no code implementations • 24 Mar 2024 • Geetanjali Sharma, Gaurav Jaswal, Aditya Nigam, Raghavendra Ramachandra
The results demonstrate the superior performance of FH-SSTNet for forehead-based user verification, confirming its effectiveness in identity authentication.
no code implementations • 24 Mar 2023 • Raghavendra Ramachandra, Sushma Venkatesh, Gaurav Jaswal, Guoqiang Li
We present a systematic study on benchmarking the vulnerability of Face Recognition Systems (FRS) to lookalike and identical twin morphing images.
no code implementations • 20 May 2022 • Edwin H. Salazar-Jurado, Ruber Hernández-García, Karina Vilches-Ponce, Ricardo J. Barrientos, Marco Mora, Gaurav Jaswal
With the recent success of computer vision and deep learning, remarkable progress has been achieved on automatic personal recognition using vein biometrics.
no code implementations • 1 Nov 2021 • Gaurav Jaswal, Aman Verma, Sumantra Dutta Roy, Raghavendra Ramachandra
To alleviate these shortcomings, this paper proposes DFCANet: Dense Feature Calibration and Attention Guided Network which calibrates the locally spread iris patterns with the globally located ones.
Cross-Domain Iris Presentation Attack Detection Incremental Learning +1
no code implementations • 2 Apr 2019 • Daksh Thapar, Gaurav Jaswal, Aditya Nigam
In distinguished experiments, the individual performance of finger, as well as weighted sum score level fusion of major knuckle, minor knuckle, and nail modalities have been computed, justifying our assumption to consider full finger as biometrics instead of its counterparts.
no code implementations • 18 Dec 2018 • Avantika Singh, Gaurav Jaswal, Aditya Nigam
At present spoofing attacks via which biometric system is potentially vulnerable against a fake biometric characteristic, introduces a great challenge to recognition performance.
no code implementations • 15 Dec 2018 • Daksh Thapar, Gaurav Jaswal, Aditya Nigam, Vivek Kanhangad
Designing an end-to-end deep learning network to match the biometric features with limited training samples is an extremely challenging task.
2 code implementations • 13 Dec 2018 • Avantika Singh, Ashish Arora, Shreya Hasmukh Patel, Gaurav Jaswal, Aditya Nigam
In this work, we have proposed a secure cancelable finger dorsal template generation network (learning domain specific features) secured via.