Breaking Internet Banking CAPTCHA Based on Instance Learning

摘要

Visual textual CAPTCHAs have been widely used on Internet banking in China to defend against malicious bot programs. In this paper, four categories of representative CAPTCHAs are chosen to break. We present an efficient method for solving visual textual CAPTCHAs using image processing techniques and instance learning, such as graying, thresholding, interference noises removing, segmentation, character normalization, extracting feature vector for each character, and recognizing it based on instance learning. At last, we discuss defense from attacking viewpoint to improve the design of visual textual CAPTCHAs.