计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (30): 13-15.DOI: 10.3778/j.issn.1002-8331.2008.30.004
• 博士论坛 • 上一篇 下一篇
杨志华
收稿日期:
修回日期:
出版日期:
发布日期:
通讯作者:
YANG Zhi-hua
Received:
Revised:
Online:
Published:
Contact:
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
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
杨志华. 利用Radon变换实现手写数字识别的新方法[J]. 计算机工程与应用, 2008, 44(30): 13-15.
YANG Zhi-hua. Novel handwritten numeral recognition based on Radon transform[J]. Computer Engineering and Applications, 2008, 44(30): 13-15.
0 / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://cea.ceaj.org/CN/10.3778/j.issn.1002-8331.2008.30.004
http://cea.ceaj.org/CN/Y2008/V44/I30/13
