Kaggle Kannad hand written digit reoginition

Kannada is a language spoken predominantly by people of Karnataka in southwestern India. The language has roughly 45 million native speakers and is written using the Kannada script.

This program aims to detect digit written Kannada script.

The code highly resembels to the kernel: https://www.kaggle.com/datahobbit/cnn-for-digit-recognition-in-the-kannada-script

The CNN-model used here is trained on google colab and the colab notebook is available in the code. Only the trained model saved in the folder "model" is uesd.

Web interface used incldes both click and touch interface, so smartphone users could also use this application. Here is what the homepage would look like,

The result page,

This application could be used for OCR in Kannada script, be extending the training dataset and making minor changes in the code.