An Image Processing and Belief Network Approach to Face Detection

This work describes an approach for face detection, which is the rst stage of any fully automatedhumanface recognition system. We propose several enhancements to a feature-based approach described by Yow and Cipolla 20 in an attempt to obtain more accurate results. Namely, the attentive feature selection and grouping phases are modi ed in order to deal with incomplete feature detection while, at the same time, reducing the number of candidates and candidate groups considered.

• Type: Conference
• Year: 1999
• Where: SIBGRAPI
• Authors: Paulo Sérgio de Souza Coelho, Claudio Esperança, Antonio A. F. Oliveira
• Keywords: Attentive Feature Selection, Automatedhumanface Recognition System, Computer Graphics, Incomplete Feature Detection, SIBGRAPI 1999