Building a morphable 3-D face model that relates impressions of the face to physical features

This paper describes a vector representation of 3-D shapes acquired in the form of 2-D range images produced using a range finder (NEC Danae-R). The vectorization was performed by first extracting feature points that correspond to each other as landmarks among different 3-D face shapes, and then re-sampling each surface region of the face divided by the landmarks into other regions to obtain corresponding elements of the 3-D shape vector. A linear description of the 3-D shape spaces obtained by principal component analysis allows a smooth morphable modeling of a human face in terms of a smaller number of projection parameters. We scientifically solved the relations between shapes and impressions of faces and attempted face-image manipulations that transform impressions on facial attributes.