.subject.other	Video recording	en
dc.subject.other	Visualization	en
dc.subject.other	Feature extraction	en
dc.title	Enhancing the robustness of skin-based face detection schemes through a visual attention architecture	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2005.1530301	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2005.1530301	en
heal.identifier.secondary	1530301	en
heal.publicationDate	2005	en
heal.abstract	Bottom up approaches to Visual Attention (VA) have been applied successfully in a variety of applications, where no domain information exists, e.g. general purpose image and video segmentation. In face detection, humans perform conscious search; therefore, bottom up approaches are not so efficient. In this paper we introduce the inclusion of two channels in the VA architecture proposed by Itti et al [8] to account for motion and conscious search in a scene. Increasing the channels in the architecture requires an efficient way of combining the various maps that are produced. We solve this problem by using an innovative committee machine scheme which allows for dynamically changing the committee members (maps) and weighting the maps according to the confidence level of their estimation. The overall VA architecture achieves significantly better results compared with the simple skin based face detection as shown in the experimental results. © 2005 IEEE.	en
heal.journalName	Proceedings - International Conference on Image Processing, ICIP	en
dc.identifier.doi	10.1109/ICIP.2005.1530301	en
dc.identifier.volume	2	en
dc.identifier.spage	1298	en
dc.identifier.epage	1301	en