Research Interests

Projects

3D Facial Reconstruction

Identification of human faces is a very challenging research area, which has gained much attention during the last few years, as the role of this technology could be relevant in many related applications such surveillance of access critical systems. The vast majority of face recognition methodologies are based on 2D image processing of photos or video footage offering the advantage of a simple and affordable data acquisition. They typically perform well when scene lighting, camera position and orientation are carefully controlled, but recognition becomes increasingly more difficult and unreliable when face position and orientation are not known or in case of strong variations in facial expression. As tridimensional scanning techniques for face and full body are becoming more diffused and reliable, it is now possible to create detailed 3D facial database for biometrical purposes. This technology is pushing the development of recognition methods to fully exploits the potential of 3D face representation.

Moregine: A case of study

This study presents a face reconstruction methodology optimized for archaeological/anthropological applications applied to one of the skulls found in the archaeological site of Murecine (in the Pompei surroundings). This site, originally discovered about fifty years ago, is known for the presence of an exceptionally well preserved roman villa including many bones belonged to a group of people who found death during the volcanic eruption of 79 a. C.

website: http://www.dmi.unisa.it/murecine/

3D Face Recognition

Face recognition is a very challenging research area, featuring a growing interest from scientific community during the last few years, as the role of this technology could be crucial in many security related applications such as surveillance or access to critical systems. The term 3D face recognition usually refers to a recognition methodology operating on dataset representing face shape as range data or polygonal mesh. The 3D approach is interesting for many reasons such as a more accurate representation of actual facial features leading to a potentially higher discriminating power and the promise to better cope with the large amount of variations present in human face: extra-subject variations (individual appearance) and intra-subject variations (facial expression and aging).

Università degli Studi di Salerno | Dipartimento di Matematica ed Informatica | Gabriele Sabatino | ©2004