| 基于贝叶斯最小错误率的一种新的指纹分割算法 |
| |
| 引用本文： | 沈虹,汪剑鸣,苗长云.基于贝叶斯最小错误率的一种新的指纹分割算法[J].微计算机信息,2006,22(1):208-210. |
| |
| 作者姓名： | 沈虹 汪剑鸣 苗长云 |
| |
| 作者单位： | 300160,天津工业大学信息与通信工程学院 |
| |
| 基金项目： | 天津市科委资助项目;天津市高等学校科技发展基金 |
| |
| 摘 要： | 指纹图像分割是自动指纹识别系统中非常重要的一步。本文介绍了一种新的基于贝叶斯最小错误率的指纹分割方法。首先,提出了一种新的基于方向信息的分割特征。然后,具体介绍了基于这种特征的分割算法。最后根据最小错误率的贝叶斯决策确定合适的阈值割除背景区域。这种方法在FVC2000指纹库中进行了测试,实验结果证明了它的有效性。
|
| 关 键 词： | 指纹分割 指纹识别 贝叶斯决策 特征选取 |
| 文章编号： | 1008-0570(2006)01-1-0208-03 |
| 修稿时间： | 2005年6月16日 |
A new fingerprint segmentation algorithm based on the Bayes minimum error probability |
| |
| Shen,Hong,Wang,Jianming,Miao,Changyun.A new fingerprint segmentation algorithm based on the Bayes minimum error probability[J].Control & Automation,2006,22(1):208-210. |
| |
| Authors: | Shen Hong Wang Jianming Miao Changyun |
| |
| Abstract: | Fingerprint image segmentation is a very important step in the automated fingerprint identification system. This paper introduce a new approach to fingerprint segmentation based on the Bayes minimum error probability. First, present a new segmentation feature based on the direction imformation. Then, based on the new feature, introduce the segmentation algorithm detailed. Finally, an adaptive threshold is applied to determine the block of interest by the Bayes minimum error probability policy decision. This method is tested on the FVC2000 database and the experimental results have proven its efficiency. |
| |
| Keywords: | fingerprint segmentation fingerprint recognition Bayes policy decision feature selection |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
