| Title | Digit Character CAPTCHA recognition Based on Deep Convolutional Neural Network |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Zhou, Ziyue |
| Conference Name | 2021 2nd International Conference on Computing and Data Science (CDS) |
| Keywords | Activation Function, Analytical models, CAPTCHA, captchas, character recognition, composability, convolutional neural network, convolutional neural networks, Data models, Data Science, handwriting recognition, Human Behavior, pubcrawl |
| Abstract | With the developing of computer technology, Convolutional Neural Network (CNN) has made big development in both application region and research field. However, CAPTCHA (one Turing Test to tell difference between computer and human) technology is also widely used in many websites verification process and it has received great attention from researchers. In this essay, we introduced the CNN based on tensorflow framework and use the MINIST data set which is used in handwritten digit recognition to analyze the parameters and the structure of the CNN model. Moreover, we use different activation functions and compares them with different epochs. We also analyze many problems during the experiment to make the original data and the result more accurate. |
| DOI | 10.1109/CDS52072.2021.00033 |
| Citation Key | zhou_digit_2021 |
Digit Character CAPTCHA recognition Based on Deep Convolutional Neural Network