Survey — Vein Recognition

Peter Chan
4 min readFeb 7, 2023

--

Keywords: Biometric Feature, Vein Recognition, Convolutional Neural Network (CNN), Attention Mechanism, Neural Architecture Search (NAS), Knowledge Distillation (KD)

  1. AGCNN: Adaptive Gabor Convolutional Neural Networks with Receptive Fields for Vein Biometric Recognition. Concurrency and Computation: Practice and Experience, 2020. https://onlinelibrary.wiley.com/doi/full/10.1002/cpe.5697

2. An Improved Finger Vein Recognition Model with a Residual Attention Mechanism. CCBR, 2021. https://link.springer.com/chapter/10.1007/978-3-030-86608-2_26

Network architecture of LFVRN

3. Different Dimension Issues in Deep Feature Space for Finger-Vein Recognition. Chinese Conference on Biometric Recognition (CCBR), 2021. https://link.springer.com/chapter/10.1007/978-3-030-86608-2_33#Abs1

4. ResNeXt with Cutout for Finger Vein Analysis. International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2021. https://ieeexplore.ieee.org/abstract/document/9650921

ResNet and ResNeXt with cardinality=32, with roughly the same complexity. (a) ResNet. (b) ResNeXt

5. Finger-Vein Recognition Using a NASNet with a Cutout. International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2021. https://ieeexplore.ieee.org/abstract/document/9650980?casa_token=9P2Lmlie_TgAAAAA:lUloDCy6vhyozX8-bl-ukK6xfDBcQxB__MsOfU8NVU9gkhLGL8iTR6v6kdXHWzoSw20OimZdzA

6. Fusion loss and inter-class data augmentation for deep finger vein feature learning. Expert Systems with Applications, 2021. https://www.sciencedirect.com/science/article/pii/S0957417421000257

Overall diagram of the proposed framework.

7. GAN-Based Inter-Class Sample Generation for Contrastive Learning of Vein Image Representations. IEEE Transactions on Biometrics, Behavior, and Identity Science, 2022. https://ieeexplore.ieee.org/abstract/document/9717270

Diagram of the proposed framework.

8. DS-CNN: A pre-trained Xception model based on depth-wise separable convolutional neural network for finger vein recognition. Expert Systems with Applications, 2022. https://www.sciencedirect.com/science/article/pii/S0957417421015943?ref=pdf_download&fr=RR-2&rr=78842303db69a331

The architecture of the Proposed Pre-trained Network Model

9. New Hierarchical Finger-Vein Feature Extraction Method for iVehicles. IEEE Sensors Journal, 2022. https://ieeexplore.ieee.org/abstract/document/9788520

10. Triplet-Classifier GAN for Finger-Vein Verification. IEEE Transactions on Instrumentation and Measurement, 2022. https://ieeexplore.ieee.org/abstract/document/9721917

Architecture of the proposed triplet-classifier GAN.

11. FVT: Finger Vein Transformer for Authentication. IEEE Transactions on Instrumentation and Measurement, 2022. https://ieeexplore.ieee.org/abstract/document/9772498?casa_token=jSexKYPD_NMAAAAA:0T84u1x7qfvOi4zjw3T8d0UZmdZtzQSjI8S5GnRU8gPYEnjH1-Ir8GMAOmxhfile3X-VDv8d8Q

Overall architecture of the FVT. (a) Concise architecture of FVT. There are three stages in the FVT. The first stage includes two FVT blocks, and the second and third stages consist of one FVT block each. (b) Architecture of the VT block. The FVT block consists of conditional position embedding, expansion token embedding and SA, a local information-enhanced FFN, and the ELM.

12. Residual Feature Pyramid Network for Enhancement of Vascular Patterns. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022. https://ieeexplore.ieee.org/document/9857440

Architectures of the proposed finger vein enhancement technique: (a) ResFPN and (b) SDBlock. The blue dotted lines in (a) represent FAM.

13. Study of Contactless Finger-Vein Identification System. IEEE 5th International Conference on Knowledge Innovation and Invention (ICKII ), 2022. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9983581

Flowchart of the proposed system.

14. MMRAN: A novel model for finger vein recognition based on a residual attention mechanism. Applied Intelligence, 2023. https://link.springer.com/content/pdf/10.1007/s10489-022-03645-7.pdf?pdf=button

The architecture of the proposed model

15. Robust and Efficient Finger Vein Recognition Using Binarized Difference of Gabor Jet on Grid. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9930790

Diagram of preprocessing.

Review paper

  1. Recent Advancements in Finger Vein Biometrics: A Review. IEEE 4th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA). 2022. https://ieeexplore.ieee.org/abstract/document/9989104
  2. Single-Sample Finger Vein Recognition via Competitive and Progressive Sparse Representation. IEEE Transactions on Biometrics, Behavior, and Identity Science. 2022. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9973284&tag=1
  3. Recent advancements in finger vein recognition technology: Methodology, challenges and opportunities. Information Fusion, 2022. https://www.sciencedirect.com/science/article/pii/S1566253521002025#bib0034
  4. Artificial Neural Networks for Finger Vein Recognition: A Survey. arXiv:2208.13341. 2022. https://arxiv.org/pdf/2208.13341.pdf

--

--

Peter Chan

[AI Medical.] Researcher. Deep Learning; Computer Vision; Vein Recognition; Skin Lesion Analysis;