This project is focused on using the MNIST dataset to train a handwriting recognition model using machine learning techniques.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
You will need to have Python3 and the following libraries installed on your machine:
Tensorflow
Keras
OpenCV
Numpy
PIL
Tkinter
Clone the repository to your local machine
Change directory into the cloned repository
Install the required libraries
The model exist in model.py you can discover or change something you can get yours or just use the .h5 where the model already trained
To run the application , navigate to the root of the cloned repository and run Interface.py
You will get :
Draw a numbers in the white zone
Click recognize digit
This will take a screen of the white zone and it will send it to the model where it will be detected and return what's the number and the accuracy in another window
also it will store 2 png one before recognizing and other after recognizing
