AI engineering glossary · Computer vision
What is image normalisation?
Image normalisation (also called Pixel normalisation): Rescaling pixel values before feeding an image to a model, typically dividing by 255 and then subtracting a per-channel mean and dividing by a standard deviation. It puts inputs on a consistent scale so training is stable and pretrained weights receive the statistics they expect.
Image normalisation: an example
With ImageNet statistics, a red-channel value of 0.5 becomes (0.5 - 0.485) / 0.229, which is about 0.066.
Related terms
More Computer vision terms
- Image pyramid
- Image resizing
- Image segmentation
- ImageNet
- Inception module
- Instance segmentation
- Intersection over union
- Mask R-CNN
Where you learn it
Image normalisation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.