Projects on Visual Forensics and Biometrics with Sino-Singapore International Joint Research Institute (SSIJRI)

Sino-Singapore International Joint Research Projects (Phase 1)

Project title: User Oriented Biometric Authentication Technology for Financial Services

Partners: South China University of Technology (SCUT), Sino-Singapore International Joint Research Institute (SSIJRI), and GRG Banking (GRG)

Description: The objective of this project is to develop a reliable biometric authentication system for e-commerce applications, including

1) scalable face spoofing detection algorithm based on advanced machine learning and deep learning technologies;

2) reliable low-quality finger vein recognition based on adaptive image enhancement and multi-scale deep neural networks.

Duration: 1/Aug/2017-31/July/2020

Project Outcomes:  

• 6 papers published
• In discussions with partners for filing of up to 5 patents

Publications:

[1] Alfasly Saghir, Beibei Liu, Yongjian Hu, et al. Auto-Zooming CNN-Based Framework for Real-Time Pedestrian Detection in Outdoor Surveillance Videos. IEEE Access. 2019, 7: 105816-105826.

[2] Yufei Wang, Yongjian Hu, Alan Wee-Chung Liew, and Chang-Tsun Li. ENF Based Video Forgery Detection Algorithm. International Journal of Digital Crime and Forensics. 2020, 12(1): 131-156.

[3] Haoliang Li, Sinno Jialin Pan, Shiqi Wang, Alex C. Kot. Heterogeneous Domain Adaptation via Nonlinear Matrix Factorization, IEEE Transactions on Neural Networks and Learning Systems. 2020, 31(3): 984-996.

[4] Yufei Wang, Yongjian Hu, Alan W. C. Liew, et al. Weakly Supervised Video Object Segmentation, TENCON 2018-2018 IEEE Region 10 Conference. IEEE, 2018: 315-320

[5] Haoliang Li, Wen Li, Hong Cao, Shiqi Wang, Feiyue Huang, and Alex C. Kot. "Unsupervised domain adaptation for face anti-spoofing." IEEE Transactions on Information Forensics and Security 13 no. 7 (2018): 1794-1809.

[6] Haoliang Li, Peisong He, Shiqi Wang, Anderson Rocha, Xinghao Jiang, and Alex C. Kot. "Learning generalized deep feature representation for face anti-spoofing." IEEE Transactions on Information Forensics and Security 13, no. 10 (2018): 2639-2652.

Team from NTU, SCUT and SSIJRI visiting GRG Banking

________________________________________________________________________________________________________________________________________________________

Sino-Singapore International Joint Research Projects (Phase 2)

Project title:  Face Spoofing Detection based on Self-Service System

Partners: South China University of Technology, Sino-Singapore International Joint Research Institute

Description: We focus on studying a more robust face verification technique by incorporating a face spoofing detection module into the self-service banking terminal systems. In particular, we aim to design a novel and practical face spoofing detection module by leveraging the advantage of biometric security, computer vision and machine learning.

Duration: 1/Jan/2019-1/Jan/2021

Project Outcomes:  

• 5 papers published
• In discussions with partners for filing of up to 9 patents

Publications:

[1] Alfasly Saghir, Yongjian Hu, Haoliang Li, et al. Multi-Label-Based Similarity Learning for Vehicle Re-Identification, IEEE Access. 2019, 7: 162605-162616.

[2] Yixiang Xie, Yan Wang, Yongjian Hu, et al. Cross-Camera Person Re-Identification With Body-Guided Attention Network, IEEE Sensors Journal. 2019, 20(1): 359- 368.

[3] Alfasly Saghir, Yongjian Hu, Tiancai Liang, et al. Variational Representation Learning for Vehicle Re-Identification, 2019 IEEE International Conference on Image Processing. IEEE, 2019: 3118-3122.

[4] Zhi Li, Haoliang Li, Kwok-Yan Lam, Alex C. Kot. Unseen Face Presentation Attack Detection with Hypersphere Loss, 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2020

 [5] Yufei Wang, Haoliang Li, Alex C. Kot. Heterogeneous Domain Generalization via Domain Mixup, 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 2020