AI engineering glossary · Computer vision
What is image resizing?
Image resizing: Changing an image to a different width and height by interpolating pixel values. Vision pipelines resize because networks expect fixed-size inputs, and the choice of interpolation (nearest, bilinear, bicubic) and whether the aspect ratio is kept can change accuracy.
Image resizing: an example
Resizing a 640 x 480 photo to 224 x 224 without cropping squashes it horizontally, while resizing the short side to 224 and centre-cropping preserves shapes.
Related terms
More Computer vision terms
- Image segmentation
- ImageNet
- Inception module
- Instance segmentation
- Intersection over union
- Mask R-CNN
- Max pooling
- Median filter
Where you learn it
Image resizing is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.