All terms

Computer Vision

The field of AI that enables machines to interpret images and video — detect, classify, segment, and describe visual content.

AI Foundations1 min read

Definition

Computer vision covers classification, object detection, segmentation, OCR, pose estimation, and video understanding. Deep CNNs and vision transformers power most modern systems.

It pairs with language in multimodal models that caption images or answer visual questions.

In simple terms

Computer vision is teaching cameras to describe what they see — not just record pixels, but name objects and relationships.

Where you see it

  • Face unlock and photo search.
  • Warehouse robotics and quality inspection.
  • Medical imaging triage.

How it works

  1. 1.Capture pixels

    Images or video frames as input tensors.

  2. 2.Extract features

    CNN or ViT encodes visual patterns.

  3. 3.Predict

    Labels, boxes, masks, or captions.

Why it matters

  • Vision is how AI interacts with the physical world of photos, screens, and cameras.

Often confused

  • Computer vision solved all visual tasks.

    Robustness to lighting, rare objects, and adversarial examples remains hard.