This project implements a Convolutional Neural Network (CNN) to recognize CAPTCHA images. It's designed as a learning project for the RTP-B14 team. The goal of this project is to build a CNN model that can recognize characters in CAPTCHA images. The model is trained to predict individual characters in the CAPTCHA, handling both letters and digits.
The project uses a custom dataset of CAPTCHA images. Each image contains 5-6 characters (both letters and digits) with some noise and distortion typical of CAPTCHAs.
Built with