In object detection, they usually resize by keeping the ratio the same as the original image, which usually names "letterbox" resize. My question is: Why do we need to do that? As I see with some images too long in vertical or horizontal, we will lose a lot of features in those images. If it is better than normal resize, why people don't apply it in the classification task?

Resize image in object detection task of computer vision

Data Science Asked on March 28, 2021

In object detection, they usually resize by keeping the ratio the same as the original image, which usually names "letterbox" resize.

My question is:

Why do we need to do that? As I see with some images too long in vertical or horizontal, we will lose a lot of features in those images.
If it is better than normal resize, why people don’t apply it in the classification task?

Get help from others!