Visible to the public A CAPTCHA recognition technology based on deep learning

TitleA CAPTCHA recognition technology based on deep learning
Publication TypeConference Paper
Year of Publication2018
AuthorsHu, Y., Chen, L., Cheng, J.
Conference Name2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA)
Date Publishedmay
KeywordsAdaptation models, adaptive learning rate, automatic malicious program attack, CAPTCHA, CAPTCHA recognition technology, captchas, character recognition, Completely Automated Public Turing Test to Tell Computers and Humans Apart, composability, convolution, convolutional neural network, convolutional neural network model, Deep Learning, feature extraction, feedforward neural nets, handwriting recognition, Human Behavior, human-machine distinction technology, image recognition, learning (artificial intelligence), license plate recognition, model recognition, Multi task joint training, multitask joint training model, pubcrawl, security breaches, security of data, Task Analysis, Training
AbstractCompletely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is an important human-machine distinction technology for website to prevent the automatic malicious program attack. CAPTCHA recognition studies can find security breaches in CAPTCHA, improve CAPTCHA technology, it can also promote the technologies of license plate recognition and handwriting recognition. This paper proposed a method based on Convolutional Neural Network (CNN) model to identify CAPTCHA and avoid the traditional image processing technology such as location and segmentation. The adaptive learning rate is introduced to accelerate the convergence rate of the model, and the problem of over-fitting and local optimal solution has been solved. The multi task joint training model is used to improve the accuracy and generalization ability of model recognition. The experimental results show that the model has a good recognition effect on CAPTCHA with background noise and character adhesion distortion.
Citation Keyhu_captcha_2018