- Prof. Nick Fieller – Department of Probability & Statistics – University of Sheffield
- FCUL (DEIO) – Campo Grande – Bloco C/6 Piso 4 – Sala 6.4.30 – 14h
- Quinta-feira, 5 de Março de 2009
Abstract:
There are many existing systems for automatic facial recognition. These select one or more images from a databse of known people as the best available match to a questioned image of a human face. These systems are successful and widely used in areas such as security surveillance, especially scanning for known suspects. However, they do not attempt to provide any quantitative measure of quality of match but only give the best available match. In this respect they fall short of a facial identification which can give evidential information of use in a court of law. The work described here provides a statisfically based method which can remedy these defects. It is based on landmark identification of facial features and routine techniques of shape analysis to provide measures of inter and intra variability of measured facial features, thus allowing a more statistical assessment of facial identification. By modelling the joint distribution of facial features and so construction of likelihood rations for assessing evidence of identification.