[1]王闪闪,巩长庆,秦华锋,等.基于深度学习的K近邻图迭代静脉识别算法研究[J].智能系统学报,2024,19(5):1149-1156.[doi:10.11992/tis.202307009]
WANG Shanshan,GONG Changqing,QIN Huafeng,et al.Vein recognition algorithm combining K-nearest neighbor and graph iterative based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19(5):1149-1156.[doi:10.11992/tis.202307009]
点击复制
WANG Shanshan,GONG Changqing,QIN Huafeng,et al.Vein recognition algorithm combining K-nearest neighbor and graph iterative based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19(5):1149-1156.[doi:10.11992/tis.202307009]
基于深度学习的K近邻图迭代静脉识别算法研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1149-1156
栏目:
学术论文—机器感知与模式识别
出版日期:
2024-09-05
- Title:
- Vein recognition algorithm combining K-nearest neighbor and graph iterative based on deep learning
- Keywords:
- biometric recognition; palm vein recognition; image processing; deep learning; KNN algorithm; convolutional neural network; graph iterative algorithm; graph neural network
- 分类号:
- TP391.4
- 文献标志码:
- 2024-08-28
- 摘要:
- 深度学习在计算机视觉中具有强大的特征表达能力，近年来广泛应用于静脉特征的提取与识别。通常，基于深度学习的静脉识别模型在训练阶段，每次仅输入1幅图像及其对应的标签，学习图像与标签之间的映射关系，然而，这种每次只处理单幅图像的方法，难以捕捉不同类别多幅静脉图像之间的关系。为了解决该问题，提出一种基于深度学习的K近邻图迭代静脉识别算法。用较优的深度学习模型提取掌静脉图像特征；利用K近邻算法通过特征距离在训练集中选出最近的K幅图像及其标签，通过这些特征向量生成标签传播矩阵和标签矩阵；利用图迭代算法预测待分类图像的标签，完成分类。在香港理工大学和同济大学提供的掌静脉数据集上进行实验，最高识别精度分别为99.67%和92.72%。
- Abstract:
- In recent years, deep learning has been widely applied in the extraction and recognition of vein features due to its excellent performance in computer vision. Usually, vein recognition models based on deep learning learn the mapping between a single input image and its label. This approach barely captures the connections between multiple vein images from different categories. To solve this problem, this study introduces a deep learning-based K-nearest neighbor iterative vein recognition algorithm. First, the algorithm extracts features from palm vein images by using advanced deep learning models. Then, it calculates the distances between an image to be classified and training images by using the K-nearest neighbor algorithm, which determines the K most similar images and their labels. A label propagation matrix and a label matrix are created from these feature vectors. Finally, a graph iteration algorithm is used to predict the classifications. Tests are conducted on palm vein datasets provided by Hong Kong Polytechnic University and Tongji University. Recognition accuracies of 99.67% and 92.72% are obtained for the two datasets, respectively.
- 参考文献/References:
-
[1] 谭振林, 刘子良, 黄蔼权, 等. 掌静脉识别的深度学习方法综述[J]. 计算机工程与应用, 2024, 60(6): 55-67.
TAN Zhenlin, LIU Ziliang, HUANG Aiquan, et al. Review of deep learning methods for palm vein recognition[J]. Computer engineering and applications, 2024, 60(6): 55-67.
[2] 赵程, 马彦波, 景荣, 等. 基于面部识别和掌静脉识别的AFC支付技术研究[J]. 智能城市, 2023, 9(5): 13-17.
ZHAO Cheng, MA Yanbo, JING Rong, et al. Research on AFC payment technology based on facial recognition and palmar vein recognition[J]. Intelligent city, 2023, 9(5): 13-17.
[3] WU Zhendong, TIAN Longwei, LI Ping, et al. Generating stable biometric keys for flexible cloud computing authentication using finger vein[J]. Information sciences, 2018, 433: 431-447.
[4] KONO M. A new method for the identification of individuals by using of vein pattern matching of a finger[C]//Proc Fifth Symposium on Pattern Measurement. Yamaguchi: CiNii, 2000: 9-12.
[5] 刘伟业, 鲁慧民, 李玉鹏, 等. 指静脉识别技术研究综述[J]. 计算机科学, 2022, 49(S1): 1-11.
LIU Weiye, LU Huimin, LI Yupeng, et al. Survey on finger vein recognition research[J]. Computer science, 2022, 49(S1): 1-11.
[6] QIN Huafeng, LAN Qin, YU Chengbo. Region growth–based feature extraction method for finger-vein recognition[J]. Optical engineering, 2011, 50(5): 057208.
[7] SONG W, KIM T, KIM H C, et al. A finger-vein verification system using mean curvature[J]. Pattern recognition letters, 2011, 32(11): 1541-1547.
[8] MIURA N, NAGASAKA A, MIYATAKE T. Extraction of finger-vein patterns using maximum curvature points in image profiles[J]. IEICE - transactions on information and systems, 2007, E90-D(8): 1185-1194.
[9] QIU Xinwei, KANG Wenxiong, TIAN Senping, et al. Finger vein presentation attack detection using total variation decomposition[J]. IEEE transactions on information forensics and security, 2018, 13(2): 465-477.
[10] 杨如民, 许琳英, 余成波. 基于Hessian矩阵和Gabor滤波的手指静脉特征提取[J]. 兵器装备工程学报, 2019, 40(3): 103-107, 111.
YANG Rumin, XU Linying, YU Chengbo. Finger vein feature extraction based on Hessian matrix and Gabor filtering[J]. Journal of ordnance equipment engineering, 2019, 40(3): 103-107, 111.
[11] LEE E C, LEE H C, PARK K R. Finger vein recognition using minutia-based alignment and local binary pattern-based feature extraction[J]. International journal of imaging systems and technology, 2009, 19(3): 179-186.
[12] GU Gaojie, BAI Peirui, LI Hui, et al. Dorsal hand vein recognition based on transfer learning with fusion of LBP feature[C]//Biometric Recognition. Cham: Springer, 2021: 221-230.
[13] QIN Huafeng, EL YACOUBI M A, LIN Jihai, et al. An iterative deep neural network for hand-vein verification[J]. IEEE access, 2019, 7: 34823-34837.
[14] 胡娜, 马慧, 湛涛. 融合LBP纹理特征与B2DPCA技术的手指静脉识别方法[J]. 智能系统学报, 2019, 14(3): 533-540.
HU Na, MA Hui, ZHAN Tao. Finger vein recognition method combining LBP texture feature and B2DPCA technology[J]. CAAI transactions on intelligent systems, 2019, 14(3): 533-540.
[15] HOU Borui, YAN Ruqiang. ArcVein-arccosine center loss for finger vein verification[J]. IEEE transactions on instrumentation and measurement, 2021, 70: 5007411.
[16] YANG Wenming, HUI Changqing, CHEN Zhiquan, et al. FV-GAN: finger vein representation using generative adversarial networks[J]. IEEE transactions on information forensics and security, 2019, 14(9): 2512-2524.
[17] WANG Wenhai, XIE Enze, LI Xiang, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 548-558.
[18] KHANDELWAL U, LEVY O, JURAFSKY D, et al. Generalization through memorization: nearest neighbor language models[EB/OL]. (2019-11-01)[2023-07-12]. https://arxiv.org/abs/1911.00172.
[19] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[20] QIN Huafeng, EL-YACOUBI M A, LI Yantao, et al. Multi-scale and multi-direction GAN for CNN-based single palm-vein identification[J]. IEEE transactions on information forensics and security, 2021, 16: 2652-2666.
[21] YANG Weili, LUO Wei, KANG Wenxiong, et al. FVRAS-net: an embedded finger-vein recognition and AntiSpoofing system using a unified CNN[J]. IEEE transactions on instrumentation and measurement, 2020, 69(11): 8690-8701.
[22] 袁臣虎, 刘铁根, 李秀艳. 基于kNN-SVM的手背静脉虹膜和指纹融合身份识别[J]. 光电工程, 2013, 40(4): 101-105.
YUAN Chenhu, LIU Tiegen, LI Xiuyan. Identification algorithm for fusion of hand vein iris and fingerprint based on kNN-SVM[J]. Opto-electronic engineering, 2013, 40(4): 101-105.
[23] 刘辉玲, 陶洁, 邱磊. 基于Python的One-hot编码的实现[J]. 武汉船舶职业技术学院学报, 2021, 20(3): 136-139.
LIU Huiling, TAO Jie, QIU Lei. Implementation of one-hot encoding based on python[J]. Journal of Wuhan Institute of Shipbuilding Technology, 2021, 20(3): 136-139.
[24] ZHANG Lin, CHENG Zaixi, SHEN Ying, et al. Palmprint and palmvein recognition based on DCNN and a new large-scale contactless palmvein dataset[J]. Symmetry, 2018, 10(4): 78.
[25] SHEN Jiaquan, LIU Ningzhong, XU Chenglu, et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 1-13.
[26] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132–7141.
- 相似文献/References:
-
[1]颜廷秦,周昌雄.二维EMD分解提高PCA掌纹识别率[J].智能系统学报,2013,8(4):377.[doi:10.3969/j.issn.1673-4785.201211002]
YAN Tingqin,ZHOU Changxiong.The research of improving PCA recognition rate of palmprints with BEMD[J].CAAI Transactions on Intelligent Systems,2013,8():377.[doi:10.3969/j.issn.1673-4785.201211002]
[2]陈阳,覃鸿,李卫军,等.仿生模式识别技术研究与应用进展[J].智能系统学报,2016,11(1):1.[doi:10.11992/tis.201506011]
CHEN Yang,QIN Hong,LI Weijun,et al.Progress in research and application of biomimetic pattern recognition technology[J].CAAI Transactions on Intelligent Systems,2016,11():1.[doi:10.11992/tis.201506011]
[3]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[4]潘在宇,徐家梦,王军,等.基于模态信息度评估策略的掌纹掌静脉特征识别方法[J].智能系统学报,2024,19(5):1136.[doi:10.11992/tis.202310002]
PAN Zaiyu,XU Jiameng,WANG Jun,et al.Palmprint and palm vein recognition method based on modal information evaluation strategy[J].CAAI Transactions on Intelligent Systems,2024,19():1136.[doi:10.11992/tis.202310002]
[5]金怡凡,王海涛,贾伟.使用掌纹线对基于深度学习的掌纹识别进行数据增强[J].智能系统学报,2024,19(5):1178.[doi:10.11992/tis.202308026]
JIN Yifan,WANG Haitao,JIA Wei.Using palmprint lines for data enhancement of palmprint recognition based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19():1178.[doi:10.11992/tis.202308026]
[6]林孙旗,徐家梦,郑瑜杰,等.面向掌纹掌静脉识别网络轻量化的非对称双模态融合方法[J].智能系统学报,2024,19(5):1190.[doi:10.11992/tis.202212031]
LIN Sunqi,XU Jiameng,ZHENG Yujie,et al.An asymmetric bimodal fusion method for lightweight palm print and palm vein recognition network[J].CAAI Transactions on Intelligent Systems,2024,19():1190.[doi:10.11992/tis.202212031]
备注/Memo
收稿日期:2023-7-12。
基金项目:国家自然科学基金项目(61976030)；重庆市高校创新研究群体项目(CXQT21034)；河南省科技厅科技攻关项目(222102210301)；重庆市研究生科研创新项目(CYS23565).
作者简介:王闪闪，硕士研究生，主要研究方向为生物特征识别。E-mail：wangshanexpression@163.com;巩长庆，硕士研究生，主要研究方向为生物特征识别。E-mail：gongchangqing@ctbu.edu.cn;秦华锋，教授，主要研究方向为生物特征识别、大数据的分析与处理。主持国家自然科学基金项目、重庆市青年人才培养项目等10余项，授权发明专利10余项。发表学术论文40余篇。E-mail：qinhaufengfeng@163.com。
通讯作者:秦华锋. E-mail：qinhaufengfeng@163.com
更新日期/Last Update:
2024-09-05