Download:

Exploting the time domain in face-based biometrics

Prof. Massimo Tistarelli
Università di Sassari, Italy

Biometric recognition has attracted the attention of scientists, investors, government agencies as well as the media for the great potential in many application domains. It turns out that there are still a number of intrinsic drawbacks in all biometric techniques. In this paper we postulate the need for a proper data representation which may simplify and augment the discrimination among different instances or biometric samples of different subjects. Considering the design of many natural systems it turns out that spiral (circular) topologies are the best suited to economically store and process data. Among the many developed techniques for biometric recognition, face analysis seems to be the most promising and interesting modality. The ability of the human visual system of analyzing unknown faces, is an example of the amount of information which can be extracted from face images. This is not limited to the space or spectral domain, but heavely involves the time evolution of the visual signal. Nonetheless, there are still many open problems which need to be “faced” as well. This not only requires to devise new algorithms but to determine the real potential and limitations of existing techniques, also exploiting the time dimensionality to boost recognition performances.

This talk will survey face image analysis under a new perspective: i.e. the exploitation of the time dimension. 

This lecture will review several methods for face matching, based on diverse similarity measure and image representations, but dealing with image streams. Some new methods are described, tested with conventional and also new databases from real working environments.

 

with support from