2026
Classic CV, from scratch
Canny edge detection, Hough line transforms and marker-based watershed segmentation, implemented from the description of each algorithm with plain for loops.
cv-classic-naive
Why
A way to challenge myself: implement classic algorithms from their description and mechanism, without reaching for the library call. The implementations are unoptimised, for-loop versions, and none of the code is AI generated.
Notebooks
- Canny edge detector: greyscale, Gaussian blur, gradient magnitude and direction, non-maximum suppression, double thresholding and edge hysteresis.
- Hough line transform, plus the probabilistic variant.
- Marker-based watershed segmentation.