Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (12): 3673-3678.DOI: 10.11772/j.issn.1001-9081.2020050667

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Palm vein image recognition based on side chain connected convolution neural network

LOU Mengying, WANG Tianjing, LIU Yaqin, YANG Feng, HUANG Jing   

  1. School of Biomedical Engineering, Southern Medical University, Guangzhou Guangdong 510515, China
  • Received:2020-05-19 Revised:2020-07-21 Online:2020-12-10 Published:2020-08-14
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61771233), the Research and Development and Industrialization Project of Guangdong (2013B090500104).

基于侧链连接卷积神经网络的手掌静脉图像识别

娄梦莹, 王天景, 刘娅琴, 杨丰, 黄靖   

  1. 南方医科大学 生物医学工程学院, 广州 510515
  • 通讯作者: 刘娅琴(1965-),女,湖南邵阳人,教授,硕士,主要研究方向:生物特征识别、图像处理。liuyq@smu.edu.cn
  • 作者简介:娄梦莹(1994-),女,山东滨州人,硕士研究生,主要研究方向:图像处理、模式识别;王天景(1998-),男,江西九江人,主要研究方向:图像处理、模式识别;杨丰(1965-),男,湖北麻城人,教授,博士,主要研究方向:医学成像技术、机器学习;黄靖(1981-),男,湖南长沙人,副教授,博士,主要研究方向:生物特征识别、图像处理
  • 基金资助:
    国家自然科学基金资助项目(61771233);广东省研发与产业化项目(2013B090500104)。

Abstract: To overcome the performance degradation of palm vein recognition system due to the small quantity and the uneven quality of palm vein images, a palm vein image recognition method based on side chain connected convolutional neural network was proposed. Firstly, palm vein features were extracted by convolution layer and pooling layer based on ResNet model. Secondly, the Exponential Linear Unit (ELU) activation function, Batch Normalization (BN) and Dropout technology were used to improve and optimize the model, so as to alleviate gradient disappear, prevent over fitting, speed up convergence and enhance the generalization ability of the model. Finally, Densely Connected Network (DenseNet) was introduced to make the extracted palm vein features more abundant and effective. Experimental results on two public databases and one self-built database show that, the recognition rates of the proposed method on the three databases are 99.98%, 97.95%, 97.96% respectively, indicating that the proposed method can effectively improve the performance of palm vein recognition system, and is more suitable for the practical applications of palm vein recognition.

Key words: palm vein recognition, ResNet, Exponential Linear Unit (ELU) activation function, Batch Normalization (BN), Dropout, Densely Connected Network (DenseNet)

摘要: 针对手掌静脉图像数量少且质量参差不齐,进而导致掌脉识别系统的性能降低的现象,提出一种基于侧链连接卷积神经网络的手掌静脉图像识别方法。首先,在ResNet模型的基础上,用卷积层和池化层提取掌脉特征。然后,采用指数线性单元(ELU)激活函数、批归一化(BN)和Dropout技术来改进和优化模型,以缓解梯度消失、防止过拟合、加快收敛及增强模型泛化能力。最后,引入稠密连接网络(DenseNet),使提取到的手掌静脉特征更具丰富性和有效性。在两个公开库和一个自建库上分别进行实验,结果表明所提方法在三个数据库上的识别率分别为99.98%、97.95%、97.96%。可见该方法能有效提高掌脉识别系统的性能,且更适用于掌脉识别的实际应用。

关键词: 手掌静脉识别, ResNet, 指数线性单元激活函数, 批归一化, Dropout, 稠密连接网络

CLC Number: