Computer Vision.

Computer Vision (CV) is the AI discipline focused on enabling machines to extract meaningful information from digital images and video. Using convolutional neural networks and more recently vision transformers, CV systems can classify images, detect objects within them, segment scenes, read text (OCR), and understand visual context.

Computer Vision in Search

Google Lens uses computer vision to enable visual search—users photograph a product, plant, or landmark and receive relevant search results. Image search ranking increasingly depends on CV-based quality signals: whether an image clearly shows what its alt text and surrounding context claim, whether it is unique, and whether it adds value beyond what text alone provides. Optimising images for CV-based systems—with accurate alt text, descriptive filenames, and high visual quality—improves discoverability in both image and visual search.