1 code implementation • 7 Jan 2023 • Kevin H. M. Cheng, Xu Cheng, Guoying Zhao
However, this approach results in a large feature dimension, and the trained classification layer is required for comparing probe samples, which limits the introduction of new classes.
1 code implementation • 16 Feb 2022 • Zitong Yu, Ajian Liu, Chenxu Zhao, Kevin H. M. Cheng, Xu Cheng, Guoying Zhao
Can we train a unified model, and flexibly deploy it under various modality scenarios?
1 code implementation • 13 Jan 2021 • Kevin H. M. Cheng, Ajay Kumar
This article advances the state-of-the-art method by introducing a new curvature based feature descriptor and a method to compute the similarity functions based on the statistical distribution of the encoded feature space.
1 code implementation • 9 Oct 2020 • Kevin H. M. Cheng, Ajay Kumar
This paper attempts to address the above challenges and introduces a new deep neural network based approach for the contactless 3D finger knuckle identification.
1 code implementation • 9 Sep 2020 • Kevin H. M. Cheng, Ajay Kumar
The current 3D finger knuckle recognition methods are limited by computationally complex or inefficient matching algorithms, which attempt to compute the matching scores from all possible translational and rotational parameters for matching a pair of templates.
1 code implementation • 1 Aug 2020 • Kevin H. M. Cheng, Ajay Kumar
Although our feature descriptor is designed for 3D finger knuckle patterns, it is also attractive for other hand-based biometric identifiers with similar patterns such as the palmprint and fingerprint.
1 code implementation • 11 Oct 2018 • Kevin H. M. Cheng, Ajay Kumar
This paper presents two novel outlier rejection techniques that attempt to identify the data that are more reliable and likely to be Lambertian.