Auricle Structural Feature for 3D Ear Recognition

Kai Wang, Zhi-chun Mu

Abstract


The existing local surface representation methods of 3D ear recognition not only ignore the physiological structure of ear, but also have high computation complexity. Aiming at these problems, a novel 3D ear representation called 3D Auricle Structural Feature(3DASF) is proposed. It extracts the auricle structural information by the Surface Variation. 3DASF is used to coarsely align the probe gallery ear pairs, and subsequently ICP fine alignment is performed. The experiments results conducted on the University of Notre Dame(UND) collection J2 dataset outperform the state-of-the-art 3D ear recognition methods based on ICP.

Keywords


3D ear recognition; 3D feature; auricle structure; iterative closest point

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ACSA©: World Science Publisher United States