基于增量行列二维主成分分析的深度子空间网络
A new deep subspace network based on incremental row-column two-dimensional principal component analysis
毕洪旭 1王肖锋1
作者信息
- 1. 天津理工大学天津市先进机电系统设计与智能控制重点实验室,天津 300384;天津理工大学机电工程国家级实验教学示范中心,天津 300384
- 折叠
摘要
主成分分析网络(principal component analysis network,PCANet)是一种基于卷积神经网络模型进行简化的深度子空间网络模型.针对PCANet在卷积核提取过程中无法对图像样本进行实时处理的问题,本文提出了一种基于增量行列二维主成分分析方法(incremental sequential row-col-umn 2DPCA,IRC2 DPCA)的增量行列二维主成分分析网络(incremental sequential row-column 2 DPCA network,IRC2 DPCANet).该方法可以在卷积核的训练过程中对训练样本进行实时处理,从而提高网络的训练效率.通过在PIE、AR、Yale3个典型人脸数据集上的实验表明,本文所提出的方法具有良好的分类性能.最后,本文还研究了卷积核大小及卷积层中卷积核数量对于算法分类率的影响.
Abstract
The principal component analysis network(PCANet)is a kind of deep subspace network based on the simplified architecture of convolutional neural network.To address the issue that PCANet cannot process image samples in real-time during the convolutional kernel extraction process,this article proposes an incremental sequential row-column 2DPCA network(IRC2DPCANet).This method can process training samples on time in the process of filter training,which can improve the efficiency of network training.The experiments on three typical face datasets,which is PIE,AR and Yale,indicate that this method has good classification performance.Finally,the influence of the filter number and filter size on classification rate is also investigated.
关键词
主成分分析网络(PCANet)/增量方法/特征提取/人脸识别Key words
principal component analysis network(PCANet)/incremental method/feature extraction/face recognition引用本文复制引用
出版年
2024
NETL
NSTL
万方数据