Domain-Specific Face Synthesis for Video Face Recognition from a Single Sample Per Person
share
The performance of still-to-video face recognition (FR) systems can decline significantly because faces captured in the unconstrained operational domain (OD) have a different underlying data distribution compared to faces captured under controlled conditions in the enrollment domain (ED). This is particularly true when individuals are enrolled to the system using a single reference still. To improve the robustness of these systems, it is possible to augment the gallery set by generating synthetic faces based on the original still. However, without the OD knowledge, many synthetic faces must be generated to account for all possible capture conditions. FR systems may therefore require complex implementations and yield lower accuracy when training on less relevant images. This paper introduces an algorithm for domain-specific face synthesis (DSFS) that exploits the representative intra-class variation information available from the OD. Prior to operation (during camera calibration), a compact set of faces from unknown persons appearing in the OD is selected through clustering in the captured condition space. The domain-specific variations of these faces are projected onto the reference still of each individual by integrating an image-based face relighting technique inside a 3D reconstruction framework. A compact set of synthetic faces is generated under the OD capture conditions. In a particular implementation based on sparse representation classification, the synthetic faces generated with the DSFS are employed to form a cross-domain dictionary where the dictionary blocks combine the original and synthetic faces of each individual. Experimental results obtained with the Chokepoint and COX-S2V datasets reveal that augmenting the gallery set using the DSFS approach provide a higher level of accuracy compared to state-of-the-art methods, with only a moderate increase in its complexity.
READ FULL TEXT