J4 ›› 2014, Vol. 41 ›› Issue (4): 20-25+165.doi: 10.3969/j.issn.1001-2400.2014.04.004

• 研究论文 • 上一篇    下一篇

鼻子区域生物特征识别

李云飞;卢朝阳;李静;姚超   

  1. (西安电子科技大学 综合业务网理论及关键技术国家重点实验室,陕西 西安  710071)
  • 收稿日期:2013-04-02 出版日期:2014-08-20 发布日期:2014-09-25
  • 通讯作者: 李云飞
  • 作者简介:李云飞(1974-),男,副教授,西安电子科技大学博士研究生,E-mail:wnlff@126.com.
  • 基金资助:

    国家自然科学基金资助项目(60872141) ;中央高校基本科研业务费专项资金资助项目(K50510010007);华为高校创新研究计划资助项目(IRP-2012-03-06)

Personal recognition with nose area biometrics

LI Yunfei;LU Zhaoyang;LI Jing;YAO Chao   

  1. (State Key Lab. of Integrated Service Networks, Xidian Univ., Xi'an  710071, China)
  • Received:2013-04-02 Online:2014-08-20 Published:2014-09-25
  • Contact: LI Yunfei

摘要:

人脸图像信息中鼻子区域受表情、胖瘦、发型等变化的影响极小,为人脸识别过程提供了稳定的个体特征.首先对鼻子的生理结构进行了剖析,分析了利用鼻子区域识别个体的可行性及其特点;再对提取鼻子特征的Gabor参数进行了简化;然后用Gabor 核Fisher判别分析算法在不同数据库上对鼻子区域的识别效果进行了实验分析.结果表明,在表情和姿态变化较大的情况下,鼻子区域的识别效果要比人脸的识别效果好.

关键词: 鼻子识别, 人脸识别, 生物特征识别, Gabor核Fisher判别分析

Abstract:

The nose area of a face can provide some stable individual characteristic information for personal recognition because of its tiny changes affected by expression, weight and hairstyle. The paper first dissects the physiological structure of the nose and discusses the feasibility and characteristics of nose recognition. Furthermore, authors simplify Gabor's parameters in extracting nose features, and compare the recognition effect by experiment with the Gabor Kernel Fisher Discriminant Analysis in different databases. Experiment shows that the nose area has a better recognition result than the face when the face image has a rich expression or wide range poses.

Key words: nose recognition, face recognition, biometrics recognition, Gabor kernel Fisher discriminant analysis

中图分类号: 

  • TP39l