Computer Vision project in which traditional computer vision techniques are used to determine the location and numbers of pips on the top side of the dice from a video.
Input: Video files of a hand throwing some dice on a tray which is kept on a table. The videos may contain tricky hand movements, different lighting conditions, noise, and transparent dice (made of glass).
Output: Detection of every dice location and the number of pips on the top face of each die after they settle down on the tray
Libraries used:
- OpenCV
- Scipy
- Numpy
- matplotlib
A comprehensive discussion of the approach and evaluation results can be found in the project-report.pdf file.