A Multi-Modal Approach to Frontal and Non Frontal Facial Feature Detection

Biometrics are measurable characteristics specific to an individual. They can be used to identify individuals. The use of biometrics for identification has the potential to make our lives easier, and the world we live in a safer place. While numerous different types of exploitable biometrics exist, facial identification is highly pursued because the data can be captured at a distance without requiring the subject s active cooperation. While traditionally 2D images of faces have been used, 3D scans that contain both 3D data and registered color are becoming easier to acquire. Before 3D face images can be used to identify an individual, they require some form of initial alignment information, typically based on facial feature locations. This thesis proposes and analyzes a multimodal approach to automatic facial feature detection. After beginning with a discussion on biometrics and the role of automatic facial feature detection, we provide a comparative evaluation of 3D sensors. We follow this by a discussion of the algorithm s performance when constrained to frontal images and an analysis of its performance on a more complex dataset with significant head pose variation.