A Selective Attention Driven Two-Stage Classifier for Fast Face Detection

Abstract

A novel system for face detection in images and video sequences is presented. The system incorporates a two-stage linear discriminant and nonlinear support vector machine classifier driven by a front-end selective attention search scheme. Additionally, by organizing the system into a client/server framework, efficient parallelization is achieved since the classifier can work independent of the selective attention mechanism once sufficient initial data has been shared between the client and server. Experimental results based on the CMU face image set demonstrate that by using such a classifier arrangement with a non-exhaustive searching scheme, a significant reduction in computational complexity is achieved while maintaining comparable accuracy to other leading face detection systems.