基于SIFT特征及改进Gabor滤波器的低质量指纹增强算法  

Enhancement Algorithm Based on SIFT Features and the Improvement of Gabor Filter Low-quality Fingerprint

作　　者：张升斌[1] 李吉成[1] 陈小波[1] 

机构地区：[1]国防科学技术大学,长沙410073

出　　处：《重庆理工大学学报（自然科学）》2013年第2期79-83,共5页Journal of Chongqing University of Technology：Natural Science

摘　　要：针对指纹增强Gabor滤波过程中指纹纹线方向参数取值不够精确、指纹纹线频率参数求取方法效率不高的缺点,对现场低质量残缺指纹处理过程中的实际需求提出改进,在Gabor滤波器前增加SIFT分析,通过在某种程度上抑制噪声来提高Gabor滤波精度,从而有效地实现对低质量残缺指纹的滤波增强。通过一系列理论分析和实验验证了算法的可行性和适用性。Parameter values for the ridge orientation Gabor filtering process are not precise enough. Based on the frequency parameters of the ridge strike and the inefficient method shortcomings, this paper suggests improvements for the actual needs of the incomplete site low-quality fingerprint process, before the Gabor filter to increase the SIFT analysis method of noise suppression to some extent to improve the Gabor filter accuracy, thus obtaining the effective low-quality filtering of incomplete fingerprint enhancement. In this paper, the feasibility and applicability of the algorithm are verified by a series of theoretical analysis and experiments.

关 键 词：SIFT分析 二维Gabor滤波 低质量指纹图像 图像增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]