摘要
本文提出了一种基于力场转换理论的人耳识别方法,在检测出耳廓边缘的基础上,将图像分别通过力场和能量场进行描述,利用测试点在力场中运动最终收敛至图像能量局部最小值处这一个特征,对人耳图像特征点进行定位,最终利用提取出的"势能阱"和"势能渠"实现匹配与识别,经在选用的耳廓图库上实验,错误接受率FAR为1.28%,错误拒绝率FRR为6.28%。
This paper presents an ear identification method based on force field transformation. The ear contour is measured first, then the ear image is described by the force field and energy field. And the ear image feature points can be located according to the character that the field lines converge toward the local minium value of image energy. Experiment shows that the FAR（False Acceptance Rate） and FRR（False Rejection Rate） are 1.28% and 6.28% respectively.
出处
《自动化技术与应用》
2009年第1期82-87,57,共7页
Techniques of Automation and Applications
关键词
耳廓识别
力场转换
势能阱
car identification
force field transformation
energy wells and channels
