Parametric Facial Landmark Detection Using Active Shape Models

Facial landmark detection plays a vital role in various applications, including face recognition and 3D face reconstruction. In this study, we introduce a parametric approach based on Active Shape Models (ASM) for facial landmark detection. Specifically, we encode landmark locations using ASM parameters and employ cascade regression to estimate these parameters. The final landmark positions are then derived from the ASM parameters. This parametric formulation offers a more compact and efficient representation compared to existing methods. Experimental results validate the effectiveness of our approach