[IMGREC-19] Re-run image recognition on demand Created: 05/Sep/18  Updated: 26/Aug/22

Status: Open
Project: Image Recognition
Component/s: None
Affects Version/s: None
Fix Version/s: None

Type: Improvement Priority: Neutral
Reporter: Antti Hietala Assignee: Unassigned
Resolution: Unresolved Votes: 0
Labels: None
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified

Template:
Acceptance criteria:
Empty
Task DoD:
[ ]* Doc/release notes changes? Comment present?
[ ]* Downstream builds green?
[ ]* Solution information and context easily available?
[ ]* Tests
[ ]* FixVersion filled and not yet released
[ ]  Architecture Decision Record (ADR)
Epic Link: ImgRec Later
Team: AuthorX

 Description   

Provide a way to re-run image recognition and tagging if the first batch-recognition did not give good results.

User story:

As a practitioner, I tried Magnolia's local image recognition service but the results were poor. Magnolia failed to recognize and tag many of my images. I have now configured Amazon Rekognition and want to re-run image recognition to get better tags. 

Acceptance criteria:

  • Provide a practitioner-accessible way to re-run image recognition.
  • Provide a way to re-run image recognition:
    • on assets that have no tags.
    • on all assets.

Nice-to-have criteria:

  • Avoid having to restart the Magnolia instance. The user may want to adjust the confidence score threshold and re-run the recognition. Having to restart the instance feels like overkill.

Generated at Mon Feb 12 02:08:44 CET 2024 using Jira 9.4.2#940002-sha1:46d1a51de284217efdcb32434eab47a99af2938b.