What I Learned in My First Computer Vision Class: How a Computer Sees

Computer vision involves teaching computers to process images, which they perceive as numbers rather than pictures. A photo consists of a grid of pixels, where each pixel contains three values representing red, green, and blue light, ranging from 0 to 255. For example, a photo with 400 rows and 600 columns contains 720,000 numbers. While humans instantly recognize objects like buses, computers only receive these numerical grids without explicit labels for the objects depicted.