基于注意力特征融合网络的手指静脉图像质量评价方法

doi:10.6040/j.issn.1672-3961.0.2023.142

摘要/Abstract

摘要： 为充分挖掘质量特征以提高手指静脉图像质量评价的性能,提出一种基于注意力特征融合的深度可分离卷积网络,将其用于手指静脉图像质量评价。该方法主要包括静脉纹路提取、深度质量特征提取、注意力特征融合和图像质量类别预测等四个步骤。使用深度可分离卷积代替传统卷积,减少网络参数,使网络轻量化。使用注意力特征融合代替特征串联融合,从手指静脉灰度图像和手指静脉纹路图像中挖掘更具区分性的质量特征。考虑到目前没有公开手指静脉图像质量数据库,手工标注山东大学手指静脉公开库中图像的质量标记。试验结果表明,本研究提出的方法在手工标注数据库上的图像质量分类正确率为89.67%,图像质量评价性能优于现有手指静脉图像质量评价方法。

关键词: 手指静脉识别, 图像质量评价, 卷积神经网络, 注意力特征融合, 深度可分离卷积

中图分类号:

TP311

迟云浩,杨璐,郭杰,郝凡昌,聂秀山. 基于注意力特征融合网络的手指静脉图像质量评价方法[J]. 山东大学学报 (工学版), 2023, 53(6): 56-62.

CHI Yunhao, YANG Lu, GUO Jie, HAO Fanchang, NIE Xiushan. Finger vein image quality evaluation method based on attention feature fusion network[J]. Journal of Shandong University(Engineering Science), 2023, 53(6): 56-62.

参考文献

[1] WU Jianda, YE Siouhuan. Driver identification using finger-vein patterns with radon transform and neural network[J]. Expert Systems with Applications, 2009, 36(3):5793-5799.
[2] QIN Huafeng, HU Rongshan, EL-YACOUBI Mounim A, et al. Local attention transformer-based full-view finger-vein identification[J]. IEEE Transactions on Circuits and Systems for Video Technology,2022, 33(6):2767-2782.
[3] HUANG Junduan, LUO Weijian, YANG Weili, et al. FVT: finger vein transformer for authentication[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-13.
[4] HUANG Junduan, ZHENG An, SHAKEEL M Saad, et al. FVFSNet: frequency-spatial coupling network for finger vein authentication[J]. IEEE Transactions on Information Forensics and Security, 2023, 18:1322-1334.
[5] ZHANG Zejun, ZHONG Fei, KANG Wenxiong. Study on reflection-based imaging finger vein recognition[J]. IEEE Transactions on Information Forensics and Security, 2021, 17:2298-2310.
[6] YANG Lu, LIU Xing, YANG Gongping, et al. Small-area finger vein recognition[J]. IEEE Transactions on Information Forensics and Security, 2023, 18:1914-1925.
[7] SHAHEED Kashif, MAO Aihua, QURESHI Imran, et al. Recent advancements in finger vein recognition technology: methodology, challenges and opportunities[J]. Information Fusion, 2022, 79:84-109.
[8] KAUBA Christof, PICIUCCO Emanuela, MAIORANA Emanuele, et al. Towards practical cancelable biometrics for finger vein recognition[J]. Information Sciences, 2022, 585:395-417.
[9] 王科俊, 刘靖宇, 马慧, 等. 手指静脉图像质量评价[J]. 智能系统学报, 2011, 6(4):324-327. WANG Kejun, LIU Jingyu, MA Hui, et al. A finger vein image quality assessment method[J]. CAAI Transactions on Intelligent Systems, 2011, 6(4):324-327.
[10] MA H, WANG K, FAN L, et al. A finger vein image quality assessment method using object and human visual system index[C] // International Conference on Intelligent Science and Intelligent Data Engineering. Nanjing, China: Springer, 2013:498-506.
[11] YANG Lu, YANG Gongping, YIN Yilong, et al. Finger vein image quality evaluation using support vector machines[J]. Optical Engineering, 2013, 52(2):1-10.
[12] ZHOU Lizhen, YANG Gongping, YANG Lu, et al. Finger vein image quality evaluation based on support vector regression[J]. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015, 8(8):211-222.
[13] SHAHEED K, YANG L, YANG G, et al. Novel image quality assessment and enhancement techniques for finger vein recognition[C] //International Conference on Security, Pattern Analysis, and Cybernetics. Jinan, China: IEEE, 2018:223-231.
[14] KASHIF Shaheed, IMRAN Qureshi. A hybrid proposed image quality assessment and enhancement framework for finger vein recognition[J/OL]. Multimedia Tools and Applications. [2022-02-25]. https://doi.org/10.1007/s11042-021-11877-x.
[15] QIN Huafeng, EL-YACOUBI Mounim A. Deep representation for finger-vein image quality assessment[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 28(8):1677-1693.
[16] QIN H, El-YACOUBI M A. Finger-vein quality assessment by representation learning from binary images[C] //International Conference on Neural Information Processing. Istanbul, Turkey: Springer, 2015:421-431.
[17] WANG Y, FANG P. A finger-vein image quality assessment algorithm combined with improved SMOTE and convolutional neural network[C] //International Conference on Software Engineering and Service Science. Beijing, China: IEEE, 2020:1-4.
[18] REN Hengyi, SUN Lijuan, GUO Jian, et al. A high compatibility finger vein image quality assessment system based on deep learning[J]. Expert Systems with Applications, 2022, 196:1-12.
[19] QIN Huafeng, EL-YACOUBI Mounim A. Finger-vein quality assessment based on deep features from grayscale and binary images[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2019, 33(11):1-19.
[20] 曾军英, 谌瑶, 秦传波, 等. 级联优化CNN的手指静脉图像质量评估[J].中国图象图形学报, 2019, 24(6):902-913. ZENG Junying, CHEN Yao, QIN Chuanbo, et al. Finger vein image quality assessment based on cascaded fine-tuning convolutional neural network[J].Journal of Image and Graphics, 2019, 24(6):902-913.
[21] QIN Huafeng, CHEN Ziran, HE Xiping. Finger-vein image quality evaluation based on the representation of grayscale and binary image[J]. Multimedia Tools and Applications, 2018, 77:2505-2527.
[22] DAT Tien Nguyen, YOUNG Ho Park, KWANG Yong Shin, et al. New finger-vein recognition method based on image quality assessment[J]. KSII Transactions on Internet and Information Systems, 2013, 7(2):347-365.
[23] HUANG Z, KANG W, WU Q, et al. A finger vein identification system based on image quality assessment[C] // Chinese Conference on Biometric Recognition, Chengdu, China: Springer, 2016:244-254.
[24] KUMAR Ajay, ZHOU Yingbo. Human identification using finger images[J]. IEEE Transactions on Image Processing, 2011, 21(4):2228-2244.
[25] DAI Y, GIESEKE F, OEHMCKE S, et al. Attentional feature fusion[C] // IEEE Winter Conference on Applications of Computer Vision, Waikoloa, USA: IEEE, 2021:3560-3569.
[26] HOWARD Andrew G, ZHU Menglong, CHEN Bo, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications[J/OL]. ArXiv. [2017-05-17]. https://doi.org/10.48550/arXiv.1704.04861.
[27] YIN Y, LIU L, SUN X. SDUMLA-HMT: a multimodal biometric database[C] // Chinese Conference on Biometric Recognition. Guangzhou, China: Springer, 2011:260-268.

相关文章 15

[1]	那绪博,张莹,李沐阳,陈元畅,华云鹏. 基于ODCG的网约车需求预测模型[J]. 山东大学学报 (工学版), 2023, 53(5): 48-56.
[2]	范海雯,郝旭东,赵康,邢法财,蒋哲,李常刚. 基于卷积神经网络的含分布式光伏配电网静态等值[J]. 山东大学学报 (工学版), 2023, 53(4): 140-148.
[3]	王智伟,徐海超,郭相阳,马炯,褚云龙,陈前昌,卢治. 基于卷积神经网络和层次分析的新能源电源调频能力智能预测方法[J]. 山东大学学报 (工学版), 2022, 52(5): 70-76.
[4]	王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[5]	张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.
[6]	尹旭,刘兆英,张婷,李玉鑑. 基于弱监督和半监督学习的红外舰船分割方法[J]. 山东大学学报 (工学版), 2022, 52(2): 99-106.
[7]	陶亮,刘宝宁,梁玮. 基于CNN-LSTM 混合模型的心律失常自动检测[J]. 山东大学学报 (工学版), 2021, 51(3): 30-36.
[8]	廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.
[9]	廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[10]	李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[11]	宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.
[12]	蔡国永, 林强, 任凯琪. 基于域对抗网络和BERT的跨领域文本情感分析[J]. 山东大学学报 (工学版), 2020, 50(1): 1-7.
[13]	侯霄雄,许新征,朱炯,郭燕燕. 基于AlexNet和集成分类器的乳腺癌计算机辅助诊断方法[J]. 山东大学学报 (工学版), 2019, 49(2): 74-79.
[14]	权稳稳,林明星. CNN特征与BOF相融合的水下目标识别算法[J]. 山东大学学报 (工学版), 2019, 49(1): 107-113.
[15]	梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed