The field of AI focused on enabling machines to interpret and understand visual information from the world — images, video, 3D scenes, and documents. Computer vision powers everything from facial recognition and autonomous driving to medical imaging and AI image generation. Core tasks include object detection, image classification, segmentation, OCR, and pose estimation.
Why it matters
Computer vision was the first area where deep learning clearly surpassed human performance (ImageNet 2012), and it remains one of the most commercially impactful AI applications. Every AI image or video you generate, every document you OCR, every security camera with smart detection — it's all computer vision.