Three-dimensional (3D) facial recognition and prediction

This paper provides solution to the problem in identifying humans from their three dimensional facial characteristics. For this reason a standard 3D facial recognition system was built and used in this research work. The system which also consist of several other systems were divided into simpler form for proper analysis and better performances. The sub-system consist of: registration, representation of faces, extraction of discriminative features, and fusion of matchers. For each of the sub-system, this paper evaluates the state of the art methods, and also propose new and better ones. This research uses generic face model which speeds up the correspondence establishment process. In facial representation schemes, implementation of diverse range of approaches such as point clouds, curvature-based descriptors, and range images were implored. While various feature extraction methods were used to determine the discriminative facial features. An in-depth analysis of decision-level fusion algorithms was perform. In addition to the evaluation of baseline fusion methods, we propose to use two novel fusion schemes where the first one employs a confidence-aided combination approach, and the second one implements a two-level serial integration method. Recognition simulations performed on the 3DRMA and the FRGC databases show that: generic face template-based rigid registration of faces is better than the non-rigid variant, principal curvature directions and surface normals have better discriminative power, representing faces using local patch descriptors can both reduce the feature dimensionality and improve the identification rate, and confidence-assisted fusion rules and serial two-stage fusion schemes have a potential to improve the accuracy when compared to other decision-level fusion rules.