A Comparative Study of Face Landmarking Techniques

Face landmarking, that is detection and localization of certain characteristic points on the face, is an important intermediary step for many subsequent face processing operations that range from biometric recognition to the understanding of mental states. Despite its conceptual simplicity, this computer vision problem has proven extremely challenging due to inherent face variability as well as the multitude of confounding factors such as pose, expression, illumination and occlusions. The purpose of this survey is to give an overview and categorization of the approaches used for face landmarking. The methods are classified in broad categories, their shortcomings and advantages are comparatively discussed, their performances reported, and the main trends indicated. We expect this survey will provide further impetus for high-performance, real-life face landmarking at video rates.