Skip to content

Enum: ComputerVisionTask

Computer-vision tasks drawn from Clauses 3.7 and 9.1.

URI: iso22989:ComputerVisionTask

Permissible Values

Value Meaning Description
image_classification None Assigning a class label to an image
object_detection None Localising and classifying objects within an image
semantic_segmentation None Assigning a class label to each pixel in an image
instance_segmentation None Assigning labels to pixels grouped by individual object instance
image_recognition None General recognition of image content, including faces and scenes
pose_estimation None Estimating the spatial pose of objects or persons
optical_character_recognition None Extracting machine-readable text from images of printed or handwritten conten...
face_recognition None Identifying or verifying persons from facial images (Clause 3
scene_recognition None Classifying the type of scene or environment depicted in an image
motion_tracking None Following the position of objects across successive frames in video
visual_anomaly_detection None Identifying visual patterns that deviate from expected behaviour
three_d_reconstruction None Recovering three-dimensional structure from one or more images
action_recognition None Recognising discrete actions performed in video
activity_recognition None Recognising higher-level activities composed of multiple actions in video

Slots

Name Description
cv_task Type of computer-vision task (Clause 9

In Subsets

Identifier and Mapping Information

Schema Source

LinkML Source

name: ComputerVisionTask
description: Computer-vision tasks drawn from Clauses 3.7 and 9.1.
in_subset:
- terminology
from_schema: https://w3id.org/lmodel/iso22989
rank: 1000
permissible_values:
  image_classification:
    text: image_classification
    description: Assigning a class label to an image.
  object_detection:
    text: object_detection
    description: Localising and classifying objects within an image.
  semantic_segmentation:
    text: semantic_segmentation
    description: Assigning a class label to each pixel in an image.
  instance_segmentation:
    text: instance_segmentation
    description: Assigning labels to pixels grouped by individual object instance.
  image_recognition:
    text: image_recognition
    description: General recognition of image content, including faces and scenes.
  pose_estimation:
    text: pose_estimation
    description: Estimating the spatial pose of objects or persons.
  optical_character_recognition:
    text: optical_character_recognition
    description: Extracting machine-readable text from images of printed or handwritten
      content.
  face_recognition:
    text: face_recognition
    description: Identifying or verifying persons from facial images (Clause 3.7.2).
  scene_recognition:
    text: scene_recognition
    description: Classifying the type of scene or environment depicted in an image.
  motion_tracking:
    text: motion_tracking
    description: Following the position of objects across successive frames in video.
  visual_anomaly_detection:
    text: visual_anomaly_detection
    description: Identifying visual patterns that deviate from expected behaviour.
  three_d_reconstruction:
    text: three_d_reconstruction
    description: Recovering three-dimensional structure from one or more images.
  action_recognition:
    text: action_recognition
    description: Recognising discrete actions performed in video.
  activity_recognition:
    text: activity_recognition
    description: Recognising higher-level activities composed of multiple actions
      in video.