Computer Vision

Level 1

Teaching computers to see and understand pictures — like recognizing a cat in a photo or reading words on a sign.

Level 2

The field of AI that deals with understanding images and videos — detecting objects, reading text, recognizing faces, and understanding scenes.

Level 3

A subfield of AI focused on enabling machines to interpret visual data from the world, including object detection, image classification, and scene understanding.

Level 4

The study of algorithms that extract semantic information from visual inputs — encompassing CNNs, vision transformers, and multimodal architectures for tasks like detection, segmentation, and visual question answering.

Level 5

Computational visual perception: learning hierarchical feature representations from pixel-level inputs via convolutional, transformer, or hybrid architectures — enabling dense prediction, 3D reconstruction, and vision-language grounding tasks.

Sources

• NIST Trustworthy and Responsible AI Resource Center: Glossary — National Institute of Standards and Technology. Accessed 2026-07-20.