Computer Engineering and Applications ›› 2008, Vol. 44 ›› Issue (30): 13-15.DOI: 10.3778/j.issn.1002-8331.2008.30.004

• 博士论坛 • Previous Articles     Next Articles

Novel handwritten numeral recognition based on Radon transform

YANG Zhi-hua   

  1. Information Science School,Guangdong University of Business Studies,Guangzhou 510320,China
  • Received:2008-06-17 Revised:2008-07-28 Online:2008-10-21 Published:2008-10-21
  • Contact: YANG Zhi-hua

利用Radon变换实现手写数字识别的新方法

杨志华   

  1. 广东商学院 信息学院,广州 510320
  • 通讯作者: 杨志华

Abstract: A novel rotation-invariant handwritten numeral recognition is presented based on Radon transform and BP neural network.A Radon transform is firstly implemented to a handwritten numeral image to extract the rotation-invariant features and then,the BP network classifier is employed to classify it.Experiments show encouraging results.

Key words: handwritten numerals recognition, feature extraction, Radon transform, neural network

摘要: 提出了一种新的手写数字识别方法,利用传统的Radon变换,找到了一种新的旋转不变特征,最后采用BP神经网络分类器进行分类。实验表明,该方法不仅具有93.89%的高识别率,而且对字符旋转具有很好的鲁棒性。

关键词: 手写数字识别, 特征提取, Radon变换, 神经网络