摘要
针对指纹数据库规模不断增大的情况,为了提高指纹识别的速度和准确度,采用BP神经网络先对指纹进行分类,把指纹分成左环、右环、拱、涡、棚状拱和不辨型6种类型,然后在相应的子类库中根据特征提取进行识别。设计并实现了一个指纹识别系统,该系统能够自动地进行指纹分类,而且还能实时地将结果与指纹数据库进行比对。实验结果表明,该系统能迅速地获得被识别人员的身份信息。
In view of the increase of fingerprint database size, this paper adopts BP neural network to classify the fingerprint in order to enhance the speed and precision of recognition. As a result, the fingerprint is sorted into six types： left loop, right loop, arch, whorl, tented, and unidentified. Thus fingerprint is recognized according to the extracted feature among certain type. In the experiment, a system of fingerprint recognition is designed and implemented. This system is able to sort the fingerprint automatically, and then compare it with those in certain database, and in the end the identity information can be obtained quickly.
出处
《重庆理工大学学报（自然科学）》
CAS
2010年第1期47-50,共4页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金与中国民用航空总局联合资助项目(60776816)
广东省自然科学基金重点资助项目(8251064101000005)
广东省科技攻关项目(2007B0604017)
关键词
BP网络
指纹分类
特征提取
BP neural network
fingerprint classification
feature extraction
