Bug 402021

Summary:	face recognition not working
Product:	[Applications] digikam	Reporter:	achatssurnet
Component:	Faces-Recognition	Assignee:	Digikam Developers <digikam-bugs-null>
Status:	RESOLVED FIXED
Severity:	normal	CC:	caulier.gilles, metzpinguin
Priority:	NOR
Version First Reported In:	5.9.0
Target Milestone:	---
Platform:	Microsoft Windows
OS:	Microsoft Windows
Latest Commit:		Version Fixed/Implemented In:	7.0.0
Sentry Crash Report:

Description achatssurnet 2018-12-11 20:59:25 UTC

SUMMARY
After the detection of faces and after setting some faces for several names (labels) , when i run again the face recognition (even by deleting the db), there is no proposition and it takes less than 1s to run. It seems that face recognition does not work.

any idea ? I use windows 7

STEPS TO REPRODUCE
1. 
2. 
3. 

OBSERVED RESULT


EXPECTED RESULT


SOFTWARE/OS VERSIONS
Windows: 7


ADDITIONAL INFORMATION

Comment 1 Maik Qualmann 2018-12-11 21:10:12 UTC

Which face recognition mode did you choose? Only the LBP algorithm will give useful results if you have 2-5 images training per person.

Maik

Comment 2 achatssurnet 2018-12-12 07:56:22 UTC

Hello
Good question !
I dont know which recognition mode , i have nt see any options in the interface.
Could you tell me how To check it ?

Comment 3 caulier.gilles 2019-12-23 15:19:31 UTC

7.0.0-beta1 is out with new Face Recognition algorithm based on Deep
Learning/Neural Network API from OpenCV

https://download.kde.org/unstable/digikam/

Please test and give us a feedback

Thanks in advance
Gilles Caulier

Comment 4 achatssurnet 2019-12-24 07:56:20 UTC

Hello
Thank you for your support
I Will test this new version when i Will cime jack to my home.
I Will give you a feedback.
Laurent

Comment 5 caulier.gilles 2019-12-25 15:21:21 UTC

See the Neural Network example from digiKam 7.0.0-beta1 performing faces recognition with 2 items face-tagged in first.

https://i.imgur.com/HHF4T9X.png

1 new item is recognized, name-tagged, highlighted with green frame, and linked in "unconfirmed" virtual tag for confirmation.

Recognition work well using Deep Learning. I close this file now.

Merry Christmas and Happy new year.

Gilles Caulier