摘要
基于带限相位相关的指静脉识别算法通常忽略带限窗口的影响,其识别精度和速度有待提高。为此,提出一种修正的带限相位相关算法。根据指静脉频谱图及其成像特征设计并提取带限和遍历参数,利用相关系数峰值完成图像的匹配识别。在SDU-MLA、THU-FV和NUST-FV 3个指静脉数据库上进行实验,结果表明,该算法的指静脉识别速度和精度得到提高。
The influence of band limited parameters is usually ignored in finger vein recognition algorithm based on the Band Limited Phase Only Correlation(BLPOC) and its recognition accuracy and speed need to be improved.Thus,a novel algorithm using the modified BLPOC is proposed.The band limited and scanning range is determined using the spectrum and the features of finger vein image.Then,the correlation coefficient peak value is used to complete the match of finger vein image.Experiments are based on three finger vein databases,namely,SDU-MLA,THU-FV and NUST-FV,the results show that,the recognition accuracy and speed of the novel algorithm is effectively improved.
作者
雷蕾
席峰
陈胜垚
LEI Lei;XI Feng;CHEN Shengyao(School of Electronic and Optical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)
出处
《计算机工程》
CAS
CSCD
北大核心
2019年第5期187-193,共7页
Computer Engineering
关键词
生物识别
指静脉
带限相位相关
频谱图
识别速度
biometric recognition
finger vein
Band Limited Phase Only Correlation(BLPOC)
spectrum image
recognition speed