Proposal for the DigiKam DNN based Faces Recognition Improvements project

digiKam is a famous open source photo management software. With a huge effort, the developers of digiKam have implemented face detection and facial recognition features in a module called faces engine. This module implements different methods to scan faces and then label them based on the pre-tagged photos given by users.

The most recent methods used in the faces engine use Convolution Neural Network (CNN) based algorithms for facial detection and recognition. Since Google Summer of Code 2019, with the excellent work of Thanh Trung Dinh[1], the SSD-MobileNet and YOLO algorithms for face detection, and OpenFace for facial recognition have been implemented using OpenCV DNN. His work has achieved a great precision in face detection and facial recognition. However, there still are some issues that affect the performance of the facial engine. Therefore, the objective of this project is to improve the performance of the digiKam faces engine.