| 基于主曲线的指纹细节特征提取方法 |
| |
| 引用本文： | 唐庆适,苗夺谦,张红云.基于主曲线的指纹细节特征提取方法[J].计算机科学,2005,32(1):187-189. |
| |
| 作者姓名： | 唐庆适 苗夺谦 张红云 |
| |
| 作者单位： | 同济大学计算机科学与工程系,上海,200092;同济大学计算机科学与工程系,上海,200092;同济大学计算机科学与工程系,上海,200092 |
| |
| 基金项目： | 国家自然科学基金(No.60175016),上海市教委“曙光计划”项目 |
| |
| 摘 要： | 要提高指纹识别的识别率,关键是指纹特征的提取。主曲线是主成份分析的非线性推广,它是通过数据分布“中间’’并满足“自相合”的光滑曲线,较好地反映了数据分布的结构特征。本文尝试使用主曲线这种新的方法来提取指纹的细节特征。实验结果表明利用主曲线来提取指纹的结构特征是可行的,它为指纹特征提取的研究提供了一条新途径。
|
| 关 键 词： | 主曲线 指纹 细节特征 特征提取 |
A Method Based on Principle Curves for Minutiae Extraction in Fingerprint Images |
| |
| TANG Qing-Shi,MIAO Duo-Qian,ZHANG Hong-Yun Dept. of Computer Science and Engineering. Tongji University,Shanghai.A Method Based on Principle Curves for Minutiae Extraction in Fingerprint Images[J].Computer Science,2005,32(1):187-189. |
| |
| Authors: | TANG Qing-Shi MIAO Duo-Qian ZHANG Hong-Yun Dept of Computer Science and Engineering Tongji University Shanghai |
| |
| Affiliation: | TANG Qing-Shi,MIAO Duo-Qian,ZHANG Hong-Yun Dept. of Computer Science and Engineering. Tongji University,Shanghai 200092 |
| |
| Abstract: | The extraction of fingerprint feature is critical to improve the rate of fingerprint recognition. Principal curves are nonlinear generalizations of principal components analysis. They are smooth self-consistent curves that pass through the "middle" of the distribution and they preferably reflect the structural features of the data. In this pa- per, principal curves are used to extract the minutiae of fingerprint. From the result of experiment, it is proved that using principal curves for minutiae extraction is feasible. |
| |
| Keywords: | Principal curve Fingerprint Minutiae Minutiae extraction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
