计算机科学 ›› 2011, Vol. 38 ›› Issue (Z10): 204-205.

• CRSSC-CWI-CGrC2015 • 上一篇    下一篇

基于改进BP神经网络的手写体数字识别

何松,戚建宇   

  1. (常州工学院计算机信息工程学院 常州213002);(常州工学院延陵学院 常州213002)
  • 出版日期:2018-11-16 发布日期:2018-11-16

Handwritten Numeral Recognition Based on the Improved BP Neural Network

HE Song, QI Jian-yu   

  • Online:2018-11-16 Published:2018-11-16

摘要: 数字识别在许多领域有广泛的应用。通过对人工神经网络的研究与学习,运用改进的PP神经网络对无约束手写体数字识别过程中的数字样本进行识别。实验证明,该方法具有很强的抗干扰性,克服了传统PP算法的局限性,其识别率和准确率都有很大提高。

关键词: 神经网络,数字识别,改进PP网络

Abstract: The digital recognitions have extensive application in a lot of important fields. The artificial network was studied in the paper. The figure specimens were filtered through the process of unconstrained handwritten numeral, that it was recognized by the improved BP neural network. The result of experiment demonstrates that the method has very high noise immunity capacity and overcomes the limitation of traditional BP algorithm. The recognition rate and precision rate are greatly improved at the same time.

Key words: Neural network, Digital recognition, Improve BP network

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!