Eye and Nose Fields Detection from Gray Scale Facial Images

Detection of facial features such as eye, nose, and mouth is an important step for many subsequent facial image analysis tasks such as face recognition. In this paper, we introduce a method to detect eye and nose fields from gray scale facial images. The Independent Components Analysis (ICA) is utilized to learn the appearance and shape of the facial feature. The regions with high response to the ICA basis vectors are chosen as the target facial features. For improving the performance further, the local characteristics of eye and nose are adapted besides ICA. Experiments on different databases show the promising results of the proposed method.