Hand-written-digit-recognition

Using CNN

Requirements

1. Install anaconda
2. Install Tensorflow,scikit-learn,numpy,pandas

MNIST dataset:

MNIST is a collection of handwritten digits from 0-9. Image of size 28 X 28

Description

1. I loaded MNIST dataset using the Keras API and creates a plot of image in the training dataset.
2. It achieved 97.13% of accuracy with CNN.
3. Finally I build a GUI using App using Tkinter(The tkinter package is the standard Python interface to the Tk GUI toolkit).

Screenshots