News
2024-06: 1 paper on latent fingerprint desctiptor is accepted by IJCB 2024.
2024-05: 1 paper on fingerprint dense registration is accepted by T-IFS.
2023-07: 1 paper on fingerprint distortion rectification is accepted
by T-IFS.
2022-07: 1 paper on fingerprint distortion rectification is accepted
by IJCB 2022.
|
Research
* indicates equal contribution
|
|
Joint Identity Verification and Pose Alignment for Partial Fingerprints
Xiongjun Guan ,
ZhiyuPan ,
Jianjiang Feng ,
Jie Zhou
IEEE Transactions on Information Forensics and Security
(T-IFS), 2024
(under review)
[Code]
A novel framework for joint partial fingerprint identity verification and
pose alignment of partial fingerprint pairs is proposed, which utilizes a
multi-task
CNN-Transformer hybrid network and a pre-training task on enhancement.
|
|
Latent Fingerprint Matching via Dense Minutia Descriptor
ZhiyuPan ,
Yongjie Duan ,
Xiongjun Guan ,
Jianjiang Feng ,
Jie Zhou
International Joint Conference on Biometrics (IJCB), 2024
[Paper]
[Code]
Latent fingerprint matching is a daunting task, primarily due to the poor
quality of latent fingerprints.
In this study, we propose a deep-learning based dense minutia descriptor (DMD)
for latent fingerprint matching.
|
|
Phase-aggregated Dual-branch Network for Efficient
Fingerprint Dense Registration
Xiongjun Guan ,
Jianjiang Feng ,
Jie Zhou
IEEE Transactions on Information Forensics and Security
(T-IFS), 2024
[Paper]
[Code]
We propose a Phase-aggregated Dual-branch Registration Network to combine the
strengths of
traditional fingerprint dense registration methods and deep
learning.
|
|
Regression of Dense Distortion Field from a Single Fingerprint Image
Xiongjun Guan ,
Yongjie Duan ,
Jianjiang Feng ,
Jie Zhou
IEEE Transactions on Information Forensics and Security
(T-IFS), 2023
[Paper]
[Code]
We proposed an end-to-end network to directly estimate a dense distortion field
instead of
its low dimensional representation, from a single fingerprint.
|
|
Direct Regression of Distortion Field from a Single Fingerprint Image
Xiongjun Guan ,
Yongjie Duan ,
Jianjiang Feng ,
Jie Zhou
International Joint Conference on Biometrics (IJCB), 2022
Oral Presentation
[Paper]
[Code]
[Slide]
We proposed an end-to-end network to directly estimate a dense distortion field
from a single
fingerprint instead of its low dimensional representation.
|
|
Pose-Specific 3D Fingerprint Unfolding
Xiongjun Guan ,
Jianjiang Feng ,
Jie Zhou
Chinese Conference on Biometric Recognition (CCBR), 2021
Oral Presentation
[Paper]
[Slide]
We proposed a visualization and pose-specific unfolding method for 3D
fingerprints, which can
improve the compatibility between 3D and 2D fingerprints in recognition.
|
Honors and Awards
Silver Award for Social Practice of Ph.D Students,
Tsinghua University,
2023
Comprehensive Excellence Award, Tsinghua University,
2022 & 2023
Excellent Graduates, Tsinghua University, 2021
Outstanding Graduates, Tsinghua University (Dept. of
Automation), 2021
Academic Excellence Award, Tsinghua University, 2019 &
2020
1st Prize in the 35th China Regional College Students
Physics Competition,
2018
Gold Medal in the 33th Chinese Physics Olympiad (Top
100 in the country),
2016
|
Teaching
Teaching Assistant, Programming Fundamentals, 2024
Spring
Semester
Teaching Assistant, Interdisciplinary Research and
Practice: Image Processing, 2023 Fall
Semester
Teaching Assistant, Basic of Information Theory, 2023
Spring
Semester
Teaching Assistant, Digital Image Processing, 2022
Fall Semester
|
|