Research on Robust Face Recognition Algorithms
In recent years, face recognition algorithms based on deep neural networks have achieved human-level performance when tested on face recognition database. However, when put into real-world application, those algorithms are not robust enough, due to factors such as different lighting conditions, camera distance, and face orientations. In this project, the university team and the partner organization will work together to improve the performance of the partnerâs existing face recognition algorithms, by investigating methods such as triplet loss function, dense facial feature points, and designing novel neural network architectures. The results from this project will improve the competitiveness of the partnerâs product on the market.