AI engineering glossary · Computer vision
What is canny edge detector?
Canny edge detector: A classic multi-step edge detection algorithm: blur the image, compute gradients, thin edges to one pixel by non-maximum suppression, then keep strong edges and weak edges connected to them using two thresholds (hysteresis). It gives clean, thin edge maps.
Canny edge detector: an example
With thresholds 100 and 200, pixels with gradient above 200 are kept as edges, and those between 100 and 200 are kept only if touching a strong edge.
Related terms
More Computer vision terms
- Channel
- CIFAR-10
- CLS token
- Colour jitter
- Confidence score
- Connectionist temporal classification
- Contour detection
- Contrastive language-image pretraining
Where you learn it
Canny edge detector is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.