摘要
由于单一虹膜特征相对简单,容易引起虹膜识别不准确的问题,本文使用特征加权融合来表示虹膜纹理。提取虹膜纹理的空域特征和频域特证,使用主成分分析法(PCA)降噪去冗余。空域特征采用二分统计局部二值模式(DS-LBP)表示虹膜纹理的灰度值变化规律,形成空域特征码。频域特征采用二维Haar小波提取虹膜纹理的高频系数,形成频域特征码。分别计算两个特征码的汉明(Hamming)距离,并乘以相应的加权权重。通过与设定的分类阈值比较来判定虹膜类别。用多种虹膜库与其他虹膜识别算法进行比较,实验结果表明,本文算法在识别率、等错率、稳定性等方面更具有优势。
The features of single iris are relatively simple,which can easily lead to the inaccurate iris recognition.To solve this problem,the feature weighted fusion is used to represent the iris texture in this paper.First,the iris texture spatial domain features and frequency domain features are extracted using Principal Component Analysis(PCA)to reduce noise and redundancy.Second,Dichotomous Statistical Local Binary Pattern(DSLB)is used to represent variation rule of iris texture gray value,forming spatial domain feature code;and for frequency domain features,2 D-Haar wavelet is used to extract the high frequency coefficients of iris feature and form frequency domain feature code.Third,the Hamming distances of the two feature codes are calculated respectively and multiplied by the corresponding weighted factors.Finally,the iris category is determined by comparison with the setclassification threshold.A variety of iris libraries are used to compare the performance of proposed algorithm with other iris recognition algorithms.Experiment results show that the proposed algorithm has more advantages in recognition rate,equal error rate and stability.
引文
[1]刘元宁,刘帅,朱晓冬,等.基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J].吉林大学学报:工学版,2018,48(5):1606-1613.Liu Yuan-ning,Liu Shuai,Zhu Xiao-dong,et al.Log operator and adaptive optimization Gabor filtering for iris recognition[J].Journal of Jilin University(Engineering and Technology Edition),2018,48(5):1606-1613.
[2]Liu Shuai,Liu Yuan-ning,Zhu Xiao-dong,et al.Gabor filtering and adaptive optimization neural network for iris double recognition[C]∥13th Chinese Conference on Biometric Recognition,Springer,Cham,2018:441-449.
[3]Harada Y,Fujimoto K,Fukuhara M,et al.A minimum Hamming distance search associative memory using neuron CMOS inverters[J].Electronics and Communications in Japan,2017,100(3):10-18.
[4]Huo Guang,Liu Yuan-ning,Zhu Xiao-dong,et al.Secondary iris recognition method based on local energy-orientation feature[J].Journal of Electronic Imaging,2015,24(1):013033.
[5]Lim S,Lee K,Byeon O,et al.Efficient iris recognition through improvement of feature vector and classifier[J].ETRI Journal,2011,23(2):61-70.
[6]He Fei,Han Ye,Wang Han,et al.Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network[J].Journal of Electronic Imaging,2017,26(2):023005.
[7]方强,姚鹏.基于二维正交滤波的虹膜识别算法[J].计算机科学,2015,42(5):281-285.Fang Qiang,Yao Peng.Reliable iris recognition using 2Dquadrature filters[J].Computer Science,2015,42(5):281-285.
[8]苑玮琦,朱立军.基于线性模板和模糊规则的虹膜坑洞纹理检测[J].仪器仪表学报,2015,34(6):1363-1371.Yuan Wei-qi,Zhu Li-jun.Iris crypt texture detection based on linear template and fuzzy rules[J].Chinese Journal of Scientific Instrument,2015,34(6):1363-1371.
[9]Zhang B,Yuan W.Iris Cracks Detection Method Based on Minimum Local Gray Value and Dilating Window of Regional Mean Gray Value[J].Optimization Letters,2012,6(5):927-940.
[10]Shen F,Flynn P J.Are iris crypts useful in identity recognition?[C]∥IEEE 6th International Conference on Biometrics:Theory,Applications and Systems,United States,2013.
[11]董宏兴.基于自适应Gabor滤波的虹膜特征提取与识别方法研究[D].长春:吉林大学计算机科学与技术学院,2016.Dong Hong-xing.Research on iris feature extraction and recognition based on the adaptive Gabor filtering[D].Changchun:College of Computer Science and Technology,Jilin University,2016.
[12]刘帅,刘元宁,朱晓冬,等.蚁群变异粒子群优化的2次虹膜识别[J].计算机辅助设计与图形学学报,2018,30(9):1604-1614.Liu Shuai,Liu Yuan-ning,Zhu Xiao-dong,et al.Ant colony mutation particle swarm optimization for secondary iris recognition[J].Journal of Computer Aided Design and Computer Graphics,2018,30(9):1604-1614.
[13]李星光,孙哲南,谭铁牛.虹膜图像质量评价综述[J].中国图象图形学报,2014,19(6):813-824.Li Xing-guang,Sun Zhe-nan,Tan Tie-niu.Overview of iris image quality-assessment[J].Journal of Image and Graphics,2014,19(6):813-824.
[14]Huo Guang,Liu Yuan-ning,Zhu Xiao-dong,et al.Face-iris multimodal biometric scheme based on feature level fusion[J].Journal of Electronic Imaging,2015,24(6):063020.
[15]周汐,曹林.分块LBP的素描人脸识别[J].中国图象图形学报,2015,20(1):50-58.Zhou Xi,Cao Lin.The sketch face recognition combining with AdaBoost and blocking LBP[J].Journal of Image and Graphics,2015,20(1):50-58.
[16]孙冬,周俊,魏勇.基于Haar小波的虹膜特征提取算法[J].科学技术与工程,2014,14(1):81-85.Sun Dong,Zhou Jun,Wei Yong.Iris feature extraction based on Haar wavelet[J].Science Technology and Engineering,2014,14(1):81-85.
[17]Liu Yuan-ning,He Fei,Zhu Xiao-dong,et al.The improved characteristics of bionic Gabor representations by combining with SIFT key-points for iris recognition[J].Journal of Bionic Engineering,2015,12(3):504-517.
[18]赵天明.虹膜特征提取方法研究[D].长春:吉林大学计算机科学与技术学院,2016.Zhao Tian-ming.Research on iris feature extraction[D].Changchun:College of Computer Science and Technology,Jilin University,2016.
[19]李欢利,郭立红,李小明,等.基于统计特征中心对称局部二值模式的虹膜识别[J].光学精密工程,2013,21(8):2129-2136.Li Huan-li,Guo Li-hong,Li Xiao-ming,et al.Iris recognition based on SCCS-LBP[J].Optics and Precision Engineering,2013,21(8):2129-2136.
[20]苑玮琦,朱立军,张波.基于形态学与支持向量机的虹膜坑洞纹理检测[J].仪器仪表学报,2017,38(3):664-671.Yuan Wei-qi,Zhu Li-jun,Zhang Bo.Iris crypt texture detection based on morphology and SVM[J].Chinese Journal of Scientific Instrument,2017,38(3):664-671.
[21]Dong Hong-xing,Zhu Xiao-dong,Liu Yuan-ning,et al.Iris recognition based on CPSO algorithm for optimizing multichannel gabor parameters[J].Journal of Computational Information Systems,2015,11(1):333-340.
[22]Yu Zhi-wen,Li Le,Liu Ji-ming,et al.Hybrid adaptive classifier ensemble[J].IEEE Transactions on Cybernetics,2015,45(2):177-190.
[23]Yu Zhi-wen,Chen Han-tao,You Jane,et al.Hybrid K nearest neighbor classifier[J].IEEE Transactions on Cybernetics,2016,46(6):1263-1275.