计算机与数字工程2019，Vol.47Issue(12)：3177-3181,5.DOI:10. 3969/j. issn. 1672-9722. 2019. 12. 045
基于LeNet-5模型的手写数字识别优化方法
Handwritten Digital Recognition Optimization Method Based on LeNet-5 Model
汪雅琴 1夏春蕾 1戴曙光1
作者信息
- 1. 上海理工大学光电信息与计算机工程学院 上海 200093
- 折叠
摘要
Abstract
As a kind of depth feedforward artificial neural network,convolutional neural network has been successfully ap?plied in the field of image recognition. Among them,the LeNet-5 model is the most classic convolutional neural network model. This model is used on the MNIST character library and the sample training method of convolution layer is optimized. That is to say, the training method that uses the number of fixed input samples per batch and the number of fixed iterations is optimized to be a mixed training sample mode with different numbers of input samples per batch and different iterations. The optimized training meth?od can reduce the pre-processing workload and speed up the recognition speed. The experimental results show that the optimized mixed sample input method can get a higher recognition rate under the premise of equal sample training time.关键词
图像识别/卷积神经网络/LeNet-5模型/MNIST字符库/手写数字识别Key words
image identification/convolutional neural network/LeNet-5 model/MNIST character library/handwritten dig⁃it recognition分类
信息技术与安全科学引用本文复制引用
汪雅琴,夏春蕾,戴曙光..基于LeNet-5模型的手写数字识别优化方法[J].计算机与数字工程,2019,47(12):3177-3181,5.
