[Digikam-devel] Re: Face detection

[Marcel Wiesweg]

> I think it really is the first tag I added.
> 
> And those faces confused are already quite well trained, i.e. > 50 pitures
> confirmed for each.

I'll test face recognition. Maybe it simply still doesnt work.


> 
> Here the first checkbox(es) are dark as well.

Dont know. certainly no line of code in digikam for this.

> > 
> > In preview, you'll need to click on the label with the name to open that
> > one for editing again.
> 
> Nothing happens if I click on the label in the preview, neither right nor
> left-click does anything.

This is very strange. When you hover a confirmed face, instead of the combo 
box + confirm + reject widget, there should be a simple text label with the 
confirmed name. The cursor should be a hand cursor, and the label should be 
clickable like a link.

> i.e. train the facerecognition that this is not a face at all.

That would be face detection ("Is it a face?") which is not trained. Only 
recognition ("Who is it?") is trained.

> The picture whose Person 1 tag I removed and which still shows up in the
> Person 1 tag view does not show any mouse-over GUI anymore.

That was a bug now fixed. You should at least be able to edit that from the 
preview mode.


> 
> In preview mode, i.e. clicking on a picture when viewing all pictures with
> People > Person 1 tag, clicking on "add face" does not do anything. So I
> cannot answer this yet.

mouse-hover items - see above.

> 
> This gets me to another point. Would it be possible to not only have
> unknown pictures but groups of unknown, i.e. digikam should be able to
> guess which faces might look the same although it does not know their
> name.

I have already thought of this. No idea if face recognition technology 
availalbe to us is ready for this.

> 
> And also, what happens if a user scans the whole collection and ends up
> with thousands of pictures in unknown? He would have to assign tags to
> each of them and digikam would not try automatically to guess faces again
> after it got some training. So the user would have to know about the
> "recognise again" feature in the scanning GUI. I think there should be
> some smartness in digikam that at least asks after x pictures training for
> a tag whether it should try to find all pictures for that person.

Yes, interesting idea.

> 
> Also, since digikam only uses tags, is it possible to add more to a face,
> i.e. some data about that person, e.g. a photo (as icon for that tag),
> which familiy/group of persons (other persons/tags) he belongs to?

Principally yes, implemented: no. We should aim at integration with Nepomuk / 
PIMO ontologies.


> > Debug statements contain "Check for finish: "
> Should I see this when I run digikam from the konsole?

Yes, once for each package:
digikam(24532)/digikam (core) 
Digikam::FacePipeline::FacePipelinePriv::checkFinished: Check for finish:  13 
packages, 0 infos to filter, hasFinished() false
...
digikam(24532)/digikam (core) 
Digikam::FacePipeline::FacePipelinePriv::checkFinished: Check for finish:  0 
packages, 0 infos to filter, hasFinished() true