一种频谱分方向指纹纹线距离估计的新方法  

New method based on directional spectral analysis for fingerprint ridge distance estimation

作　　者：周俊懿[1] 尹义龙[1] 刘捷[1] 陈旭[1] 

机构地区：[1]山东大学计算机科学与技术学院,山东济南250100

出　　处：《计算机工程与设计》2006年第22期4229-4231,4235,共4页Computer Engineering and Design

基　　金：山东省自然科学基金项目(Z2004G05)

摘　　要：纹线距离是指纹的固有本质属性,在自动指纹识别中有着重要的作用。然而目前多数纹线距离估计的方法直接在空域作估计,对低质量指纹图像的处理普遍存在较大误差。为了适应低质量指纹图像,提出了一种基于频谱分析的纹线距离估计的新方法,该方法首先通过快速傅立叶变换将指纹图像变换到频域,然后将频谱图像分成n个方向分别求纹线距离,最后作处理从而得到指纹图像的纹线距离。部分典型指纹图像的实验结果表明,该方法具有较强的有效性和鲁棒性。Ridge distance is an intrinsic texture property of fingerprints and plays an important role in automatic fingerprint identification. But most of the present methods give bad results when the fingerprint image is low quality. For the solution of this problem, a new method based on spectral analysis is presented. Firstly, the fingerprint image data is transformed to the frequency domain via the fast Fourier transform （FFT）, then the spectrum image is divided into n direction, in each direction ridge distance is estimated, the finally fingerprint distance is gained by processing. Tests with some typical images show the good performance of the method.

关 键 词：指纹识别 纹线距离 频谱分析 傅立叶变换 方向频谱分析 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]