摘要
针对虹膜特征匹配速度较慢的问题,提出了一种改进的Hamming距离算法来缩短匹配的时间。传统的特征匹配是采用8次移位比对的方式,选择其中最小的一次Hamming距离与阈值进行比较,这种方法会带来计算量的增加,影响实时性。为此提出一种新的方法。在进行特征移位比对的同时,将每次得到的Hamming距离与阈值进行比较,若小于阈值,则结束移位比对,判定这2个虹膜来自同一采集者;若不小于阈值,则继续移位比对,直到移位8次为止。在mini2440开发板上,使用CASIA虹膜数据库对该算法进行了大量的实验。结果表明:该方法比传统的Hamming距离匹配法更快,并且准确率有所提高,说明该方法可行有效。
Aiming at the problem that iris feature matching speed is slow,the research puts forward a kind of improved Hamming distance algorithm to shorten the time of the match.Traditional feature matching is 8 times shift ratio on the way,the study chooses the smallest Hamming distance compared with the threshold value at a time.This approach leads to the increase of the amount of calculation and affects the real-time performance.This paper proposes a new method,in characterizing the shift than at the same time;it will compare the obtained Hamming distance every time with threshold.If the result is less than the threshold,it will determine the two from the same iris template picker,and finish shifting.If not less than the threshold,then it will continue to shift,until the shift 8 times.On the embedded mini 2440 development board,the use of a large number of CASIA iris database iscarried out to verify the algorithm,and the results show that this method is faster than the traditional Hamming distance matching method;besides,the accuracy is improved,which shows that the method is feasible and effective.
作者
张攀
张莲
陈大孝
李云昊
ZHANG Pan ZHANG Lian CHEN Da-xiao LI Yun-hao(College of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, Chin)
出处
《重庆理工大学学报（自然科学）》
CAS
2017年第1期118-123,共6页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金资助项目(61402063)
重庆高校优秀成果转化资助项目(KJZH14213)
