摘要
文章根据一类图片验证码的字符颜色、大小、字符间位置关系,使用粗糙集的方法将验证码图片中的字符分割出来,再使用AdaBoost算法进行训练,将分割得到的字符识别出来。经实验证明,该算法对该类彩色验证码,无需很高的训练样本,即具有很高的识别率和速率,基本可以满足实时应用。
A new Recognition Algorithm of Colored hnage CAPTCHA（Completely Automated Public Turing test to tell Computers and Humans Apart, CAPTCHA） was introduced in this article. At first, using Rough Set method to detect the characters, by attrib of characters of colored Image CAPTCHA which is color, size and, position relationship between the characters, then use the AdaBoost classifier to identification the characters was. And experiments show that the algorithm is run good for that type of color code, and need not lots of training samples, which has a high recognition rate and speed, and is close to real-time applications.
出处
《信息网络安全》
2012年第6期26-28,43,共4页
Netinfo Security
