计算机工程与应用2019，Vol.55Issue(13)：134-139,6.DOI:10.3778/j.issn.1002-8331.1803-0409
基于PCA初始化卷积核的CNN手写数字识别算法
CNN Handwritten Digital Recognition Algorithm Based on PCA Initialization Convolution Kernel
摘要
Abstract
On the issues about the slow convergence speed and low identification rate in handwritten digit recognition, based on CNN(Convolutional Neural Network)in which the convolution kernels are initialized randomly, an improved algorithm in which the convolution kernels are initialized by PCA(Principal Component Analysis)is proposed. Firstly, training samples are selected and sent to CNN. In the corresponding layer feature map is processed by image block extraction, after that feature vectors extracted by the way of PCA in layered learning are used to initialize the convolution kernels. Finally, original images of the CNN are processed by these convolution kernels. Compared with the CNN hand-written digit recognition algorithm that randomly initializes the convolution kernel, the improved algorithm not only converges when applied to the MNIST database training, but also has fewer iterations and higher recognition rate when the same mean square error is generated.关键词
主成分分析/卷积神经网络/卷积核/手写数字识别Key words
Principal Component Analysis(PCA)/ Convolutional Neural Network(CNN)/ convolution kernel/ hand-written digit recognition分类
信息技术与安全科学引用本文复制引用
MA Yichao,ZHAO Yunji,ZHANG Xinliang..基于PCA初始化卷积核的CNN手写数字识别算法[J].计算机工程与应用,2019,55(13):134-139,6.基金项目
河南省高等学校重点科研项目(No.13160025). （No.13160025）
