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
-
摘要: 针对传统数字字符识别算法收敛速度慢且有可能陷入局部极小值等问题,提出了将BFGS拟牛顿算法应用于舍噪数字字符识别:构造前馈型神经网络,调用Matlab神经网络工具箱中的训练函数trainbfg对网络进行训练.该算法收敛速度快、识别精度高,能够对含有一定噪声的数字字符进行识别,具有广阔的应用前景.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.
-
Key words:
- numeric character recognition /
- neural network /
- BFGS quasi-Newton algorithm /
- Matlab
-
-
[1]
马锐.人工神经网络原理[M].北京:机械工业出版社,2010.
-
[2]
丛爽.面向Matlab工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,2009.
-
[3]
张德丰.Matlab神经网络设计与应用[M].北京:机械工业出版社,2009.
-
[4]
叶喜民,廖文军.基于BP人工神经网络的数字符识别[J].郑州轻工业学院学报:自然科学版,2009,24(2):60.
-
[5]
唐莹梅.人工神经网络在数字字符识别中的应用[J]. 科技创新导报,2009(23):233.
-
[6]
石云.BP神经网络的Matlab实现[J].湘南学院学报, 2010,31(5):86.
-
[7]
牛慧娟,汪森霖.基于神经网络的带噪声英文字母和数字识别[J].现代计算机:专业版,2008(10):59.
-
[8]
曾志军,孙过强.基于改进的BP网络数字字符识别[J].上海理工大学学报,2008,30(2):201.
-
[1]
计量
- PDF下载量: 29
- 文章访问数: 744
- 引证文献数: 0