郑州轻工业学院学报（自然科学版）2011，Vol.26Issue(4)：79-81,3.
基于BFGS拟牛顿算法的含噪数字字符识别
Recognition of numeric characters with noise based on BFGS quasi-Newton algorithm
杨超 1聂仙娥 1赵河明1
作者信息
- 1. 中北大学机电工程学院,山西太原030051
- 折叠
摘要
Abstract
The traditional numeric character recognition algorithm which has slow convergence speed and might fall into the local minimum. To solve such problems,the BFGS quasi-Newton algorithm was presented that was applied to the recognition of numeric characters. First,a feed-forward neural network was set up, then network was trained by calling trainbfg on Matlab. The algorithm has high accuracy,fast convergence, can recognize the numeric characters with noise efficiently, so it has broad application prospects.关键词
数字字符识别/神经网络/BFGS拟牛顿算法/MatlabKey words
numeric character recognition/neural network/BFGS quasi-Newton algorithm/Matlab分类
计算机与自动化引用本文复制引用
杨超,聂仙娥,赵河明..基于BFGS拟牛顿算法的含噪数字字符识别[J].郑州轻工业学院学报（自然科学版）,2011,26(4):79-81,3.
