Variable Curvature Gabor Convolution and Multi-Branch Structures for Finger Vein Recognition
Article
Li, Jun, Wang, Huabin, Wei, Shicheng, Zhou, Jian, Shen, Yuankang and Tao, Liang. 2024. "Variable Curvature Gabor Convolution and Multi-Branch Structures for Finger Vein Recognition." IEEE Transactions on Artificial Intelligence. 5 (9), pp. 4753-4764. https://doi.org/10.1109/TAI.2024.3397293
| Article Title | Variable Curvature Gabor Convolution and Multi-Branch Structures for Finger Vein Recognition |
|---|---|
| ERA Journal ID | 212760 |
| Article Category | Article |
| Authors | Li, Jun, Wang, Huabin, Wei, Shicheng, Zhou, Jian, Shen, Yuankang and Tao, Liang |
| Journal Title | IEEE Transactions on Artificial Intelligence |
| Journal Citation | 5 (9), pp. 4753-4764 |
| Number of Pages | 12 |
| Year | 2024 |
| Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
| Place of Publication | United States |
| ISSN | 2691-4581 |
| Digital Object Identifier (DOI) | https://doi.org/10.1109/TAI.2024.3397293 |
| Web Address (URL) | https://ieeexplore.ieee.org/document/10521853 |
| Abstract | Gabor filters are able to extract texture features from finger vein images from different directions and scales. However, manually crafted Gabor filters have problems such as relatively single direction and scale, and difficulties in parameter adjustment to adapt to specific datasets. To solve these problems, this paper proposes a neural network with a learnable variable curvature Gabor (VC-Gabor) convolutional layer. Firstly, the Gabor filter is improved by adding variable curvature to extract information about different curvature degrees in the vein curves. Secondly, the VC-Gabor filter is designed as a learnable convolutional filter, with parameters updated using neural network back-propagation. This facilitates the enrichment of learned VC-Gabor filter directions, scales, and curvatures, eliminating the need for intricate manual parameter tuning. Finally, we propose adaptive multi-branch structures for feature extraction, which are used to enhance the feature extraction capability ... |
| Keywords | convolutional neural network; VC-Gabor filter; multi-branch structure; finger vein recognition |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460299. Artificial intelligence not elsewhere classified |
| Public Notes | The accessible file is the accepted version of the paper. Please refer to the URL for the published version. |
| Byline Affiliations | Anhui University, China |
| School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z851x/variable-curvature-gabor-convolution-and-multi-branch-structures-for-finger-vein-recognition
Download files
Accepted Version
| Variable_Curvature_Gabor_Convolution_and_Multi-Branch_Structures_for_Finger_Vein_Recognition.pdf | ||
| File access level: Anyone | ||
15
total views19
total downloads0
views this month3
downloads this month