激光与光电子学进展, 2019, 56 (10): 101010, 网络出版: 2019-07-04
结合深度神经网络和随机森林的手掌静脉分类 下载: 1303次
Palm Vein Classification Based on Deep Neural Network and Random Forest
图像处理 掌脉分类 迁移学习 深度神经网络 主成分分析 随机森林 image processing palm vein classification transfer learning deep neural network principal component analysis random forest
摘要
提出了一种结合深度神经网络和随机森林的手掌静脉分类新方法。利用预训练深度神经网络模型AlexNet提取掌脉特征,采用主成分分析法对提取的高维掌静脉特征进行降维处理,以减少存储空间、降低分类误差,结合对噪声具有很好容忍能力的随机森林进行分类。基于香港理工(PolyU)数据库、中国科学院(CASIA)数据库和自建库的测试精度分别为100%、97.00%和99.50%。相较传统方法,所提方法避免了人工选择特征提取算法的局限性,有效降低了手掌静脉的分类误差, 具有更好的稳健性。
Abstract
A new palm vein classification method that combines a deep neural network and a random forest is proposed. First, the proposed method extracts the palm vein features using AlexNet, a pre-trained deep neural network model. Then, the principal component analysis is used to reduce the dimensionality of the extracted high-dimensional palm vein features in order to conserve storage space and reduce classification errors. Finally, the random forest is used for classification owing to its high tolerance to noise. Based on the PolyU, CASIA, and self-built databases, the test accuracies obtained are 100%, 97.00%, and 99.50%, respectively. Compared with the traditional methods, the proposed method overcomes the limitations of the manual feature extraction algorithms, effectively reduces the palm vein classification errors, and demonstrates better robustness.
袁丽莎, 娄梦莹, 刘娅琴, 杨丰, 黄靖. 结合深度神经网络和随机森林的手掌静脉分类[J]. 激光与光电子学进展, 2019, 56(10): 101010. Lisha Yuan, Mengying Lou, Yaqin Liu, Feng Yang, Jing Huang. Palm Vein Classification Based on Deep Neural Network and Random Forest[J]. Laser & Optoelectronics Progress, 2019, 56(10): 101010.