Ajay Kumar
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University
How to recover and match finger crease keypoint-based graphs?
Explainability and interpretability are critical for the successful prosecution of suspects from surveillance and child abuse cases. Read more on the first such explainable approach and online approach to march challenging finger knuckle patterns.
How to accurately segment and match iris images acquired at-a-distance?
Accurate iris segmentation is the key for accurate iris recognition and challenges when imaging distance is large. Read more on our framework to accurately segment iris images for at-a-distance iris recognition.
Can we use very low resolution fingerprint images to establish human identity?
Very low-resolution images of about 50 dpi can also reveal useful information for biometrics. Read more on such efforts to identify human from level zero features with experimentation on 156 subjects database.
How can we synthesize very large databases of multi-view contactless 3D fingerprints?
Such fingerprints can also provide accurate ground truth of 3D minutiae locations with their orientations, along with surface normal and depth maps.Read more on synthesizing large databases in our recent paper.
How can we protect biometrics systems from spoof attacks?
Fingerprint devices have shown to be highly vulnerable from artificial fingerprints. Read more on our system that detects fake spoof fingerprints from the oxygenated haemoglobin measurements.
How can we recover and match minutiae features in 3D space?
Contactless fingerprint imaging is hygienic and avoids deformations but full potential from this biometrics is yet to be realized. Read more on first such efforts to recover 3D fingerprint templates using minutiae features and match them in 3D space.
How can we recover deeply learned features for advanced iris recognition?
Deep learning capabilities offer tremendous potential to address limitations of currently available iris recognition technologies. Read more on such efforts to develop deep learning architecture for the iris recognition.
How to ensure higher security at border crossings?
Emerging challenges from sophisticated face masks and make-up pose serious threat for border security. Our team developed a prototype for automated watchlist surveillance to assist for law enforcement personnels at border-crossings and some more details are here.
How unique and stable are our finger knuckle patterns?
Our study on uniqueness of knuckle patterns from over 500 different subjects and its stability from 6 year interval data provides more insights. More details from this study in the paper here.
Can we use minor knuckle patterns for biometrics?
Knuckle patterns can only be the pieces of evidence available to establish identity of suspects. Read more on this investigation from such possibility of using first minor knuckle patterns here and second minor knuckle patterns in the recent publications here.
How can we recover 3D features from a single 2D image?
The ordinal measurements under known light source can reveal 3D profile of unknown surface. Read on such efforts in our recent paper.
How to more accurately and efficiently match 3D palmprints?
Palmprints have been used to establish identity of humans over several decades. Read more on our investigation into problems with the state-of-art and successful efforts to develop more accurate/efficient matching algorithms for palmprints.
News
- IEEE Biometrics Council Interview June 2025
- Ming Pao Newspaper Interview, 𝐈𝐫𝐢𝐬 𝐏𝐡𝐨𝐭𝐨𝐬’ and 𝐏𝐫𝐢𝐯𝐚𝐜𝐲 𝐑𝐢𝐬𝐤𝐬 March 2025
- PolyU Hosts WIFS 2018 in Hong Kong
- PolyU Hosts ISBA 2015 in Hong Kong
- Ms Fieke Hillerström Wins Best Paper Award in BIOSIG 2014
- PolyU Co-Organizes IJCB 2014
- Mr Kam Yuan Cheng Wins First Prize in IEEE HK Student Paper Contest - Excel@PolyU, Demo
- Ms Lau O HungWins HKEIA Gold Award - HKEIA 2011 Awards, Excel@PolyU, Summary
- Currently Available Research Positions
- You may contact me for New Projects (MSc Dissertation, Capstone Project) if you are a student at PolyU and interested in my research areas
Publications
- Shum Hing Ling*, Zhenyu Zhou*, AjayKumar, "Detecting Hyper-Realistic Videos Generated by Diffusion Models via Text-Guided Semantic Enhancement," IEEE International Joint Conference on Biometrics, IJCB 2025, pp 181-190, Osaka, September 2025
- Chengdong Dong* and Ajay Kumar, "Bridging Dimensions in Fingerprints to Advance Distinctiveness: Recovering 3D Minutiae from a Single Contactless 2D Fingerprint Image," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 7812-7831, September 2025
- Zhenyu Zhou*, Chengdong Dong*, Ajay Kumar, "Towards Explainable and Unprecedented Accuracy in Matching Challenging Finger Crease Patterns," IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2025, pp. 7855-7864, Nashville, June 2025
- Ajay Kumar, "Insights on ‘Complex-Valued Iris Recognition Network’," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 2232-2236, March 2025
- Ritesh Vyas and Ajay Kumar, "A Collaborative Approach Using Ridge-Valley Minutiae for More Accurate Contactless Fingerprint Matching," Proc. Intl. Conf. Pattern Recognition, ICPR 2024, pp 273–287, Kolkata, December 2024
Activities
- IEEE International Joint Conference on Biometrics, IJCB 2025, Osaka, Japan, September 2025
- The IEEE/CVF Conference on Computer Vision and Pattern Recognition CVPR 2025, Nashville, USA, June 2025
- IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, Louisiana, June 2022
- IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, USA, June 2020
- IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, USA, June 2019
- International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 2017
- International Conference on Pattern Recognition, ICPR 2016, Cancan, December 2016
- IEEE International Conference on Identity, Security and Behabioral Analysis, ISBA 2015, Hong Kong, March 2015
CVPR 2015 Tutorial
Book (2019)
MISP 2014 Tutorial
Book (2024)
Some leading industries/institutions which have also benefited from our algorithms, results or databases for the research and development.
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |