Tutorial 1 Trustworthy biometrics

Organizers: Weihong Deng, Baoyuan Wu, Jing Dong, Yuezun Li

Presenter bios:
Prof. Weihong Deng http://www.whdeng.cn/ received the B.E. degree in information engineering and the Ph.D. degree in signal and information processing from the Beijing University of Posts and Telecommunications (BUPT), Beijing, China, in 2004 and 2009, respectively. From Oct. 2007 to Dec. 2008, he was a postgraduate exchange student in the School of Information Technologies, University of Sydney, Australia. He is currently a professor in School of Artificial Intelligence, BUPT. His research interests include computer vision and affective computing, with a particular emphasis in face recognition and expression analysis. He has published over 100 technical papers in international journals and conferences, such as IEEE TPAMI, TIP, IJCV, CVPR and ICCV. He serves as area chair for major international conferences such as IJCB, FG, IJCAI, ACMMM, and ICME, and guest editor for IEEE TBIOM, and Image and Vision Computing Journal and the reviewer for dozens of international journals, such as IEEE TPAMI, TIP, TIFS, TNNLS, TMM, IJCV, PR / PRL. His Dissertation titled “Highly accurate face recognition algorithms” was awarded the Outstanding Doctoral Dissertation Award by Beijing Municipal Commission of Education in 2011. He has been supported by the program for New Century Excellent Talents in 2014, Beijing Nova in 2016, Young Chang Jiang Scholar in 2020.

Prof. Baoyuan Wu https://sites.google.com/site/baoyuanwu2015/. Currently, I am Associate Professor of School of Data Science, the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen). I am leading the Secure Computing Lab of Big Data (SCLBD), Shenzhen Research Institute of Big Data (SBRID). From November 2016 to August 2020, I was a Senior and Principal Researcher at Tencent AI lab.  From  August  2014  to  November  2016,  I  was a  Postdoc in  KAUST,  working with  Prof.  Bernard Ghanem. On June 2014, I received the Ph.D. degree from the National Laboratory of Pattern  Recognition,  Institute of  Automation,  Chinese  Academy of  Sciences,  supervised by  Prof.  Baogang  Hu.  I  was a  visiting student in  Prof.  Qiang  Ji’s lab of  Rensselaer  Polytechnic  Institute, from Sept. 2011 to Sept. 2013. My research interests are machine learning, computer vision, and optimization, including deep learning,  model compression,  visual reasoning,  image annotation,  weakly/unsupervised learning, structured prediction, probabilistic graphical models, video processing, and integer programming.  Recently,  I  am especially interested in  AI  security and privacy,  such as adversarial examples, backdoor attacks and defenses, federal learning.

Prof. Jing Dong http://cripac.ia.ac.cn/people/jdong/en/ ,  associate researcher,  master tutor,  director  of  “Artificial  Intelligence  and  Robot Education Joint Laboratory” of CASIA Intelligent Star. Mainly engaged in the research work of pattern recognition and image processing,  computer vision,  multimedia content security, has published nearly 50 academic papers in international authoritative journals and academic conferences,  applied for  18  invention patents and software copyright,  has authorized  11  patents,  3  international patent.  She presided over or mainly participated in more than  30  national and provincial scientific research projects,  such as the  National  863  plan,  the  973  Plan,  the science and technology support plan,  the key  R  &  D  plan,  and the  National  Natural  Science  Foundation.  She is a  member of the youth innovation promotion association of the Chinese Academy of Sciences and the American Institute of Electrical and Electronic Engineers (IEEE) Senior member, an outstanding member of China artificial intelligence society; Deputy Secretary-General, and director of China Artificial Intelligence Society (2014 present);  Deputy  Secretary-General and director of  China  Image  Graphics  Society  (2016  present).

Dr. Yuezun Li https://yuezunli.github.io/, is a lecturer in the Center on Artificial Intelligence, at Ocean University of China. I was a Senior Research Scientist at the Department of Computer Science and Engineering of University at Buffalo, SUNY, working with Prof. Siwei Lyu from 2020.09 to 2020.12. I received Ph.D. degree in computer science at University at Albany, SUNY in 2020. My Ph.D supervisor is Prof. Siwei Lyu. I received M.S. degree in Computer Science in 2015 and B.S. degree in Software Engineering in 2012 at Shandong University. My research interest is mainly focused on computer vision and multimedia forensics.

Abstract: With the wide application of biometrics systems and person analysis systems, it is becoming more and more important to ensure their trustworthiness. Untrustable biometrics systems can cause serious ethics and security problems, some of which are newly emerging and quickly gaining tremendous attentions. To name a few, facial recognition and analysis methods may be subject to bias and uncertainty, biometrics systems can be failed under adversarial attacks, imagery of people can maliciously tamper,  and recently  Deepfakes pose a  serious problem against media trustworthiness. In this tutorial, we give a selected coverage on these issues,  featuring detailed introduction on the causes,  treatments,  and prospects of these problems.  We believe that this tutorial is of interest to a  substantial part of the  IJCB  2020  audience.

Prerequisites: The tutorial requires basic knowledge in graduate-level pattern recognition and computer vision. Specifically, the audience should know basic concepts in facial analysis, deep learning, and optimization. We think almost all participants of IJCB have the prerequisite knowledge.

Tutorials session topics:

Session 1: Fairness Problems in Face Recognition

Presented by: Prof. Weihong Deng
Estimated duration: 45 mins

Associated literature:

[1] Mitigating Bias in Face Recognition using Skewness-Aware Reinforcement Learning, Mei Wang, Weihong Deng, CVPR 2020

[2] Racial Faces in-the-Wild:  Reducing  Racial  Bias  by  Information  Maximization  Adaptation Network, Mei Wang, Weihong Deng, et al., ICCV 2019.

[3] A  Deeper  Look  at  Facial  Expression  Dataset  Bias,  S  Li,  W  Deng, IEEE  Transactions  on  Affective Computing 2020

[4] Deep Face Recognition: A survey, Mei Wang, Weihong Deng, Neurocomputing, 2021 [5]  Deep Face Expression Recognition: A Survey, Shan Li, Weihong Deng, IEEE Transactions on Affective Computing 2020

Session 2: Security of Deep Learning: Adversarial attacks and Defenses

Presented by: Prof. Baoyuan Wu
Estimated duration: 45 mins

Associated literature:

[1]  Efficient  Decision-based  Black-box  Adversarial  Attacks  on  Face  Recognition,  Yinpeng  Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang and Jun Zhu, CVPR 2019

[2]  Boosting  Decision-based  Black-box  Adversarial  Attacks  with  Random  Sign  Flip,  Weilun  Chen, Zhaoxiang Zhang, Xiaolin Hu, Baoyuan Wu, ECCV 2020.

[3]  Sparse  Adversarial  Attack  via  Perturbation  Factorization,  Yanbo  Fan*,  Baoyuan  Wu*,  Tuanhui Li, Yong Zhang, Mingyang Li, Zhifeng Li, Yujiu Yang, ECCV 2020.

[4] Backdoor Attack with Sample-Specific  Triggers.  Yuezun  Li,Yiming  Li,  Baoyuan  Wu,  Longkang Li, Ran He, Siwei Lyu. Arxiv 2021.

[5] Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits. Jiawang Bai, Baoyuan Wu, Yong Zhang, Yiming Li, Zhifeng Li, Shutao Xia. ICLR 2021.

[6]  TediGAN:  Text-Guided  Diverse  Face  Image  Generation  and  Manipulation,  Weihao  Xia,  Yujiu Yang, Jing-Hao Xue, Baoyuan Wu, CVPR 2021. [7]  Prototype-supervised  Adversarial  Network  for  Targeted  Attack  of  Deep  Hashing.  Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu. CVPR 2021.

Session 3: Person-Centric Image and Video Forensics

Presented by: Prof. Jing Dong
Estimated duration: 45 mins

Associated literature:

[1] “Optimized 3D Lighting Environment Estimation for Image Forgery Detection,” Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, IEEE Transactions on Information Forensics and Security, vol. 12, no. 2, pp. 479-494, Feb. 2017.

[2] “Image Forensics Based on Planar Contact Constraints of 3D Objects,” Bo Peng, Wei Wang, Jing Dong and Tieniu Tan, IEEE Transactions on Information Forensics and Security, vol. 13, no. 2, pp. 377-392, Feb. 2018.

[3] Position Determines Perspective: Investigating Perspective Distortion for Image Forensics of  Faces,  Bo  Peng,  Wei  Wang,  Jing  Dong  and  Tieniu  Tan,  CVPR  2017  Media  Forensics  Workshop

[4] “Robust Face-Swap Detection Based on 3D Facial Shape Information”, Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan, arXiv, 2021

[5] MUST-GAN:  Multi-level  Statistics  Transfer  for  Self-driven  Person  Image  Generation,  Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong, CVPR2021. [6] Exploring Adversarial Fake Images on Face Manifold, Dongze Li, Wei Wang,Hongxing Fan, Jing Dong, CVPR2021.

Session 4: Detecting AI-synthesized Faces

Presented by: Dr. Yuezun Li
Estimated duration: 45 mins

Associated literature:

[1] DeepFake-o-meter: An Open Platform for DeepFake Detection, Yuezun Li,Cong Zhang, Pu  Sun,  Lipeng  Ke,  Yan  Ju,  Honggang  Qi  and  Siwei  Lyu.  Systematic Approaches to Digital Forensic Engineering, in conjunction with the IEEE Security and Privacy Smposium, 2021.

[2] Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights, Shu Hu, Yuezun Li  and  Siwei  Lyu.  IEEE International Conference on  Acoustics,  Speech,  and  Signal  Processing (ICASSP), 2021.

[3] Landmark  Breaker:  Obstructing  DeepFake  By  Disturbing  Landmark  Extraction,  Pu  Sun*,  Yuezun  Li*,  Honggang  Qi  and  Siwei  Lyu.  IEEE International Workshop  on  Information Forensics and Security (WIFS), 2020.

[4]    Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics, Yuezun Li, Xin Yang, Pu Sun, Honggang Qi and Siwei Lyu. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[5] Exposing DeepFake Videos By Detecting Face Warping Artifacts, Yuezun Li and Siwei Lyu. IEEE  International  Conference  on  Computer  Vision  and  Pattern  Recognition  Workshop  (CVPRW), 2019.

[6]  Exposing  GAN-synthesized  Faces  Using  Landmark  Locations,  Xin  Yang,  Yuezun  Li,  Honggang Qi and Siwei Lyu. ACM Workshop on Information Hiding and Multimedia Security (IHMMSec), 2019. [7] Exposing Deep Fakes Using Inconsistent Head Poses, Xin Yang*, Yuezun Li* and Siwei Lyu. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.


Tutorial 2 Face Analysis beyond Recognition

Organizers: Zhen Lei, Weihong Deng, Hu Han, Xiaopeng Hong, Qijun Zhao, Di Huang

Presenter bios:
Zhen Lei, IEEE Senior Member, received the BS degree in automation from the University of Science and Technology of China (USTC) in 2005 and the PhD degree from the Institute of Automation, Chinese Academy of Sciences (CASIA) in 2010. He is currently a professor at the National Laboratory of Pattern Recognition (NLPR) and the director of the Center for Biometrics and Security Research (CBSR), Institute of Automation (CASIA). His research interest includes pattern recognition and machine learning, image and vision processing, face recognition and video analytics. He has published over 180 papers in international journals and conferences,  including top  journals like  IEEE  T-PAMI,  T-IP,  T-CSVT, IJCV etc. and top vision conferences like ICCV, CVPR, ECCV. His work has been cited more than 16,000 times (by Google Scholar, with H-index: 62). He holds 18 invention patents and has drawn up 7 standards of public security. Zhen Lei is an expert in face recognition, biometrics, and intelligent video surveillance. He has  been  awarded the  IAPR Young Biometrics Investigator  Award,  given  to  a  single researcher worldwide every two years under the age of 40, whose research work has had a major  impact  in  biometrics.  He serves as associate editor  for journals  of  Neurocomputing and IET Computer Vision. He was the area editor of Encyclopedia of Biometrics, was the guest editor of special issue of neurocomputing and IET computer vision. He is/was the area chair of BTAS-2018, International Conference on Biometrics (ICB 2014-2016, 2018) and the area chair of 2015 IEEE Conference on Automatic Face and Gesture Recognition. He received the Best Student Paper in ICB-2006, 2014 and 2015, the Best Paper in ICB-2007, the Best  Student  Paper  Honorable  Mention  in  FG-2013,  the  Best  Student  Paper  Honorable Mention in ICME-2018. He won the competition of facial micro-expression recognition in FG-2017,  won  the  300-w  face  landmark  localization  held  in  ICCV-2013,  won  the  face liveness detection in ICB-2011 and 2013.
Weihong Deng received the B.E. degree in information engineering and the Ph.D. degree in signal and information processing from the Beijing University of Posts and Telecommunications (BUPT), Beijing, China, in 2004 and 2009, respectively. From Oct. 2007 to Dec. 2008, he was a postgraduate exchange student in the School of Information Technologies, University of Sydney, Australia. He is currently a professor in School of Artificial Intelligence, BUPT. His research interests include computer vision and affective computing, with a particular emphasis in face recognition and expression analysis. He has published over 100 technical papers in international journals and conferences, such as IEEE TPAMI, TIP, IJCV, CVPR and ICCV. He serves as area chair for major international conferences such as IJCB, FG, IJCAI, ACMMM, and ICME, and guest editor for IEEE TBIOM, and Image and Vision Computing Journal and the reviewer for dozens of international journals, such as IEEE TPAMI, TIP, TIFS, TNNLS, TMM, IJCV, PR / PRL. His Dissertation titled “Highly accurate face recognition algorithms” was awarded the Outstanding Doctoral Dissertation Award by Beijing Municipal Commission of Education in 2011. He has been supported by the program for New Century Excellent Talents in 2014, Beijing Nova in 2016, Young Chang Jiang Scholar in 2020.
Hu Han is an Associate Professor of the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). He received the B.S. degree from Shandong University, and the Ph.D. degree from ICT, CAS, in 2005 and 2011, respectively, both in computer science. He was a Research Associate in the PRIP Lab at Michigan State University, and a visiting researcher at Google in Mountain View from 2011 to 2015. His research interests include computer vision, pattern recognition, and biometrics. Hehas published more than 70 pa-pers in journal and conference including IEEE Trans. PAMI, IEEE Trans. IP, IEEE Trans. IFS, IEEE Trans. BIOM, Pattern Recognition, CVPR, NeurIPS, ECCV, MICCAI, with more than 3600 Google Scholar citations. He is/was the Associate Editor of Pattern Recognition, Area Chair of ICPR2020, and Senior Program Committee members of IJCAI2021. He was a recipient of the 2020 IEEE Signal Processing Society Best Paper Award, 2019 IEEE FG Best Poster Presentation Award, and 2016/2018 CCBR Best Student/Poster Award. He is/was an organizer of a number of special sessions and workshops in ICCV2021/CVPR2020/FG2020/WACV2020/FG2019/BTAS2019.
Xiaopeng Hong is a distinguished research fellow at Xi’an Jiaotong University, PRC. He had been a senior researcher/adjunct professor with University of Oulu, Finland until 2019.He has authored over 50 articles in top-tier journals and conferences such as IEEE T-PAMI and CVPR. He has served as an area chair/SPC for ACM MM 21/20, AAAI 21 and IJCAI21, and a guest editor for Signal, Image and Video Processing. His current research interests include visual surveillance, continual learning, robotic planning, and micro-expression analysis. His studies about subtle facial movement analysis have been reported by International media like MIT Technology Review and been awarded the IEEE Finland Section best student conference paper of 2020.
Qijun Zhao is currently a professor of computer science at Sichuan University, and a vis-iting professor at Tibet University. His research interests lie in the fields of biometrics and computer vision. He has been focusing on 3D face modeling and perception, and animal biometrics in recent years. He has published about 100 academic papers, and been granted with 8 patents. He served as program co-chair for CCBR2016, ISBA2018 and NCIG2022, and face recognition area co-chair for BTAS2018 and IJCB2021.
Di Huang is a Professor at School of Computer Science and Engineering, Beihang University, Beijing, China. He received the B.S. and M.S. degrees in computer science from Beihang University, Beijing, China, and the Ph.D. degree in computer science from the Ecole Centrale de Lyon, Lyon, France, in 2005, 2008, and 2011, respectively. His current research interests include biometrics, in particular on 2D/3D face analysis, image/video processing, and pattern recognition. In recent years, he has published more than 80 academic papers at major journals and conferences. His papers have received 4,200+ citations and five papers were awarded at international or domestic conferences, such as ICB 2016, CCBR 2016, and AMFG 2017. He also served as area chair or SPC forICPR2020, IJCB2021, IJCAI2021, MM2019/2020/2021etc.He is a Senior Memberof IEEE.

Abstract:

Face is a rich source of signal, conveying various individual information such as identity, age, and expression. In the last few years, with the fast development of deep learning, face recognition has been substantially advanced both in the academia and industry. Evidences are not only the very high scores on large-scale benchmarks but also the extensive real-world applications, e.g., access control and mobile unlock. Meanwhile, recent studies have dedicated to more tasks, including face anti-spoofing, fairness in face analysis, remote physiological signal sensing from face, facial expression classification, and 3D face modeling. They have shown much potential and received persistently increasing attention within the community. This forum focuses on face analysis, covering the topics beyond identification, with six lectures from basic knowledge to latest progress. It will be a high-level seminar to the participants.

Prerequisites: Basic knowledge of pattern recognition.

Tutorials session topics:

Session 1: Physical and digital fake face detection (Dr. Zhen Lei)

Session 2: Fairnessinface analysis: criteria, datasets, and algorithms (Dr. Weihong Deng)

Session 3: Remote physiological signal sensing (RePSS) from face (Dr. Hu Han)

Session 4: Micro-expression recognition: challenges and trend (Dr. Xiaopeng Hong)

Session 5: Perceiving Faces in 2D Images from 3D Perspective(Dr. QijunZhao)

Session 6: Multi-modal emotionanalysis (Dr. Di Huang)


Tutorial 3 Human-centric Visual Understanding: From Research to Applications

Organizers: Shiliang Zhang, Liang  Zheng, Lingxiao  He, Weihua Chen

Presenter bios:
Shiliang Zhang is leading the Media and Vision Computing Group at Institute of Digital Media, Peking University. He received the Ph.D. degree from Institute of Computing Technology, Chinese Academy of Sciences in 2012 with honors. After that, he was a Postdoctoral Fellow in University of Texas at San Antonio and a Postdoctoral Scientist in NEC Labs America, Cupertino, CA. He has authored or co-authored over 80 papers in journals and conferences including  IEEE  Trans. on Pattern  Analysis  and  Machine Intelligence (T-PAMI), International Journal on Computer Vision  (IJCV), IEEE Trans. on Image  Processing  (T-IP), IEEE  Trans. on Multimedia  (T-MM), ACM  Multimedia, CVPR, ICCV, ECCV, IJCAI, and AAAI. His research interests include large-scale image retrieval and computer vision. He was a recipient of the Distinguished Young Scholar Fund of Beijing Natural Science Foundation, Outstanding Doctoral Dissertation Awards from the Chinese Academy of Sciences and Chinese Computer Federation, the President Scholarship from the Chinese Academy of Sciences, the NVidia Pioneering Research Award, the NEC Laboratories America Spot Recognition Award, and the Microsoft Research Fellowship, etc. He was a recipient of the Top10% Paper Award at the IEEE MMSP 2011.
Liang  Zheng (https://zheng-lab.cecs.anu.edu.au) is a Senior Lecturer and an ARC DECRA Fellow with  the  School  of  Computing,  Australian  National  University (ANU), Australia.   He received the B.S. degree in life science and the Ph.D. degree in electronic engineering from Tsinghua University, China, in 2010 and 2015, respectively.  He is best known for his contributions in object re-identification, domain adaptation, and data synthesis. He is an Area Chair of CVPR 2021, ACM  Multimedia 2020 and 2021, ECCV 2020, ICMR 2019, and ICPR 2018.He serves as an associate editor of IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT)and Visual Computer Journal.  He is an organizer of ”The AI  CITY  CHALLENGE”  Workshop  at  CVPR  2020  and2021,  and  the  workshop  on  ”Target  Re-Identification  and Multi-Target Multi-Camera Tracking” at CVPR 2019.
Lingxiao  He (https://lingxiao-he.github.io/) is a research scientist in JD AI Research. He received the B.E degree in information Engineer from the Chengdu University of Technology (CDUT), the Ph.D. degree in Computer Sciences from the Institute of   automation, Chinese Academy of Sciences (CASIA) in 2014, 2019, respectively. He visits Learning and Vision Lab, National University of Singapore (NUS) from September 2018 to May 2019.   Since August 2019.   Dr. He’s research areas include biometric, pattern recognition and computer vision, and he has authored/co-authored over 10 technical papers, including TIP, CVPR, ICCV etc.  Dr.  He is a tutor of the “Human-centric Visual Understanding” tutorial at ACM Multimedia Asia.
Weihua Chen (http://cwhgn.github.io/) is a senior algorithm engineer in Alibaba.  He received the Ph.D. degree in Computer Sciences from the Institute of automation, Chinese Academy of Sciences (CASIA) in 2018.  His research areas include computer vision and deep learning, particularly object tracking and person re-identification. He has authored/co-authored over 10 papers, including CVPR, AAAI and etc.

Abstract:
Human-centric visual understanding is one of the fundamental problems of computer vision and multimedia under-standing. With the development of deep learning and multi-modalities analysis techniques, researchers have strived to push the limits of human-centric visual understanding in a wide variety of applications, such as intelligent surveil-lance and smart retailing.  This tutorial will present recent advances under the umbrella of human-centric visual understanding, which range from the fundamental problems of person re-identification and gait recognition.  In this tutorial, we will discuss the key problems, common formulations, existing methodologies, real industrial applications, and future directions in the five topics.  Our tutorial views not only come from the research filed, but also combine the real-world requirements and experiences in the industrial community. Therefore, this tutorial will inspire the audiences  from  the  research  and  industrial  community,  and facilitate research in computer vision for human behavior analysis  and  human-centric  analysis  modeling.   We have finished a related tutorial about Human-centric visual understanding in ACM Multimedia Asia 2019. We believe that our tutorial can be of interest to a substantial part of the IJCB 2021 audience.

Prerequisites: The tutorial requires basic knowledge in graduate-level pattern recognition and computer vision.  Specifically, the audience should know some knowledge about image processing, deep learning, GAN. Besides, they  should  know how  to  evaluate  the  performance  of  re-id  and  gait  recognition.

Tutorials session topics:

Person re-identification and gait recognition facilitates various applications that require painful and boring video watching, including searching a suspect person from a city surveillance system, a lost child in a shopping mall from camera videos. Their efficiency and effectiveness accelerate the process of video analysis.  Although existing technologies  have  made  significant  advances  in  standard  datasets, they  are  still  far  from  meeting  the  requirement  of  practical applications.  In this tutorial, we will respectively intro-duce the existing challenges and fundamental technologies in re-ID and gait recognition, and then discuss them from the perspective of data-driven and model-driven methods.

The content of the tutorial is as follows:

•  We will first point out a few unsolved but interesting problems in re-ID. Then, we will give an overview of alternative strategies where datasets undergo various changes, either automatically or manually.  For example, editing synthetic data allows us to augment existing databases; composing a validation/test set makes it possible to evaluate model performance when no test labels are given. We will conclude the tutorial with viable future directions in the re-ID field.

•  We will conclude the existing challenging problems, such as occlusion, a person in similar clothes, model generalization, etc. in re-ID. We will review the recently published massive re-ID methods for addressing these challenges.

•  We will introduce some applications in practical. And then we will introduce some unsupervised methods or self-supervised methods for re-id. •  We will introduce the history, related challenges, advanced methods and some applications of gait recognition


Tutorial 4 Deep learning for fingerprint recognition

Organizers: Jianjiang Feng, Kai Cao, Zhe Cui

Presenter bios:
Jianjiang Feng (https://scholar.google.com/citations?user=qlcjuzcAAAAJ&hl=zh-CN) is an associate professor in Department of Automation, Tsinghua University, Beijing. He received his PhD degree from Beijing University of Posts & Telecommunications. After that, he has worked as a postdoc in the PRIP lab at Michigan State University. He has published over 60 papers on fingerprint/palmprint, among which two received the Best Student Paper Award on IJCB 2011 and the Best Student Paper Award Runner-Up on IJCB 2017. He has served as area chair for IJCB (2014, 2021), ICB (2015,2016), BTAS (2016), and program chair for CCBR (2015-2021). He has given tutorial talks on fingerprint recognition at several conferences (ICB 2013, CCBR 2013, Biometric Winter School 2014, IJCB 2014).
Kai Cao (https://scholar.google.com/citations?user=aA2HStQAAAAJ&hl=zh-CN&oi=ao) is a biometrics technique expert at Goodix in San Diego, CA. He received the Ph.D. degree from the Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing, China, in 2010. He was a postdoc in the PRIP lab at Michigan State University. He has published over 50 papers on fingerprint recognition. His research interests include biometric recognition, computer vision, image processing and machine learning.
Zhe Cui (https://scholar.google.com/citations?user=3xGn0usAAAAJ&hl=zh-CN&oi=sra) received the B.S. degree from the Department of Physics, Tsinghua University in 2014, and the M. Eng. degree from the Department of Automation, Tsinghua University, Beijing, China, in 2017. He is currently a Ph.D. student at the Department of Automation, Tsinghua University, Beijing, China.  His research interests include fingerprint recognition, computer vision and pattern recognition.

Abstract:
Deep learning technology has an important impact on various aspects of fingerprint recognition. With well-designed and adequate high quality data, deep learning approaches have achieved better performances than traditional hand-crafted approaches on many topics. This tutorial aims at introducing recent deep learning based fingerprint recognition techniques, including feature extraction, pose estimation, distortion rectification, dense registration, matching, indexing, and liveness detection.

Tutorials session topics:

Session1: Basics of fingerprint recognition (20 minutes)
Session2: Fingerprint feature extraction (30 minutes)
Session3: Fingerprint pose estimation (20 minutes)
Session4: Fingerprint distortion rectification (20 minutes)
Session5: Dense fingerprint registration (20 minutes)
Session6: Fingerprint matching (20 minutes)
Session7: Fingerprint indexing (20 minutes)
Session8: Liveness detection (20 minutes)