Robust nose detection in 3D facial data using local characteristics (TP-P2)

Author(s) : Chenghua Xu (National Lab of Pattern Recognition, China) Yunhong Wang (National Lab of Pattern Recognition, China) Tieniu Tan (National Lab of Pattern Recognition, China) Long Quan (Department of Computer Science, HKUST, China)

Abstract : The problem of detecting the feature points arises in many fields of science and engineering. In this paper, we focus on the 3D face range data and propose a robust scheme to solve a specific problem, i.e. locating the nose tip and nose ridge using the local statistic features and included angle curve. This work is very significant to 3D face modelling, recognition and registration. The key features of our method are the fully automated processing, the ability to deal with noisy and incomplete input data, the immunity to the rotation and translation and the adaptability to the different resolution. The experimental results in different databases fully show the robust and feasibility of the proposed method.

Menu