Year: 1999
Type: conference-paper
Abstract: Neural networks have shown their reliability and robustness for the face detection task (Rowley, Baluja and Kanade, 1995). However, the time consuming process neededbyneural networks has prevented themfrom being a practical tool. We propose a new technique that signi cantly speeds up the time needed byatrained network (MLP in our case) to detect a face in a large image. We reformulate neural activities in the hidden layer of the MLP in terms of lter convolution, enabling the use of the Fourier transform for an e cient computation of the neural activities. The method was applied to face detection in still images as well as on live video sequences. 1
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1598732512
