计算机工程 ›› 2008, Vol. 34 ›› Issue (4): 223-225.doi: 10.3969/j.issn.1000-3428.2008.04.079

• 人工智能及识别技术 • 上一篇    下一篇

基于耳廓参数与面部特征相结合的人耳识别

苑玮琦,万 新   

  1. (沈阳工业大学视觉检测技术研究所,沈阳 110023)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-02-20 发布日期:2008-02-20

Ear Recognition Based on Combination of Ear Contour’s Parameter and Facial Features

YUAN Wei-qi, WAN Xin   

  1. (Computer Vision Group, Shenyang University of Technology, Shenyang 110023)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-02-20 Published:2008-02-20

摘要: 针对外耳轮廓特征与人脸五官的比例关系,提出一种基于耳廓几何参数与面部结构特征相结合的生物鉴别方法。该方法将外耳轮廓与人脸某些特征相结合,如特征向量中包括人耳宽度与两眼瞳孔之间的水平距离之比、人耳高度与眼睛和嘴之间的垂直距离之比。实验结果表明,该算法简单、可操作性强,对数据采集设备及采集条件要求较低,识别率较高。

关键词: 人耳识别, 多模态生物识别技术, 虹膜定位, 轮廓跟踪, 模式识别

Abstract: According to the relationship between ear contour and proportion of the five sense organs, this paper adopts a method for biometrics based on combination of ear contour’s geometry parameter and facial configuration features. The method combines ear contour and some facial features such as the feature vector consists of the proportion of ear’s width compared with pupils’ horizontal distance and the proportion of ear’s height compared with vertical distance between eyes and mouth. Experimental results show that the method is simple and well operational. It has low demand on data acquisition equipment and acquisition condition, and does well in recognition.

Key words: ear recognition, multimode biometric technology, iris localization, contour tracking, pattern recognition

中图分类号: