Illumination Invariant and Component Based Approach for Face Alignment

Abstract

Localization of facial components is very important for many pattern recognition and computer vision applications such as face recognition, tracking of face expressions. This paper addresses the problem of precisely finding facial components, such as the eyes, the mouth, the nose etc. For accurate face alignment we propose a new component based AAM to get accurate location of facial landmarks. This paper combines the concept of component-based approach and Active Appearance Model based face alignment and develops component-based AAM method for fine face alignment. We demonstrate that the proposed method gives more accurate and reliable results as compared to classical AAM under various lighting conditions.