Andrew Beng Jin Teoh
Yonsei University
297 Papers
1.4K Citations
Andrew Beng Jin Teoh is an academic researcher from Yonsei University. The author has contributed to research in topics: Biometrics & Computer science. The author has an hindex of 39, co-authored 242 publications. Previous affiliations of Andrew Beng Jin Teoh include Multimedia University & Wuhan University.
Chat about Author
Papers
Photogrammetry
Masaki Watanabe,David Zhang,Vivek Kanhangad,Laura L. Liu,Andrew Beng Jin Teoh,Shiguang Shan,Xilin Chen,Wen Gao,Jihyeon Jang,Hale Kim,M. Thieme,Ted Tomonaga,David J. Hurley,M. S. Nixon,T. Sim,Frank E. Pollick +15 more
PalmHashing: A novel approach for dual-factor authentication
TL;DR: The proposed PalmHashing technique is able to produce zero equal error rate (EER) and yields clean separation of the genuine and imposter populations, so the false acceptance rate (FAR) can be eliminated without suffering from the increased occurrence of the false rejection rate (FRR).
Nearest Neighbor Guidance for Out-of-Distribution Detection
TL;DR: This work proposes a method called Nearest Neighbor Guidance (NNGuide) that guides the classifier-based score to respect the boundary geometry of the data manifold, reducing the overconfidence of OOD samples while preserving the fine-grained capability of the classifier-based score.
An analysis on equal width quantization and linearly separable subcode encoding-based discretization and its performance resemblances
TL;DR: This article aims to bridge the gap between continuous and Hamming domains, and provides a revelation upon how discretization based on equal-width quantization and linearly separable subcode encoding could affect the classification performance in the Hamming domain.
Conjugate 2DPalmHash code for secure palm-print-vein verification
Lu Leng,Ming Li,Andrew Beng Jin Teoh +2 more
- 01 Dec 2013
TL;DR: Conjugate 2DPalmHash Code (CTDPHC) is proposed as a cancelable multi-modal biometric that enjoys higher verification accuracy and stronger anti-counterfeit ability, while trades neither computational complexity nor storage cost.