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
- from schema: https://w3id.org/lmodel/iso22989
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.