This project was developed for the Signal, Image, and Video course at the Università di Trento.
It implements a handcrafted object detection and classification pipeline for chess pieces, and compares its performance with a deep learning-based approach.
In this repository, you'll find the source code and a Jupyter notebook (demo.ipynb) presenting the experimental results.
The dataset used in this project is publicly available on Roboflow:
-
Install dependencies
Make sure you have Python installed. Then, install the required packages using:pip install -r requirements.txt
-
Run the notebook
Execute the Jupyter notebook to explore the detection and classification experiments:
jupyter notebook demo.ipynb
Follow the instructions in the notebook to see detailed experimental results.