改进的指纹自适应阈值分割算法  

Improved adaptive threshold algorithm for segmentation of fingerprint images

作　　者：张德刚[1] 戴冠中[1] 刘航[1] 郝兴茂[1] 李美峰[1] 

机构地区：[1]西北工业大学自动化学院,西安710072

出　　处：《计算机应用研究》2008年第6期1739-1740,1749,共3页Application Research of Computers

基　　金：国防基础研究项目(C2720061361)

摘　　要：在传统的自适应阈值分割算法的基础上,提出了一种改进的指纹图像分割算法。该算法根据指纹与背景交接区域,以及指纹内部脊线太淡或脊线粘连的区域中图像的灰度统计特性,对此类区域采取逐点分割,从而以较低的计算代价消除了指纹图像分割后前景区域的边界方块效应。实验表明,该算法具有较高的鲁棒性,对指纹的分割更加灵活准确,分割后的指纹前景边界也更加平滑细致。Based on the traditional adaptive threshold algorithm for segmentation of fingerprint images,this paper proposed an improved segmentation algorithm.According to either local gray-level-statistics of the junction regions between fingerprint and background,or regions with light or conglutinated ridges,the algorithm was capable of eliminating the blocking effect of the foreground image edges at a low computational cost.The experimental result demonstrates that the segmentation algorithm proposed is effective and robust to the pre-process of the fingerprint images.

关 键 词：指纹 阈值 图像分割 灰度特性 块效应 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]