Authors: Konstantinos E. Rapantzikos, Nicolas Tsapatsoulis
Addresses: School of Electrical and Computer Engineering, National Technical University of Athens, 15780 Zografou, Greece. ' Department of Computer Science, University of Cyprus, 75 Kallipoleos Str., P.O. Box 20537, CY 1678, Nicosia, Cyprus, Greece
Abstract: Feature map fusion in Visual Attention (VA) models is by definition an uncertain procedure. One of the major impediments in extending the static VA architecture proposed by Itti et al. (2000) to account for motion or other information is the lack of justification on how to integrate the various channels. We propose an innovative committee machine scheme that allows for dynamically changing the committee members (maps) and weighting them according to the confidence level of their estimation. Through this machine we handle the extensions on Itti|s model; we add a motion channel and a prior knowledge channel which accounts for the conscious search performed by humans when looking for faces in a scene. The experimental results, obtained when considering face detection, show that the map fusion, through the proposed committee machine, leads to significantly better statistical results when compared with the simple skin-based face detection method.
Keywords: committee machines; map fusion; visual attention; face detection; uncertainty; image processing.
International Journal of Intelligent Systems Technologies and Applications, 2006 Vol.1 No.3/4, pp.346 - 358
Published online: 01 Jun 2006 *Full-text access for editors Access for subscribers Purchase this article Comment on this article