[1]刘广东,邱晓晖.基于多模式LBP 与深度森林的指静脉识别[J].计算机技术与发展,2018,28(07):83-87.[doi:10.3969/ j. issn.1673-629X.2018.07.018]
　LIU Guang-dong,QIU Xiao-hui.Finger Vein Recognition Based on Multi-mode LBP and Deep Forest[J].,2018,28(07):83-87.[doi:10.3969/ j. issn.1673-629X.2018.07.018]
点击复制

基于多模式LBP 与深度森林的指静脉识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年07期
页码:
83-87
栏目:
智能、算法、系统工程
出版日期:
2018-07-10

文章信息/Info

Title:
Finger Vein Recognition Based on Multi-mode LBP and Deep Forest
文章编号:
1673-629X(2018)07-0083-05
作者:
刘广东; 邱晓晖
南京邮电大学 通信与信息工程学院,江苏 南京 210003
Author(s):
 LIU Guang-dong; QIU Xiao-hui
关键词:
指静脉识别; 深度森林; LBP; 特征提取; 随机森林
Keywords:
finger vein recognition; deep forest; local binary pattern; feature extraction; random forest
分类号:
TP391
DOI:
10.3969/ j. issn.1673-629X.2018.07.018
文献标志码:
A
摘要:
深度森林(gcForest)是基于深度模型提出的级联随机森林集合方法,以解决深度学习网络模型中对大样本训练数据和对设备要求过高的问题。 深度森林不像深度神经网络那样具有很多的调节参数,对训练模型的选取需要耗费大量的时间与精力,gcForest 允许使用者可以根据设备的资源决定训练的耗费,且能自适应地调节训练模型层数。 指静脉图像含有丰富的纹理信息,文中基于多模式 LBP 提取指静脉图像的基本 LBP 特征,统一模式 LBP 分块直方图特征并将它们与深度森林结合取得的识别率达到 99.46%,训练时间大幅减少,并解决了 gcForest 在旋转适应性方面的不足。与随机森林分类器(random forest)、KNN 分类器、支持向量机分类器(SVM)、罗格斯特回归分类器(logistic regression)等进行比较,证明了深度森林识别器的有效性。
Abstract:
The deep forest,named as gcForest,is a cascade random forest ensemble method based on the deep learning model,in order to solve the problem that the deep learning network model usually requires large scale of training samples and the threshold of the deep learning is too high for personal research. GcForset doesn’t have lots of tuning parameters like convolution neural networks which cause the selection of the training models taking lots of time and effort. GcFroest allows users to determine the cost of training based on the resources of the device,and can adjust the number of training model layers in an adaptive manner. The finger-vein image contains rich texture information. Based on multi-mode LBP,we extract the basic LBP features and unified model LBP partitioned histogram features in the finger-vein image and combine them with the depth of the forest to reach the recognition rate by 99.46%,sharply reducing training time and solving the shortcoming on the adaptability for gcForest. Compared with random forest,KNN classifier,SVM and logistic regression,the effectiveness of gcForest recognizer is proved.

相似文献/References:

[1]吴 超,邵 曦.基于深度学习的指静脉识别研究[J].计算机技术与发展,2018,28(02):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
　WU Chao,SHAO Xi.Research on Finger Vein Ｒecognition Based on Deep Learning[J].,2018,28(07):200.[doi:10．3969/j．issn．1673－629X．2018．02．043]
[2]王海阳,吴奇石.基于层级提升重校正模型的备件分类研究[J].计算机技术与发展,2020,30(03):126.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 024]
　WANG Hai-yang,WU Qi-shi.Research on Classification Strategy of Spare Parts Based on Cascade Boosting and Recalibrating Model[J].,2020,30(07):126.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 024]

更新日期/Last Update: 2018-08-28