3D face geometry analysis for biometric identification
Jan Andrzej Napieralski, Michal Miroslaw Pastuszka, Wojciech Sankowski · 2014
The aim of the work presented in this paper was to develop a set of algorithms for face biometric identification based on the three dimensional face model. To fulfill this goal, the face segmentation and extraction of face features were performed. The result of the segmentation was a set of landmarks used then by the extraction process to produce the individual face features for each studied face. Those values have been obtained by the developed algorithms, calculating vector distances and triangle areas. Next, those individual features were compared among the entire database to produce the Detection Error Tradeoff (DET) curves. Based on these results, the appropriate conclusions were formulated.