Fast 3D Face Alignment and Improved Recognition Through Pyramidal Normal map Metric

Face's tri-dimensional shape represents a highly discriminating yet challenging biometric identifier due to different issues, some of which related to capture, alignment and normalization. This paper presents an improved normal map based face recognition approach, which relies on a novel method to automatically align a captured 3D face mesh to a reference template, allowing a more precise face comparison. The alignment algorithm exploits pyramidal-normal-map metric, a coarse to finer measurement of angular distance between two surfaces computed through normal maps with progressively increasing resolution. After the registration has been performed, the normalized face can be rapidly compared to any other template in the gallery database for authentication or identification purposes using standard normal map metric. The alignment approach avoids the need for a rough or manual face pre-alignment and maximizes recognition precision, requiring a fraction of the time needed by the iterative closest point (ICP) method to operate. We show preliminary experimental results on a 3D dataset featuring 235 different subjects.

1. INTRODUCTION

Many of the challenges in face recognition are directly or indirectly related to the modalities in which this biometric is captured and pre-processed, and this applies for 2D and 3D recognition approaches as well. To this regard, Bowyer, Chang and Flynn in their recent survey on the state of the art in 3D face recognition [1] show that face acquisition in three dimensions by means of range image is not free from some of the posing issues typical of 2D face capture. In fact, subject posing within the capture field randomly affects position, rotation and scaling of resulting point cloud.