Profile-based 3D-aided face recognition

This paper presents a framework for automatic face recognition based on a silhouetted face profile (URxD-PV). Previous research has demonstrated the high discriminative potential of this biometric. Compared to traditional approaches in profile-based recognition, our approach is not limited to only standard side-view faces. We propose to explore the feature space of profiles under various rotations with the aid of a 3D face model. In the enrollment mode, 3D data of subjects are acquired and used to create profiles under different rotations. The features extracted from these profiles are used to train a classifier. In the identification mode, the profile is extracted from the side-view image and its metadata is matched with the gallery metadata. We validate the accuracy of URxD-PV using data from publicly available databases.

► We introduce 3D-aided profile-based face recognition.
► A 3D-aided approach allows designing an algorithm robust to pose variation.
► The method is applicable to (visible spectrum/ infrared) image and video sequences.
► The Hausdorff Distance-based matching outperforms SVM-based matching.
► The gallery angular sampling range influences the performance.