Recognition of multi-fontstyle characters based on Convolutional neural network

摘要：

Convolutional Neural Networks are popularly used in OCR and document recognition. This paper applies stochastic diagonal Levenberg-Marquardt method into a convolutional network, which is presented by Simard. The relations between the sample class number, global learning rate and the networks convergence speed are discussed; Experiments on different train sets showed that class number is an essantial factor to the neural networks convergence. We have successfully expeanded Simard network into recognition of multifontstyle little character set like Baidu CAPTCHA and got a recognition rate as 98.4％ in single Baidu CAPTCHA character, and 93.5％ as the overall rate .Experiments in this paper has confirmed that Convolutional Neural Network can be successfully used in recognition of multi-fontstyle little character set.

关键词： CNN BP weight sharing character recognition CAPTCHA

作者: Gang Lv

作者单位: College of Technology, Jinhua Radio and Television University, Jinhua Zhejiang Province, China

会议类型: 国际会议

会议名称: 2011 Fourth International Symposium on Computational Interlligence and Design 第四届计算智能与设计国际会议 ISCID 2011

会议地点: 杭州

会议语种:英文

页码: 603-605

在线出版日期: 2011-10-28（万方平台首次上网日期，不代表论文的发表时间）