基于CNN和随机弹性形变的相似手写汉字识别

被引:29
作者
高学
王有旺
机构
[1] 华南理工大学电子与信息学院
关键词
字符识别; 深度学习; 卷积神经网络; 弹性形变;
D O I
暂无
中图分类号
TP391.43 [];
学科分类号
摘要
针对手写汉字中相似汉字的识别问题,构建了一种卷积神经网络(CNN)模型,并给出了其网络拓扑结构,通过随机弹性形变对样本集进行扩展,以提高模型的泛化性能.相似手写汉字的识别实验结果表明:相对于常规的CNN模型,文中CNN模型的手写汉字识别正确率提高1.66%,特别是对于变形的手写汉字,识别正确率提高12.85%;相对于传统的手写汉字识别方法,文中方法的识别错误率降低36.47%,从而验证了文中识别方法的有效性.
引用
收藏
页码:72 / 76+83 +83
页数:6
相关论文
共 15 条
  • [1] Effective training of a neural network character classifier for word recognition. Yaeger L,Lyon R,Webb B. Advances in Neural Information Processing Systems 10 . 1997
  • [2] Gradient-based learning applied to document recognition. Lecun, Y.,Bottou, L.,Bengio, Y.,Haffner, P. Proceedings of Tricomm . 1998
  • [3] A new feature optimization method based on two-directional 2DLDA for handwritten Chinese character recognition. Gao X,Wen W H,Jin L W. Proceedings of 2011International Conference on Document Analysis and Recognition . 2011
  • [4] HCL2000:a large-scale handwritten Chinese character database for handwritten character recognition. Zhang H,Guo J,Chen G,et al. Proceedings of 2009 International Conference on Document Analysis and Recognition . 2009
  • [5] Classification and learning methods for character recognition:advances and remaining problems. Liu C L,Fujisawa H. Machine Learning in Document Analysis and Recognition . 2008
  • [6] A fast learning algorithm for deep belief nets. Geoffrey E. Hinton,Simon Osindero,Yee-Whye Teh. Neural Computation . 2006
  • [7] Face Relighting from a Single Image under ArbitraryUnknown Lighting Conditions. Y. Wang,L. Zhang,Z. C. Liu, et al. IEEE Transactions on Pattern Analysis and MachineIntelligence . 2009
  • [8] Learning deep architectures for AI. Bengio,Yoshua. Foundations and Trends in Machine Learning . 2009
  • [9] Convolutional networks for speech detection. Sukittanon S,Surendran A C,Platt J C,et al. Proceedings of the Eighth International Conference on Spoken Language Processing . 2004
  • [10] Evaluation of pooling operations in convolutional architectures for object recognition. Scherer D,Müller A,Behnke S. Proceedings of the 20th International Conference on Artificial Neural Networks . 2010