Handwritten Digit Recognition - Machine Learning Project

Project Overview

Through this project, I strengthened my Python programming skills and gained experience working with key libraries such as NumPy and OpenCV. I used NumPy to represent pixel data as arrays and implemented OpenCV as the program’s visual input to recognize handwritten digits. I trained the model using the MNIST dataset and also experimented with custom training data that I created in Paint. The model was built and trained using TensorFlow’s Keras API, where I adjusted parameters such as the number of epochs to improve performance.

Key Features

• Numpy library
• OpenCV
• TensorFLow
• Epochs

What I Learned

With this project I learned how to work with TensorFlow and the Keras API. This was a great project to get started with Machine Learning, I also learned how to set-up a virtual environment to be used as a container to work with all the different versions of all of these libraries.