Abstract: Captcha is a program which can be used to distinguish between computer and human, the image verification code is a typical application of Captcha. The development of the Captcha is summarized, and the feature and design ideas of the common Captcha are also compared. Then this paper presents the attack method on common Captcha and designs the system of feature extraction of Captcha, reducing covering algorithm based on conditional information entropy is designed and applied to attack Captcha. The experimental results prove that the model achieve excellent robust and high success recognition rate.

摘要： Captcha是用来区分计算机与人类的一种程序，图像验证码是一种典型的Captcha。对图像验证码的发展历程进行了总结，比较了几种目前最常见验证码的特点和设计思路，提出了对一般验证码的破解方法，并设计实现了提取验证码数据的图片信息提取系统；应用基于条件信息熵的覆盖约简算法，对验证码进行识别，对比实验结果证明，识别效果良好。