In this paper, we present and investigate the performance of an algorithm designed to identify facial features on an android mobile platform. Facial feature identification is the necessary step before many computer vision systems including emotion detection, face tracking and face recognition. The facial feature identification algorithm presented is based on an anthropometric face model , box-blur filtering, and non-maximum suppression to find eyes corners, mouth corners and nose centre. Skin colour detection is used to find regions in the image that have a higher potential of containing eyes. The anthropometric face model is used to reduce the computational complexity involved in localising facial regions. This algorithm is designed to be compatible with the limited hardware and memory capabilities of mobile devices.
展开▼
