[digiKam-users] a wild idea or wish

[neinei at gmx.net]

I would like to second this.
Some sort of "object detection" would be a great addition to DigiKam.
For example, "OwnPhoto" claims to have it already implemented "Detect
objects in photos, and make them searchable by objects" using Object
detection: densecap, places365. See https://github.com/hooram/ownphotos
However the development of OwnPhoto seems somehow stuck in 2019 and it
might exist a fork already.
"Photoprism" seems an alternative using some AI stuff for image
classification, see:
https://docs.photoprism.org/developer-guide/metadata/classification/ and
in more general https://github.com/photoprism/photoprism
So, somehow object detection seems to be implemented in some open source
products.


On 7/27/20 10:48 PM, Daniel Bauer wrote:
> I have no idea if this is possible, if the necessary AI exits
> opensource, but as there is face-recognition in digikam, I dare to throw
> in my idea:
>
> google, facebook and others can recognize the contents of images. If
> it's a house, a portrait, a beach, a tree, if male/female, if she has
> nipples or if cheeks are visible (no joke, both facebook and google can
> and do - with lots of errors, though),  etc.
>
> Would it be possible that digikam can analyze and categorize images and
> make them searchable by content? So that they are searchable by content.
>
> That would be fantastic. Imagine!