计算机工程与应用2018，Vol.54Issue(3)：160-165,6.DOI:10.3778/j.issn.1002-8331.1706-0304
卷积神经网络识别汉字验证码
Chinese character CAPTCHA recognition based on convolution neural network
范望 1韩俊刚 1苟凡 1李帅1
作者信息
- 1. 西安邮电大学 研究生学院,西安 710121
- 折叠
摘要
Abstract
CAPTCHAs(Completed Automated Public Turing test to tell Computers and Humans Apart) have already been widely applied in various fields of social life. Automatic recognition of CAPTCHAs consisting of English letters and Arabic numerals has already reached an advanced level. While with general methods identifing the CAPTCHAs consisting of Chinese characters seems too difficult and the accuracy needs to be promoted. This paper mainly proposes a method of automatic identification CAPTCHAs which is based on convolutional neural network to improve the accuracy of characters recognition. In order to improve the generalization performance of the model by which adopting the framework of Keras convolution neural network and designing of multilayer convolution to extract deep-layer image information of which identifing Chinese characters CAPTCHAs and alphanumeric CAPTCHAs respectively. The experimental results indicate that the accuracy of identification has been promoted remarkably. The identification rate of Chinese characters is up to 99.4％. Meanwhile, the maximum of the identification rate of alphanumeric four-character CAPTCHAs is as high as 99.3％. These findings show that the Deep Neural Network possesses an excellent perceptivity against complex structures. It can be seen from the comparative experiments that the framework of Keras convolution neural network has better per-formance than other frameworks in CAPTCHAs recognition.关键词
验证码/汉字验证码/CNN/Keras框架Key words
CAPTCHAs(Completed Automated Public Turing test to tell Computers and Humans Apart)/Chinese character CAPTCHAs/CNN/Keras framework分类
信息技术与安全科学引用本文复制引用
范望,韩俊刚,苟凡,李帅..卷积神经网络识别汉字验证码[J].计算机工程与应用,2018,54(3):160-165,6.
