[1]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):1136-1148.[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(5):1136-1148.[doi:10.11992/tis.202310002]
点击复制
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(5):1136-1148.[doi:10.11992/tis.202310002]
基于模态信息度评估策略的掌纹掌静脉特征识别方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1136-1148
栏目:
学术论文—机器感知与模式识别
出版日期:
2024-09-05
- Title:
- Palmprint and palm vein recognition method based on modal information evaluation strategy
- Keywords:
- biometric recognition; palmprint image; palmvein image; multimodal biometric databases; modal information evaluation strategy; category confidence level; multimodal fusion; palmprint and palmvein fusion recognition
- 分类号:
- TP30
- 文献标志码:
- 2024-08-29
- 摘要:
- 多模态生物特征识别技术凭借其出色的识别效果和稳健的可靠性引起了业界的广泛关注。然而，传统多模态生物特征识别方法通常直接在特征层或决策层进行融合，很少考虑模态样本质量不同导致的融合效果差异。此外，由于缺乏大规模公开多模态生物特征数据库，多模态生物特征识别方法的研究受到一定程度上的限制。因此，设计了一款手部多模态数据采集设备，并自建了手部多模态数据库，用于多模态生物特征识别方法的验证与评估；提出了一种基于模态信息度评估策略的掌纹掌静脉特征识别方法，利用样本标签对应的类别置信度来评估每个模态特征的信息度，从而使模型在融合过程中根据不同模态对身份识别的贡献率进行自适应的权重分配。实验表明该方法在2个公开的数据库以及自建数据库上均取得了最高识别率。
- Abstract:
- Multimodal biometric recognition has gained widespread attention in the industry due to its excellent performance and robust reliability. However, traditional multimodal biometric recognition methods usually fuse directly at the feature or matching layer and rarely consider the differences in fusion effects caused by the quality of modal samples. Moreover, research on multimodal biometric recognition methods is restricted by the absence of large-scale publicly available multimodal biometric databases. Therefore, first, a hand multimodal data acquisition device is designed, and a hand multimodal database is created for the validation and evaluation of multimodal biometric recognition methods. Second, a palmprint and palm vein fusion recognition method is proposed based on a modal information evaluation strategy. It uses the category confidence level corresponding to ground truth sample labels to assess the information level of each modal feature. Thus, the model adaptively assigns weights according to the contribution rates of different modes during the identity recognition fusion process. This method outperforms other recognition methods by achieving the highest recognition rate on two public databases and one self-built multimodal biometric database.
- 参考文献/References:
-
[1] HUANG Zhe, GUO Chengan. Toward cross-dataset finger vein recognition with single-source data[J]. IEEE transactions on instrumentation and measurement, 2024, 73: 2506012.
[2] PAN Zaiyu, WANG Jun, WANG Guoqing, et al. Multi-scale deep representation aggregation for vein recognition[J]. IEEE transactions on information forensics and security, 2020, 16: 1-15.
[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): 279-286.
MA Xiao, ZHANG Fandong, FENG Jufu. Sparse representation via deep learning features based face recognition method[J]. CAAI transactions on intelligent systems, 2016, 11(3): 279-286.
[4] GUO Xinxin, PENG Jianfeng. Optimization design and implementation of web fingerprint identification[C]//2023 IEEE 12th International Conference on Communication Systems and Network Technologies. Bhopal: IEEE, 2023: 569-573.
[5] 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): 377-380.
YAN Tingqin, ZHOU Changxiong. The research of improving PCA recognition rate of palmprints with BEMD[J]. CAAI transactions on intelligent systems, 2013, 8(4): 377-380.
[6] CHEN Liukui, WANG Xiaoxing, JIANG Haiyang, et al. Design of palm vein platform and pattern enhancement model based on Raspberry Pi[C]//2021 IEEE International Conference on Emergency Science and Information Technology. Chongqing: IEEE, 2021: 495-498.
[7] PAN Zaiyu, WANG Jun, SHEN Zhengwen, et al. Disentangled representation and enhancement network for vein recognition[J]. IEEE transactions on circuits and systems for video technology, 2023, 33(8): 4164-4176.
[8] JANI R, AGRAWAL N. A proposed framework for enhancing security in fingerprint and finger-vein multimodal biometric recognition[C]//2013 International Conference on Machine Intelligence and Research Advancement. Katra: IEEE, 2013: 440-444.
[9] 周晨怡, 黄靖, 杨丰, 等. 利用特征距离信息引导决策融合的多模态生物特征识别方法[J]. 科学技术与工程, 2020, 20(10): 4036-4042.
ZHOU Chenyi, HUANG Jing, YANG Feng, et al. Multimodal biometric recognition on decision-level fusion guided by feature distance information[J]. Science technology and engineering, 2020, 20(10): 4036-4042.
[10] KABIR W, AHMAD M O, SWAMY M N S. A two-stage scheme for fusion of hash-encoded features in a multimodal biometric system[C]//2018 16th IEEE International New Circuits and Systems Conference. Montreal: IEEE, 2018: 340-343.
[11] KANG Wenxiong, LU Yuting, LI Dejian, et al. From noise to feature: exploiting intensity distribution as a novel soft biometric trait for finger vein recognition[J]. IEEE transactions on information forensics and security, 2019, 14(4): 858-869.
[12] ZHAO Pengyang, ZHAO Shuping, XUE Jinghao, et al. The neglected background cues can facilitate finger vein recognition[J]. Pattern recognition, 2023, 136: 109199.
[13] 王志强. 基于图像质量评价的掌纹识别算法研究[D]. 北京: 北京交通大学, 2016: 2-67.
WANG Zhiqiang. Research on palmprint recognition algorithm based on image quality evaluation[D]. Beijing: Beijing Jiaotong University, 2016: 2-67.
[14] 李苋兰, 张顶, 黄晞. 基于BP-AdaBoost神经网络的多参数掌静脉图像质量评价法[J]. 计算机系统应用, 2020, 29(3): 20-28.
LI Xianlan, ZHANG Ding, HUANG Xi. Multi-parameter palm vein image quality evaluation method based on BP-AdaBoost neural network[J]. Computer systems & applications, 2020, 29(3): 20-28.
[15] LI Shuyi, ZHANG B. Joint discriminative sparse coding for robust hand-based multimodal recognition[J]. IEEE transactions on information forensics and security, 2021, 16: 3186-3198.
[16] SINGH M, SINGH R, ROSS A. A comprehensive overview of biometric fusion[J]. Information fusion, 2019, 52: 187-205.
[17] 钟德星, 朱劲松, 杜学峰. 掌纹识别研究进展综述[J]. 模式识别与人工智能, 2019, 32(5): 436-445.
ZHONG Dexing, ZHU Jinsong, DU Xuefeng. Progress of palmprint recognition: a review[J]. Pattern recognition and artificial intelligence, 2019, 32(5): 436-445.
[18] MATSUMOTO K. Palm-recognition systems: an ideal means of restricting access to high-security areas[J]. Mitsubishi electric advance, 1985, 31: 31-32.
[19] WANG Xiyu, LI Hengjian, YU Changzhi, et al. An improved palmprint image recognition algorithm via image restoration[C]//2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. Xi’an: IEEE, 2018: 2687-2691.
[20] YANG Dongliang, SONG C, GAO F, et al. A 3D palm-print recognition method based on local sparse representation and weighted shape index feature[C]//2019 Chinese Automation Congress. Hangzhou: IEEE, 2019: 4537-4540.
[21] P?V?LOI I, IGNAT A, LAZ?R L C, et al. Palmprint recognition with fixed number of SURF keypoints[C]//2021 International Conference on e-Health and Bioengineering. Iasi: IEEE, 2021: 1-4.
[22] LIU Dian, SUN Dongmei. Contactless palmprint recognition based on convolutional neural network[C]//2016 IEEE 13th International Conference on Signal Processing. Chengdu: IEEE, 2016: 1363-1367.
[23] ZHONG Dexing, YANG Yuan, DU Xuefeng. Palmprint recognition using Siamese network[C]//Biometric Recognition. Cham: Springer, 2018: 48-55.
[24] WANG Gengxing, KANG Wenxiong, WU Qiuxia, et al. Generative adversarial network (GAN) based data augmentation for palmprint recognition[C]//2018 Digital Image Computing: Techniques and Applications. Canberra: IEEE, 2018: 1-7.
[25] SHAO Huikai, ZHONG Dexing, DU Xuefeng. Deep distillation hashing for unconstrained palmprint recognition[J]. IEEE transactions on instrumentation and measurement, 2021, 70: 2505613.
[26] Shimizu K. Optical trans-body imaging-Feasibility of optical CT and functional imaging of living body[J]. Medicinal philosophica, 1992, 11: 620-629.
[27] WANG Jiaqiang, YU Ming, QU Hanbing, et al. Analysis of palm vein image quality and recognition with different distance[C]//2013 Fourth International Conference on Digital Manufacturing & Automation. Shinan: IEEE, 2013: 215-218.
[28] SUN Saisai, CONG Xiaoyan, ZHANG Ping, et al. Palm vein recognition based on NPE and KELM[J]. IEEE access, 2021, 9: 71778-71783.
[29] 袁丽莎. 基于深度学习的手掌静脉识别[D]. 广州: 南方医科大学, 2019: 55-88.
YUAN Lisha. Palm vein recognition based on deep learning[D]. Guangzhou: Southern Medical University, 2019: 55-88.
[30] JIA Wei, GAO Jiao, XIA Wei, et al. A performance evaluation of classic convolutional neural networks for 2D and 3D palmprint and palm vein recognition[J]. International journal of automation and computing, 2021, 18(1): 18-44.
[31] DU Dongyang, LU Lijun, FU Ruiyang, et al. Palm vein recognition based on end-to-end convolutional neural network[J]. Journal of southern medical university, 2019, 39(2): 207-214.
[32] WANG Guoqing, SUN Changming, SOWMYA A. Learning a compact vein discrimination model with GANerated samples[J]. IEEE transactions on information forensics and security, 2020, 15: 635-650.
[33] ZHANG D, GUO Zhenhua, LU Guangming, et al. Online joint palmprint and palmvein verification[J]. Expert systems with applications, 2011, 38(3): 2621-2631.
[34] LUO Nan, GUO Zhenhua, WU Gang, et al. Joint palmprint and palmvein verification by Dual Competitive Coding[C]//2011 3rd International Conference on Advanced Computer Control. Harbin: IEEE, 2011: 538-542.
[35] 许学斌, 邢潇敏, 安美娟, 等. 基于多光谱图像融合的掌纹识别方法[J]. 光谱学与光谱分析, 2022, 42(11): 3615-3625.
XU Xuebin, XING Xiaomin, AN Meijuan, et al. Palmprint recognition method based on multispectral image fusion[J]. Spectroscopy and spectral analysis, 2022, 42(11): 3615-3625.
[36] 李俊林, 王华彬, 陶亮. 单幅近红外手掌图像掌静脉和掌纹多特征识别[J]. 计算机工程与应用, 2018, 54(9): 156-164,236.
LI Junlin, WANG Huabin, TAO Liang. Palm vein and palmprint fusion recognition with those two features existing in same near-infrared palm image[J]. Computer engineering and applications, 2018, 54(9): 156-164,236.
[37] WU Tengfei, LENG Lu, KHAN M K, et al. Palmprint-palmvein fusion recognition based on deep hashing network[J]. IEEE access, 2021, 9: 135816-135827.
[38] ZHANG D, KONG W K, YOU J, et al. Online palmprint identification[J]. IEEE transactions on pattern analysis and machine intelligence, 2003, 25(9): 1041-1050.
[39] ZHANG D, GUO Zhenhua, LU Guangming, et al. An online system of multispectral palmprint verification[J]. IEEE transactions on instrumentation and measurement, 2010, 59(2): 480-490.
[40] JIA Wei, ZHANG B, LU Jingting, et al. Palmprint recognition based on complete direction representation[J]. IEEE transactions on image processing, 2017, 26(9): 4483-4498.
[41] JIA Wei, HU Rongxiang, GUI Jie, et al. Palmprint recognition across different devices[J]. Sensors, 2012, 12(6): 7938-7964.
[42] ZHANG Lin, LI Lida, YANG Anqi, et al. Towards contactless palmprint recognition: a novel device, a new benchmark, and a collaborative representation based identification approach[J]. Pattern recognition, 2017, 69: 199-212.
[43] SUN Zhenan, TAN Tieniu, WANG Yunhong, et al. Ordinal palmprint represention for personal identification [represention read representation][C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 279-284
[44] KABACI?SKI R, KOWALSKI M. Vein pattern database and benchmark results[J]. Electronics letters, 2011, 47(20): 1127.
[45] TOME P, MARCEL S. On the vulnerability of palm vein recognition to spoofing attacks[C]//2015 International Conference on Biometrics. Phuket: IEEE, 2015: 319-325.
[46] 吕佩卓, 赖声礼, 陈佳阳, 等. 一种自适应的手背静脉区域定位算法[J]. 微计算机信息, 2008, 24(4): 208-209, 296.
LYU Peizhuo, LAI Shengli, CHEN Jiayang, et al. An adaptive locating algorithm of palm-dorsal vein image[J]. Microcomputer information, 2008, 24(4): 208-209, 296.
[47] MIURA N, NAGASAKA A, MIYATAKE T. Feature extraction of finger vein patterns based on iterative line tracking and its application to personal identification[J]. Systems and computers in Japan, 2004, 35(7): 61-71.
[48] 尚丽, 苏品刚, 淮文军. 一种新的掌纹ROI图像定位方法[J]. 激光与红外, 2012, 42(7): 815-820.
SHANG Li, SU Pingang, HUAI Wenjun. New location method of palmprint ROI images[J]. Laser & infrared, 2012, 42(7): 815-820.
[49] REN Hengyi, SUN Lijuan, GUO Jian, et al. A dataset and benchmark for multimodal biometric recognition based on fingerprint and finger vein[J]. IEEE transactions on information forensics and security, 2022, 17: 2030-2043.
[50] GUO Jian, TU Jiaxiang, HENGYI REN, et al. Finger multimodal feature fusion and recognition based on channel spatial attention[EB/OL]. (2022-09-06) [2023-10-07]. https://arxiv.org/abs/2209.02368.
[51] 李小敏, 陈英. 基于分数层融合的多生物特征融合识别[J]. 长江信息通信, 2021, 34(10): 7-11.
LI Xiaomin, CHEN Ying. Multi-biometric feature fusion recognition based on fractional layer fusion[J]. Changjiang information & communications, 2021, 34(10): 7-11.
[52] 周卫斌, 王阳, 吉书林. 基于特征融合的双模态生物识别方法[J]. 天津科技大学学报, 2022, 37(4): 44-48, 54.
ZHOU Weibin, WANG Yang, JI Shulin. Bimodal biological recognition method based on feature fusion[J]. Journal of Tianjin University of Science & Technology, 2022, 37(4): 44-48, 54.
[53] ZHOU Qing, JIA Wei, YU Ye. Multi-stream convolutional neural networks fusion for palmprint recognition[C]//Biometric Recognition. Cham: Springer, 2022: 72-81.
[54] YANG Weili, HUANG Junduan, CHEN Zhuoming, et al. Multi-view finger vein recognition using attention-based MVCNN[C]//Biometric Recognition. Cham: Springer, 2022: 82-91.
- 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]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.[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():1149.[doi:10.11992/tis.202307009]
[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:2023-10-7。
基金项目:新一代人工智能重大项目(2020AAA01073000)；中央高校基本科研业务费专项资金项目 (2023QN1077).
作者简介:潘在宇，助理研究员，主要研究方向为生物特征识别、图像修复与增强。发表学术论文10余篇。E-mail：pzycumt@163.com;徐家梦，硕士研究生，主要研究方向为深度学习、生物特征识别。E-mail：meng1633606464@163.com;王军，教授，博士生导师，主要研究方向为智能机器人与无人系统、生物特征识别、机器视觉。主持科技部科技创新2030—“新一代人工智能”重大项目，获得国家级教学科研奖1项、省部/学会级教学科研奖5项。获授权发明专利数十项，发表学术论文60余篇，出版专著教材6部。E-mail：jrobot@126.com。
通讯作者:王军. E-mail：jrobot@126.com
更新日期/Last Update:
2024-09-05