This is a simple image classification Flask app trained on the top of Keras API. The trained CNN model takes an image (Saudi Arabian Riyal) as an input and predict the class of image from 1, 5, 10, 20, 50, 100, 200, 500 denomination.
The idea of classifying currency image struck to me when I was browsing through some image recognition use cases. I couldn't find any relevant research paper (and of course dataset!) associated with it. And that led me to collect the images of Saudi Arabian Riyal using the amazing tool bing-image-downloader to train a deep learning model .
This project is divided into three part:
- Data collection and preprocessing. The Jupyter Notebook can be found here
- Training a deep learning model using Keras. The Jupyter Notebook can be found here
- Building a Flask web app.
- A user can upload image from the system.
- After uploading the image, the predictions are displayed on a Bar Chart.
The Code is written in Python 3.9.1. If you don't have Python installed you can find it here. If you are using a lower version of Python you can upgrade using the pip package, ensuring you have the latest version of pip. To install the required packages and libraries, run this command in the project directory after cloning the repository:
pip install -r requirements.txt
