一种基于非线性扩散方程的指纹预处理方法  

Fingerprint Preprocessing Method Based on Nonlinear Diffusion Equation

作　　者：朱菊华[1] 杨新[1] 杜啸晓[1] 陈勇[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200030

出　　处：《数据采集与处理》2001年第2期139-144,共6页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金 (编号 :6 9931 0 1 0 )

摘　　要：目前用于实时比对的活体指纹 ,由于受指纹采集设备的限制 ,图像中常混有噪声 ,必须经过预处理才能进行可靠的比对。本文根据指纹纹理密集的特点 ,采用改进的基于梯度算子的解非线性扩散方程的算法 ,克服了退化扩散方程对大曲率边缘点的模糊效应 ,兼顾了降噪和保边界这一平滑降噪中矛盾的两个方面。对比几种常用的平滑降噪的预处理算法 ,实验结果证明 ,本文的改进算法对于带噪指纹图像的预处理 ,优于其他几种对比算法。It is necessary for the real time acquired fingerprint to be preprocessed before matching due to the acquiring equipment which results in noisy fingerprint images. Considering the feature of fingerprint, i.e. the concentrated texture, we employ an improved smoothing algorithm based on a nonlinear diffusion equation. This method, to some extent, is effective for both smoothing and edge preserving, mainly because it prevents the blurring effect of degenerate diffusion equation for the points with big gray level variations. Compared with other methods, this algorithm has better performance for preprocessing of noisy fingerprint images.

关 键 词：偏微分方程 图像平滑 非线性扩散方程 指纹预处理 

分 类 号：TN911.73[电子电信—通信与信息系统] D918.91[电子电信—信息与通信工程]