Why do we resize images in computer vision?
Resizing images is a critical preprocessing step in computer vision. Principally, our machine learning models train faster on smaller images. An input image that is twice as large requires our network to learn from four times as many pixels — and that time adds up.
What is letterbox resizing?
Resize Methods
Letterbox - the image is scaled so that each dimension keeps the same ratio, but any areas which are not taken are filled with the background color. You do not lose any image to a crop. Percentage - the image is scaled in both dimensions at this ratio.