A CAPTCHA Image Recognition Algorithm Based on Edit Distance

Abstract

Using CAPTCHA is a simple but convenient way to ensure user data security. It’s widely used in user authentication and user interaction. In this paper, CAPTCHA images from several typical websites were used as the research objects. The paper shows the whole process on image binarization, de-noising, dilation, splitting characters. Gives out the CAPTCHA images recognition algorithm based on edit distance which defines the string similarity. Experiments show that the proposed algorithm is simple, fast, robust performance and has a high recognition accuracy rate.

A Recognition Method of CAPTCHA with Adhesion Character

“…GUO et al through the process on image binarization, de-noising, dilation, splitting characters and then gives out a algorithm based on edit distance which defines the string similarity. Experiments show that the proposed algorithm is simple, fast, robust performance and has a high recognition accuracy rate [14].Zhang L et al proposed a recognition method based on LSTM model RNNand achieved good results [15]. ZHANG et al proposed a new image analysis model named Concept Component Analysis (CCA).This new model based on the approaching idea in Newton's iteration and it was solved by a multi-population genetic algorithm, in their experiments has achieved good recognition results [16].CHEN et al proposed the probability pattern framework to recognize the target numbers in the CAPTCHA images and the experiment proved this method achieved an average of 81.05% for more than two thousand CAPTCHA cases [17].…”