传统的基于脊线细化的检测方法,耗时长、伪节点多.针对这一缺陷,本文提出了一种基于差分码的细节特征点提取方法.首先跟踪脊线边缘得到差分码,再利用不同的边界特征各自对应有独特的差分码段这一特点检测转弯点,这些点就是指纹细节点位置.实验将本文方法跟三种不同的方法进行对比,结果表明,本文的方法在检测速度和检测精度方面总体上有所提高.
An algorithm for extracting minutiae based on differential code is proposed to overcome the defects of time-consuming and getting many spurious minutiae of traditional ways based on ridge thinning.At the beginning,differential code is got by tracing ridge boundary;subsequently,the turning points are detected,as the differential code is of special characteristic for different boundary features,and the detected points are the locations of the fingerprint minutiae.Three different methods are compared with the proposed approach.The results show a global improvement in detection efficiency and accuracy.