首页> 外国专利> CAPTCHA IDENTIFICATION METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM

CAPTCHA IDENTIFICATION METHOD AND APPARATUS, AND COMPUTER DEVICE AND STORAGE MEDIUM

机译:验证码识别方法和装置,计算机设备和存储介质

摘要

Disclosed are a CAPTCHA identification method and apparatus based on data analysis, and a computer device and a storage medium. The method comprises: acquiring a target CAPTCHA picture (S1); inputting the target CAPTCHA picture into a CAPTCHA identification model based on a convolutional neural network to carry out computation to obtain a computation result, wherein the CAPTCHA identification model comprises a CNN module and an LSTM module, and in the CAPTCHA identification model, target feature extraction is carried out on the target CAPTCHA picture by using the CNN module, an extracted target feature is input into the LSTM module to carry out sequence prediction to obtain a prediction result, and the prediction result is then computed by means of a preset function to obtain the computation result (S2); and acquiring the computation result output by the CAPTCHA identification model, wherein the computation result is a CAPTCHA character corresponding to the target CAPTCHA picture (S3). Therefore, identification is directly completed from end to end, and the model has a smaller computation amount and higher identification accuracy.
机译:公开了一种基于数据分析的验证码识别方法和装置,以及计算机设备和存储介质。该方法包括:获取目标验证码图片(S1);将目标验证码图片输入到基于卷积神经网络的验证码识别模型中进行计算以获得计算结果,其中,验证码识别模型包括CNN模块和LSTM模块,在验证码识别模型中,目标特征提取使用CNN模块对目标CAPTCHA图片进行特征提取,将提取的目标特征输入LSTM模块进行序列预测,得到预测结果,然后利用预置函数计算预测结果,得到计算结果(S2);获取所述验证码识别模型输出的计算结果,所述计算结果为与所述目标验证码图片对应的验证码字符(S3)。因此,直接从头到尾完成识别,模型的计算量较小,识别精度较高。

著录项

  • 公开/公告号WO2020215573A1

    专利类型

  • 公开/公告日2020-10-29

    原文格式PDF

  • 申请/专利权人 PING AN TECHNOLOGY (SHENZHEN) CO. LTD.;

    申请/专利号WO2019CN103538

  • 发明设计人 LI GUOAN;

    申请日2019-08-30

  • 分类号G06K9/34;

  • 国家 WO

  • 入库时间 2022-08-21 11:08:51

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号