Definition and goals of computer vision

Summary

Computer vision is an interdisciplinary field that focuses on how computers can gain high-level understanding from digital images or videos. From an engineering perspective, it aims to automate tasks that the human visual system can perform. As a scientific discipline, it studies the theory behind artificial systems that extract information from images; as a technological discipline, it applies those theories and models to build computer vision systems. The goals of computer vision are to automatically extract, analyze, and understand useful information from one image or sequences of images so that the results can support decisions and appropriate actions. “Understanding” means transforming visual data into meaningful descriptions of the world that align with reasoning processes. This involves disentangling symbolic information from image data using models informed by geometry, physics, statistics, and learning theory, while handling diverse image forms such as video, multi-camera views, 3D point clouds, and medical scans.

Key Points

• 1

  Computer vision enables computers to extract high-level understanding from digital images and videos.

• 2

  Its core goal is automatic extraction, analysis, and interpretation of useful visual information to support decisions and actions.

• 3

  Computer vision combines scientific theory (how extraction works) with engineering practice (building systems that perform it).

• 4

  Image understanding is framed as converting image data into meaningful world descriptions using models from geometry, physics, statistics, and learning theory.