What can I tell from your face?Enrico Grosso and Massimo Tistarelli
Computer Vision Laboratory
University of Sassari
Palazzo del Pousalid, p.zza Duomo, 07041
Alghero (SS) – Italy
The use of biometric data for user authentication and/or recognition is now a reality. Among the many developed techniques face analysis seems to be the most promising and interesting biometric modality. Nonetheless, there are still many open problems related to face recognition which need to be "faced" as well. For example, faces convey a great amount of information (in fact too much), which must be selectively extracted to obtain useful data for recognition. For this reason, the resolution of the face within the image, face registration and facial feature extraction are still open issues. This not only requires to devise new algorithms but to determine the real potential and limitations of existing techniques. This is possible only devising standard testing and assessment procedures based on statistical observations of the outputs of the system. In order to define better a standard evaluation process, a system based on space-variant iconic image matching is described and the validation procedure defined. I turns out that all methods based on the same biometric measurements have the same intrinsic limitations, which can be only overcome by the adoption of a multi-modal or multi-algorithmic approach.