基于深度学习的手写数字分类问题研究
DOI:
作者:
作者单位:

作者简介:

通讯作者:

基金项目:


Research on the Classification of Handwriting Number  Based on Deep Learning
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    手写体数字因其书写风格差异大、上下文无关及识别准确度要求高等原因导致其识别难度大,针对手写体数字识别的特点及要求,使用深度学习算法进行分类,通过对样本的训练完成手写体数字的识别,同时与SVM算法及BP神经网络分类效果进行对比;实验结果表明深度学习在识别手写体数字时具有更高的准确率。

    Abstract:

    It is difficult to recognize handwriting number, because writing styles are different, context is free and recognition requires high accuracy. According to the characteristics and requirements of handwriting number recognition, this paper uses the Deep Learning algorithm for classification, based on the sample of training to recognize the handwriting number.At the same time, the experiment compared the classification effect with that of SVM algorithm and BP neural network. The experimental results show that the Deep Learning of handwriting number in recognition has a higher accuracy.

    参考文献
    相似文献
    引证文献
引用本文

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
SONG Zhijian, YU Rui. Research on the Classification of Handwriting Number  Based on Deep Learning[J]. Journal of Chongqing Technology and Business University(Natural Science Edition),2015,32(8):49-53

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期:
×
2024年《重庆工商大学学报(自然科学版)》影响因子显著提升