|本期目录/Table of Contents|

[1]李斯凡,高法钦.基于卷积神经网络的手写数字识别[J].浙江理工大学学报,2017,37-38(自科3):438-443.
 LI Sifan,GAO Faqin.Handwritten Numeral Recognition Based on Convolution Neural Network[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科3):438-443.
点击复制

基于卷积神经网络的手写数字识别()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第37-38卷
期数:
2017年自科3期
页码:
438-443
栏目:
出版日期:
2017-05-18

文章信息/Info

Title:
Handwritten Numeral Recognition Based on Convolution Neural Network
文章编号:
1673-3851 (2017) 03-0438-06
作者:
李斯凡高法钦
浙江理工大学信息学院, 杭州 310018
Author(s):
LI Sifan GAO Faqin
School of Information Science and Technology, Zhejiang Sci-Tech  University, Hangzhou 310018, China
关键词:
卷积神经网络手写数字识别LeNet 5
分类号:
TP391.4
文献标志码:
A
摘要:
在LeNet 5模型的基础上,改进了卷积神经网络模型,对改进后的模型及网络训练过程进行了介绍,推导了网络模型训练过程中涉及到的前向和反向传播算法。将改进的模型在MNIST字符库上进行实验,分析了卷积层不同滤波器数量、每批数量、网络学习率等参数对最终识别性能的影响,并与传统识别方法进行对比分析。结果表明:改进后的网络结构简单,预处理工作量少,可扩展性强,识别速度快,具有较高的识别率,能有效防止网络出现过拟合现象,在识别性能上明显优于传统方法。

参考文献/References:

[1] 关保林,巴力登.基于改进遗传算法的BP神经网络手写数字识别[J].化工自动化及仪表,2013,40(6):774-778.
[2] 马宁,廖慧惠.基于量子门神经网络的手写体数字识别[J].吉林工程技术师范学院学报,2012,28(4):71-73.
[3] BABU U R, CHINTHA A K, VENKATESWARLU Y. Handwritten digit recognition using structural, statistical features and knearest neighbor classifier[J]. International Journal of Information Engineering & Electronic Business,2014,6(1):62-68.
[4] GORGEVIK D, CAKMAKOV D. Handwritten digit recognition by combining SVM classifiers[C]// The International Conference on Computer as a Tool. IEEE,2005:1393-1396.
[5] 杜敏,赵全友.基于动态权值集成的手写数字识别方法[J].计算机工程与应用,2010,46(27):182-184.
[6] 刘炀,汤传玲,王静,等.一种基于BP神经网络的数字识别新方法[J].微型机与应用,2012,31(7):36-39.
[7] ZHANG X, WU L. Handwritten digit recognition based on improved learning rate bp algorithm[C]// Information Engineering and Computer Science (ICIECS), 2010 2nd International Conference on IEEE,2010:1-4.
[8] BARROS P, MAGG S, WEBER C, et al. A multichannel convolutional neural network for hand posture recognition[C]//International Conference on Artificial Neural Networks. Springer International Publishing,2014:403-410.
[9] 宋志坚,余锐.基于深度学习的手写数字分类问题研究[J].重庆工商大学学报(自然科学版),2015,32(8):49-53.
[10] 吕国豪,罗四维,黄雅平,等.基于卷积神经网络的正则化方法[J].计算机研究与发展,2014,51(9):1891-1900.

相似文献/References:

[1]张玮,张华熊.基于卷积神经网络的纺织面料主成分分类[J].浙江理工大学学报,2019,41-42(自科一):1.
 ZHANG Wei,ZHANG Huaxiong.Classification of main components of textile fabrics based on convolutional neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):1.
[2]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on  attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):208.
[3]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):208.
[4]陈巧红,董雯,孙麒,等.基于混合神经网络的单文档自动文摘模型[J].浙江理工大学学报,2019,41-42(自科四):489.
 CHEN Qiaohong,DONG Wen,SUN Qi,et al.Single document automatic summarization model based on hybrid neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):489.
[5]陈巧红,王磊,孙麒,等.基于混合神经网络的中文短文本分类模型[J].浙江理工大学学报,2019,41-42(自科四):509.
 CHEN Qiaohong,WANG Lei,SUN Qi,et al.Chinese short text classification model based on hybrid neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):509.
[6]程诚,任佳.基于自适应卷积核的改进CNN数值型数据分类算法[J].浙江理工大学学报,2019,41-42(自科五):657.
 CHENG Cheng,REN Jia.Improved CNN classification algorithm based on adaptive convolution kernel for numerical data[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科3):657.
[7]田秋红,孙文轩,章立早,等.基于改进GhostNet的轻量级手势图像识别方法[J].浙江理工大学学报,2023,49-50(自科三):300.
 TIAN Qiuhong,SUN Wenxuan,ZHANG Lizao,et al.Lightweight gesture image recognition method  based on improved GhostNet[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科3):300.
[8]祝鹏烜,黄体仁,李旭.MSAG-TransNet:肺部CT图像中新冠肺炎感染新型冠状病毒感染区域的分割模型[J].浙江理工大学学报,2023,49-50(自科六):734.
 ZHU Pengxuan,HUANG Tiren,LI Xu.MSAG-TransNet: Segmentation model of COVID-19 infected areas in lung CT images[J].Journal of Zhejiang Sci-Tech University,2023,49-50(自科3):734.

备注/Memo

备注/Memo:
收稿日期: 2016-09-16
网络出版日期:2017-01-03
基金项目: 浙江省自然科学基金项目(LY14F030025);国家自然科学基金项目(61402417)
作者简介: 李斯凡(1991-),女,湖北鄂州人,硕士研究生,主要从事深度学习及大数据分析方面的研究
通信作者: 高法钦,E-mail: gfqzjlg@126.com
更新日期/Last Update: 2017-09-13