Tri-dimensional face detection and localization
Alessandro Colombo, Claudio Cusano, Raimondo Schettini · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2005
This paper presents an innovative method that combines a feature-based approach with a holistic approach for tri-dimensional face detection and localization. Salient face features, such as the eyes and nose, are detected through an analysis of the curvature of the surface. In a second stage, each triplet consisting of a candidate nose and two candidate eyes is then processed by a PCA-based classifier, trained to discriminate between faces and non-faces. The method has been tested on about 150 3D faces acquired by a laser range scanner with good results.