首页> 外文期刊>Journal of computer sciences >3-DIMENSIONAL EAR RECOGNITION BASED ITERATIVE CLOSEST POINT WITH STOCHASTIC CLUSTERING MATCHING | Science Publications
【24h】

3-DIMENSIONAL EAR RECOGNITION BASED ITERATIVE CLOSEST POINT WITH STOCHASTIC CLUSTERING MATCHING | Science Publications

机译:基于3维耳朵识别的迭代最近点和随机聚类匹配|科学出版物

获取原文
       

摘要

> Ear recognition is a new technology and future trend for personal identification. However, the false detection rate and matching recognition are very challenging due to the ear complex geometry. The Scope of the study is to introduced a combination of Iterative Closest Point (ICP) and Stochastic Clustering Matching (SCM) algorithm for 3D ears matching based on biometrics field with a good steadiness to reduce the false detection rate. The corresponding ear extracts from the side range image and characterized by 3D features. The proposed method used matlab simulation and defined the average detection time 35ms and an identification similarity is 98.25% for the collection of different database. The result shows that the proposed combined method outperforms than the existing of ICP or SCM in terms of detection time and accuracy in training.
机译: >耳识别是一种新技术,并且是个人识别的未来趋势。然而,由于耳朵复杂的几何形状,错误检测率和匹配识别非常具有挑战性。研究的范围是引入基于生物特征场的3D耳朵匹配的迭代最近点(ICP)和随机聚类匹配(SCM)算法的组合,具有良好的稳定性以降低错误检测率。相应的耳朵从侧面图像中提取出来,并具有3D特征。该方法采用matlab仿真,定义了平均检测时间为35ms,识别相似度为98.25%。结果表明,所提出的组合方法在检测时间和训练准确性方面均优于ICP或SCM。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号