DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on

What is Computer Vision? (1)

Buy Me a Coffee

Computer Vision is the technology which enables a computer to understand and analyze the visual things such as images, videos, etc.

There are many Computer Vision technologies as shown below:

(1) Classification(Recognition):

  • can classify an entire image, video, etc into one or more classes(labels) from one or more classes(labels).
  • can be more specifically called Image Classification(Recognition), Video Classification(Recognition), Object Classification(Recognition), etc.
  • has the method Single-Label Classification which has two methods Binary Classification and Multi-Class Classification.
  • has the method Multi-Label Classification.

*Memos:

  • Binary Classification can classify an entire image, video, etc into a single class(label) from two classes(labels).
  • Multi-Class Classification can classify an entire image, video, etc into a single class(label) from more than two classes(labels).
  • Multi-Label Classification can classify an entire image, video, etc into multiple classes(labels) from more than two classes(labels).

Image description

(2) Localization:

  • can localize the multiple objects and interesting regions in an image, video, etc with bounding boxes.
  • can be more specifically called Image Localization and Video Localization, Object Localization, etc.

Image description

(3) Detection:

  • can localize and classify the objects and interesting regions in an image, video, etc with classes(labels) and bounding boxes.
  • is the combination of Object Localization and Classification(Recognition).
  • can be more specifically called Image Detection, Video Detection, Object Detection, etc.

Image description

(4) Segmentation:

  • can do Object Detection more precisely, differentiating stuff and things with colors: *Memos:
    • Stuff is uncountable things(classes) such as sky, sea, forrest, road, grass, landscape, etc.
    • Things are countable things(classes) such as car, tree, person, animal, flower, etc.
  • can be more specifically called Image Segmentation and Video Segmentation, Object Segmentation, etc.
  • has the popular methods Semantic Segmentation, Instance Segmentation and Panoptic segmentation: *Memos:
    • Semantic Segmentation is good at differentiating stuff but not good at differentiating things.
    • Instance Segmentation is good at differentiating things but not good at differentiating stuff.
    • Panoptic segmentation:
    • is good at differentiating both stuff and things.
    • is the combination of Semantic Segmentation and Instance Segmentation.

Image description

Image description

Image description

Top comments (0)