Kim, KangGeon Chang, Feng-Ju Choi, Jongmoo Morency, Louis-Philippe Nevatia, Ramakant Medioni, Gerard 2024-01-12T06:13:46Z 2024-01-12T06:13:46Z 2023-02-09 2017-06-02 https://pubs.kist.re.kr/handle/201004/79510 A key to successful face recognition is accurate and reliable face alignment using automatically-detected facial landmarks. Given this strong dependency between face recognition and facial landmark detection, robust face recognition requires knowledge of when the facial landmark detection algorithm succeeds and when it fails. Facial landmark confidence represents this measure of success. In this paper, we propose two methods to measure landmark detection confidence: local confidence based on local predictors of each facial landmark, and global confidence based on a 3D rendered face model. A score fusion approach is also introduced to integrate these two confidences effectively. We evaluate both confidence metrics on two datasets for face recognition: JANUS CS2 and IJB-A datasets. Our experiments show up to 9% improvements when face recognition algorithm integrates the local-global confidence metrics. English IEEE Local-Global Landmark Confidences for Face Recognition Conference 10.1109/fg.2017.84 1 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp.666 - 672 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) 666 672 US Washington, DC, DC, USA 2017-05-30 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) 000414287400090