Faces are detected, but not recognised. This is the error I get when launched on the command line. --- Digikam::DetectionWorker::process: Found 1 faces in "P7123086.ORF" QSize(2400, 3200) QSize(3472, 4640) OpenCV(3.4.1) Error: Bad argument (This LBPH model is not computed yet. Did you call the train method?) in predict, file /b/dktemp/digikam-master/core/libs/facesengine/recognition-opencv-lbph/facerec_borrowed.cpp, line 376 Digikam::RecognitionDatabase::recognizeFaces: cv::Exception: OpenCV(3.4.1) /b/dktemp/digikam-master/core/libs/facesengine/recognition-opencv-lbph/facerec_borrowed.cpp:376: error: (-5) This LBPH model is not computed yet. Did you call the train method? in function predict --- Tested with appimage on Fedora 28 and CentOS 7.4
This is not a real error message and no bug. There are no entries in the face database. In order for faces to be recognized, they must train the database by entering a few names for the found faces. Maik
After 3 weeks of work, i finally completed the compilation of AppImage using Qt 5.11.3 + QWebkit 5.212. New 6.1.0 pre-release AppImage bundle can be found here (64 bits only for the moment) : https://files.kde.org/digikam/ Please check if this bugzilla entry still valid. Thanks in advance Gilles Caulier
This is not an error, the database has to be trained to get results. I close the bug now. Maik