computer vision (the field)

Getting a machine to extract meaning -- what, where, how far -- from an image or video.

Computer vision is the field concerned with extracting meaning from visual data: identifying what an image contains, locating it, estimating its distance or motion, or reconstructing a scene's 3D structure. It draws on image processing (as a preprocessing step), classical machine learning, and deep learning as three overlapping toolkits, not three competing definitions of the field itself.

Examples

Recognizing a stop sign, estimating how far away it is, and tracking it across video frames are all computer-vision tasks built on the same acquired image.