3D Facial Recognition: A Quantitative Analysis

Among the ensemble of biometric technologies employed for identification the use of noninvasive 2D facial recognition has, traditionally, been an attractive biometric. However, the accuracy of 2D facial recognition (FR) is performance limited and insufficient when confronted with extensive numbers of people to screen and identify, and the numerous appearances that a 2D face can exhibit. In efforts to overcome many of the issues limiting 2D FR technology, researchers and industrial companies are beginning to focus their attention on 3D FR technology. While 3D is thought to provide a richer representation for the recognition task, acquiring a cost-effective, accurate sensor that can perform over large distances is difficult, thus, limiting 3D FR’s wide-scale use and performance in a variety of settings. However, despite sensor issues a more fundamental question is whether 3D FR is reliable, accurate, and robust for identification. In this paper, a quantitative analysis of a 3D FR system being developed at Sandia National Laboratories is performed. The study involves the use of 200 subjects on which verification (one-to-one) matches are performed using a single probe database (one correct match per subject) and 30 subjects on which identification matches are performed. Only 3D facial data is used (i.e. no intensity data is used) so that the performance sensitivity of a purely 3D system can be assessed. The system is evaluated in terms of probability of detection (Pd) and probability of false accepts (FAR). The results presented will aid in providing an initial understanding of the performance of 3D FR.