AI engineering glossary · Computer vision
What is convolution?
Convolution (also called Conv, 2D convolution): An operation that slides a small grid of numbers, called a kernel, across an image and at each position sums the products of the kernel values with the pixels beneath it. It detects local patterns such as edges and reuses the same weights everywhere, making it efficient for images.
Convolution: an example
Sliding a 3 x 3 kernel over a 5 x 5 image with no padding and stride 1 gives a 3 x 3 output, each value a weighted sum of 9 pixels.
Related terms
More Computer vision terms
- Convolutional neural network
- Cross-correlation
- CutMix
- Cutout
- Data augmentation for images
- DeepLab
- Depthwise separable convolution
- Dice coefficient
Where you learn it
Convolution is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.