Abstract: In 3D face related applications,the input faces are required to be well aligned to a reference one.In this paper,we present an automatic approach to correct the pose of the input face through nose detection.Firstly,vertices of the input face are clustered according to the property of normal vectors.Secondly,a graph-based partitioning algorithm is proposed to further partition the input face into several patches and an SVM detector is trained to select the patches that belong to the nose region.Then,pose correction is achieved by approximating a 3D affine transformation between the input face and the reference face.Finally,the ICP algorithm is used to correct the face pose more precisely.The evaluation of our approach is demonstrated on the BU-3D FE database and experimental results shows that our approach outperforms the representative conventional methods.