This project is intended to recognise and predict alphabets shown by the user using sign language using a convolutional neural network. The CNN model is trained on the sign language mnist dataset and the trained model takes in input through a webcam and the predicts the alphabets. Accuracy of 97% was achieved
- Python
- Tensorflow
- Keras
- OpenCV
Dataset used:- https://www.kaggle.com/datamunge/sign-language-mnist
The trained model is located in the model folder in .h5 format.