Hello
First of all I have to apologise, I’m a novice at this kind of discussion and I’m not even an in-depth Digikam user.
I’ve moved to digikam from google picasa because a have a huge protos database with plenty of faces properly recognised and tagged, and I love the picasa face recognition feature.
I’ve imported this database into Digikam, but I have to say that now digikam face recognition is very seldom giving proper answers.
I read into Digikam manual that “Face recognition only works well with faces that have been automatically detected by digiKam, not with manually drawn face rectangles or faces from other programs.”
could be this the reason of this behaviour?
Since during last years of use I’ve increased the digikam database from the imported one, is there the possibility of training the deep-learning face recognition engine from areduced set of pictures, without anyway removing tags?
many thanks