Skip to content
AIComets
Models & Architectures Glossary

Computer Vision

The field of teaching computers to interpret images and video.

Last updated

Computer vision covers tasks such as image classification, object detection, segmentation and tracking. Deep learning transformed the field by learning features directly from pixels. Applications include medical imaging, quality inspection, autonomous vehicles and photo tools, and vision models increasingly work alongside language models in multimodal systems.

Related terms

Multimodal AI

AI that understands and generates more than one type of data, such as text, images and audio together.

Deep Learning

Machine learning that uses multi-layered neural networks to learn complex patterns directly from raw data.

Read more about Computer Vision

Keep exploring

Browse the full AI glossary or compare AI tools that use this technology.

Report an issue with this page