An effective search method for NN-based face detection using PSO

This paper presents a novel method to speed up neural network (NN) based face detection systems. Face detection can be viewed as a classification and search problem. The proposed method formulates the search problem as an integer nonlinear optimization problem (INLP) and expands the basic particle swarm optimization (PSO) to handle it. In PSO, each particle represents a subwindow in the input image. The subwindows are evaluated by how well they match a NN based face filter. A face is indicated when the filter response of the best particle is above a given threshold. Experiments results show that to find a face, only a small number of subwindows need to be evaluated compared to using the classical technique.