| Summary: | Add automatic tags to describe photo contents based on Wikidata taxonomy. | ||
|---|---|---|---|
| Product: | [Applications] digikam | Reporter: | JLZIMMERMANN <osm.jlzimmermann> |
| Component: | Tags-AutoAssignement | Assignee: | Digikam Developers <digikam-bugs-null> |
| Status: | RESOLVED FIXED | ||
| Severity: | wishlist | CC: | caulier.gilles, metzpinguin, quochungtran1999 |
| Priority: | NOR | ||
| Version First Reported In: | 7.8.0 | ||
| Target Milestone: | --- | ||
| Platform: | Microsoft Windows | ||
| OS: | Microsoft Windows | ||
| Latest Commit: | Version Fixed/Implemented In: | 8.3.0 | |
| Sentry Crash Report: | |||
| Attachments: |
image.png
image.png image.png |
||
|
Description
JLZIMMERMANN
2022-09-01 06:07:22 UTC
What exactly should Wikidata support with tags? Describe a specific use case. In the current digiKam-8.0.0 development version, spell checking and automatic translation of comments, titles and more have already been added. Maik Created attachment 151754 [details] image.png Hello, First I give you links of great posts explaining the improvement for professionals using a lot of contents as journalists : http://wikimedia.fi/2016/04/15/yle-3-wikidata/ https://www.bbc.co.uk/blogs/bbcinternet/2012/04/sports_dynamic_semantic.html https://av.tib.eu/media/52305 The IPTC organization has published that wikidata can help photodescription here https://iptc.org/news/wikidata/ An example : I describe a church in Orange named "église Saint Florent", the photo has relic of "Saint florent" it would be easier to be able simply to add the items of wikidata that already exists : église Saint Florent <https://www.wikidata.org/wiki/Q3581446> Saint Florent <https://www.wikidata.org/wiki/Q93327041> relica <https://www.wikidata.org/wiki/Q187616> [image: image.png] Other use case Disabilities, here a person using wheelchair [image: image.png] I use a lot OpenStreetMap and we need pictures to help mapping parking spaces. This is why I pushish a lot of these pictures in Flickr <https://www.flickr.com/photos/jeanlouis_zimmermann/collections/72157635264003472/> (>50 k pictures) to help people to understand the disability typology. [image: image.png] As you can see here <https://www.flickr.com/photos/jeanlouis_zimmermann/9506213460/in/album-72157635218860720/>I would spend a lot of time to push all tags in every languages wikidata would help me to get an international tagging. Wishing this answer gives more explanation, Regards Jean-Louis ZIMMERMANN OpenStreetMap community & Wikidata lover ;-) Le jeu. 1 sept. 2022 à 08:27, Maik Qualmann <bugzilla_noreply@kde.org> a écrit : > https://bugs.kde.org/show_bug.cgi?id=458592 > > Maik Qualmann <metzpinguin@gmail.com> changed: > > What |Removed |Added > > ---------------------------------------------------------------------------- > CC| |metzpinguin@gmail.com > > --- Comment #1 from Maik Qualmann <metzpinguin@gmail.com> --- > What exactly should Wikidata support with tags? Describe a specific use > case. > > In the current digiKam-8.0.0 development version, spell checking and > automatic > translation of comments, titles and more have already been added. > > Maik > > -- > You are receiving this mail because: > You reported the bug. Created attachment 151755 [details]
image.png
Created attachment 151756 [details]
image.png
Hi, With next digiKam 8.3.0 release, the auto-tags assignment feature have been implemented without using a cloud service. The processing is done in core application with delegate neural network models stored in computer. For more details about auto-tags assignment feature, look on student work report : https://community.kde.org/GSoc/2023/StatusReports/QuocHungTran#Add_Automatic_Tags_Assignment_Tools_and_Improve_Face_Recognition_Engine_for_digiKam Best regards Gilles Caulier |