3D Ear Recognition Using SIFT Keypoint Matching
In this paper, we present a novel algorithm for 3D ear recognition. The basic idea is to rotate each 3D point cloud representing an individuals ear around the x, y or z axes, respectively generating multiple 2.5D images at each step of the rotation. Then we use SIFT descriptors to extract and describe the features of human ears. The test ear images are recognized by the application of a new weighted keypoint matching algorithm. Experimental results show that this method is both accurate and efficient.
SIFT keypoint detection 2.5D image
Xin Dong Yin Guo
School of Information Engineering University of Science and Technology Beijing Beijing, China
国际会议
重庆
英文
183-186
2011-01-21（万方平台首次上网日期，不代表论文的发表时间）