欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
自动指纹分类不仅能够为大型指纹库提供重要的索引机制,而且还能够优化系统运行,提高指纹匹配的效率和性能;由于指纹较大的类内差异和较小的类间差异以及低质量指纹的存在,使得自动指纹分类仍是一项公认的难题;采用指纹连续分布方向图跟踪技术,提出了指纹对称轴的概念及其算法;在此基础上,提出了一种基于方向图跟踪的六类自动指纹分类算法,在FVC2000、FVC2002、FVC2004的Set B、FVC2004的Set A指纹库以及文中所采集的指纹库上的分类结果表明,本算法能有效地将双旋型（Twin Loop）和漩涡型（Whorl）指纹正确分开,实现了六类指纹分类,分类正确率达到95.57%,具有较好的健壮性。
英文摘要：
Automatic fingerprint classification can provide an important indexing mechanism in a fingerprint database.An accurate and consistent classification can greatly reduce fingerprint matching time for large databases.In practice,however,large intraclass and small interclass variations in global pattern configuration and poor quality of fingerprint images make the classification problem very difficult.In this paper,a new concept on the fingerprint core axis and the method to compute it in the fingerprint images are proposed,using the continuously distributed directional image tracing.Then,a novel fingerprint classification algorithm based on the directional image tracing is developed,which classifies input fingerprints into six categories： arch,tented arch,left loop,right loop,twin loop,and whorl.The experimental results obtained on the Set B fingerprint database of FVC2000、FVC2002、FVC2004,the Set A fingerprint database of FVC2004 and our fingerprint database demonstrate that this algorithm is invariant to image rotation of any degrees,and successfully separates the twin loop fingerprint from the whorl fingerprint.For the 4,000 images in our fingerprint database,a classification accuracy of 95.57% for the six-class problem has been achieved.So it has better classification performance than previously reported in the literature.
同期刊论文项目
同项目期刊论文
期刊信息
位置：