Standard handwritten form numeral off-line recognition based on PSO-BP neural network

XU Peng1

doi:10.13873/j.1000-97872009.09.012

Chinese

您当前的位置：

首页 >

文章列表页 >

Standard handwritten form numeral off-line recognition based on PSO-BP neural network

更新时间：2025-09-11

- Standard handwritten form numeral off-line recognition based on PSO-BP neural network
- Vol. 28, Issue 9, Pages: 9-11(2009)
- 作者机构：
  
  1. 东北林业大学机电工程学院
  2. 哈尔滨学院数计学院
  3. 东北林业大学机电工程学院哈尔滨学院数计学院
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872009.09.012
  CLC： TP391.41
- Published：2009
- 稿件说明：
移动端阅览
[1]徐鹏.基于PSO-BP算法的规范手写体数字离线识别[J].传感器与微系统,2009,28(09):9-11.

XU Peng1. Standard handwritten form numeral off-line recognition based on PSO-BP neural network[J]. 2009, 28(9): 9-11.
[1]徐鹏.基于PSO-BP算法的规范手写体数字离线识别[J].传感器与微系统,2009,28(09):9-11. DOI： 10.13873/j.1000-97872009.09.012.

XU Peng1. Standard handwritten form numeral off-line recognition based on PSO-BP neural network[J]. 2009, 28(9): 9-11. DOI： 10.13873/j.1000-97872009.09.012.

摘要

针对BP算法存在的易陷入局部极小点、收敛速度慢、所设计的网络泛化能力不能保证等问题

提出了一种基于粒子群优化算法（PSO）的BP（PSO-BP）网络的权值调整新方法。该算法在基本BP算法的误差反传调整权值的基础上

再引入PSO算法的权值修正

从而建立了基于PSO-BP网络模型。基于此模型设计了规范手写体数字识别的分类器

采用随机手写数字样本进行了仿真实验

结果表明:PSO-BP算法提高了网络的稳定性

避免了BP算法容易进入平坦区、陷入局部极小等问题。

Abstract

For BP algorithm has local minimum point easy

slow convergence and the generalization ability of network design can not be guaranteed and other issues

a particle swarm optimization（PSO）algorithm BP（PSO-BP）network is proposed

which can adjust the network value.On the basis of the basic BP algorithm back-propagation algorithm adjust weights

re-introduction PSO of the right to correction

which set up BP network model based on PSO algorithm.Handwritten numeral recognition classifier is designed based on this model

using random samples of the handwritten figure simulation results show that PSO-BP neural network algorithm enhances the stability of the network

avoids the BP algorithm easy access to flat areas and a partial very small and so on.

关键词

Keywords

references

基于非线性PCA神经网络的手写体字符识别 [J]. 孙光民,张程,王鹏,邓超. 北京工业大学学报 . 2007(09)

基于支持向量机的手写体数字识别 [J]. 尚磊,刘风进. 兵工自动化 . 2007(03)

HMM-based handwritten word recognition: on the optimization of the number of states, training iterations and Gaussian components [J] . Simon Günter,Horst Bunke. Pattern Recognition . 2004 (10)

Neural networks with enhanced outlier rejection ability for off-line handwritten word recognition [J] . Jinhui Liu,Paul Gader. Pattern Recognition . 2002 (10)

A nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition [J] . Bailing Zhang,Minyue Fu,Hong Yan. Pattern Recognition . 2001 (2)

Views

108

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Ambient temperature compensation of infrared temperature sensor based on PSO-BP

Research on optimal dispatching algorithm of power routers in farming and pastoral areas based on SSA

PSO localization algorithm based on node density weighting and distance correction

Computation offloading strategy based on PD-BPSO algorithm

Temperature prediction method of greenhouse based on PCA-PSO-LSSVM

Related Author

ZHAO Bin

WANG Jian-hua

Lü Xiaoyuan

ZHANG Zhanqiang

MENG Keqilao

SUN Yujie

FANG Wangsheng

WANG Zhou

Related Institution

School of Electronics and Information,Jiangsu University of Science and Technology

College of Energy and Power Engineering, Inner Mongolia University of Technology

College of Information Engineering, Inner Mongolia University of Technology

Faculty of Information Engineering,Jiangxi University of Science and Technology

National Mobile Communications Research Laboratory,Southeast University

⁰