← All topics

Core Machine Learning Topics

Computer Vision

コンピュータビジョン

Computer vision extracts useful information from images and video. Object detection locates objects, while image segmentation assigns pixels to meaningful regions.

Japanese terms

  1. Computer vision — コンピュータビジョン: The field that enables computers to extract information from images and video.
  2. Object detection — 物体検出ぶったいけんしゅつ: The task of locating and classifying objects within an image or video.
  3. Image segmentation — 画像がぞうセグメンテーション: The task of assigning image pixels to meaningful regions or classes.

Classification is a basic vision task, and multimodal AI combines visual information with text, audio, or other modalities.