Handwritten-Digit-Recognition

MNIST is a widely used dataset for the hand-written digit classification task. It consists of 70,000 labeled 28x28 pixel grayscale images of hand-written digits. The dataset is split into 60,000 training images and 10,000 test images. There are 10 classes (one for each of the 10 digits).

Sample images from the dataset

Dependencies

List of dependencies for running this application.

• Keras
• tensorflow
• Opencv
• Pandas
• Numpy
• Matplotlib

DEMO

Taking input as an image

Contoured Image

Digits Recognition from the image

How to use

1. Download or clone this repository.
2. Use git clone https://github.com/mayanksharma019/Handwritten-Digit-Recognition.git
3. Extract the repository to some location.
4. Weights and model configuration is saved in mnist_handwritten.h5 file.
5. Run prediction.ipynb and give your own handwritten image as input.