How does a computer “see” an image? When you look at a photo of a dog, you instantly see ears, eyes, fur and a wagging tail. A computer sees none of that. It sees a giant table of numbers. Every picture is made of tiny dots called pixels. Each pixel has a number that tells how bright it is. For a black-and-white image, 0 means black and 255 means white, and everything between is a shade of gray. A small 28 × 28 image is just 784 numbers sitting in a grid. So the big question becomes: how do we teach a machine to look at a grid of numbers and say “this is a dog”? That is exactly the problem CNNs solve
Loading post…
Join Marsel to reply and react. Browsing is free — sign in or request access to take action.