| Title | The Text Captcha Solver: A Convolutional Recurrent Neural Network-Based Approach |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Dou, Zhongchen |
| Conference Name | 2021 International Conference on Big Data Analysis and Computer Science (BDACS) |
| Keywords | CAPTCHA, captchas, character recognition, composability, Connectionist Temporal Classification, Convolutional Recurrent neural network, Deep Learning, Human Behavior, Image color analysis, Information security, Internet, noise reduction, Optical character recognition software, pubcrawl, Recurrent neural networks |
| Abstract | Although several different attacks or modern security mechanisms have been proposed, the captchas created by the numbers and the letters are still used by some websites or applications to protect their information security. The reason is that the labels of the captcha data are difficult to collect for the attacker, and protector can easily control the various parameters of the captchas: like the noise, the font type, the font size, and the background color, then make this security mechanism update with the increased attack methods. It can against attacks in different situations very effectively. This paper presents a method to recognize the different text-based captchas based on a system constituted by the denoising autoencoder and the Convolutional Recurrent Neural Network (CRNN) model with the Connectionist Temporal Classification (CTC) structure. We show that our approach has a better performance for recognizing, and it solves the identification problem of indefinite character length captchas efficiently. |
| DOI | 10.1109/BDACS53596.2021.00067 |
| Citation Key | dou_text_2021 |
The Text Captcha Solver: A Convolutional Recurrent Neural Network-Based Approach