Finger Vein and Inner Knuckle Print Recognition Based on Multilevel Feature Fusion Network
Source abstract
Abstract
Multimodal biometric recognition involves two critical issues: feature representation and multimodal fusion. Traditional feature representation requires complex image preprocessing and different feature-extraction methods for different modalities. Moreover, the multimodal fusion methods used in previous work simply splice the features of different modalities, resulting in an unsatisfactory feature representation. To address these two problems, we propose a Dual-Branch-Net based recognition method with finger vein (FV) and inner knuckle print (IKP). The method combines convolutional neural network (CNN), transfer learning, and triplet loss function to complete feature representation, thereby simplifying and unifying the feature-extraction process of the two modalities. Dual-Branch-Net also achieves deep multilevel fusion of the two modalities’ features. We assess our method on a public FV and IKP homologous multimodal dataset named PolyU-DB. Experimental results show that the proposed method performs best and achieves an equal error rate (EER) of the recognition result of 0.422%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Biometric Identification and Security · Face recognition and analysis · Forensic Fingerprint Detection Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
College of Information Engineering and Technology, Zhejiang University of Technology, Hangzhou 310023, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Zhejiang Province · Leading Innovation Team of Zhejiang Province
References (44)
Show source-provided references
1. Yang, W., Wang, S., Sahri, N.M., Karie, N.M., Ahmed, M., and Valli, C. (2021). Biometrics for Internet-of-Things security: A review. Sensors, 21.10.3390/s21186163 ↗
2. Ramya, S., Sheeba, R., Aravind, P., Gnanaprakasam, S., Gokul, M., and Santhish, S. (2022, January 25–27). Face Biometric Authentication System for ATM using Deep Learning. Proceedings of the 2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India.10.1109/ICICCS53718.2022.9788310 ↗
3. Srinivas, K.K., Vijitha, U., Chandra, G.A., Kumar, K.S., Peddi, A., and Uppala, B.S. (2022, January 10–11). Artificial Intelligence based Optimal Biometric Security System Using Palm Veins. Proceedings of the 2022 International Mobile and Embedded Technology Conference (MECON), Noida, India.10.1109/MECON53876.2022.9752324 ↗
4. Carvalho, J.M., Brãs, S., Ferreira, J., Soares, S.C., and Pinho, A.J. (2017). Impact of the acquisition time on ECG compression-based biometric identification systems. Iberian Conference on Pattern Recognition and Image Analysis, Springer.10.1007/978-3-319-58838-4_19 ↗
5. Preprocessing and feature selection for improved sensor interoperability in online biometric signature verification10.1109/ACCESS.2015.2431493 ↗
6. Convolutional neural network-based feature extraction using multimodal for high security application10.1007/s12065-020-00522-5 ↗
7. FESD: An approach for biometric human footprint matching using fuzzy ensemble learning10.1109/ACCESS.2021.3057931 ↗
8. Synthesis of palm print in feature fusion techniques for multimodal biometric recognition system online signature10.36548/jiip.2021.2.005 ↗
9. Continuous multimodal biometric authentication schemes: A systematic review10.1109/ACCESS.2021.3061589 ↗
10. Optimal feature level fusion for secured human authentication in multimodal biometric system10.1007/s00138-020-01146-6 ↗
11. Shaheed, K., Liu, H., Yang, G., Qureshi, I., Gou, J., and Yin, Y. (2018). A systematic review of finger vein recognition techniques. Information, 9.10.3390/info9090213 ↗
12. Basic finger inner-knuckle print: A new hand biometric modality10.1049/bme2.12000 ↗
13. Human identification using finger images10.1109/TIP.2011.2171697 ↗
14. Liu, C. (2013, January 16–18). A new finger vein feature extraction algorithm. Proceedings of the 2013 6th International Congress on Image and Signal Processing (CISP), Hangzhou, China.10.1109/CISP.2013.6744026 ↗
15. Huang, B., Dai, Y., Li, R., Tang, D., and Li, W. (2010, January 23–26). Finger-vein authentication based on wide line detector and pattern normalization. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.316 ↗
16. A finger-vein verification system using mean curvature10.1016/j.patrec.2011.04.021 ↗
17. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification10.1007/s00138-004-0149-2 ↗
18. Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2017, January 4–9). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.11231 ↗
19. Schroff, F., Kalenichenko, D., and Philbin, J. (2015, January 7–12). Facenet: A unified embedding for face recognition and clustering. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298682 ↗
20. Finger-vein recognition based on densely connected convolutional network using score-level fusion with shape and texture images10.1109/ACCESS.2020.2996646 ↗
21. Finger-vein recognition based on deep DenseNet using composite image10.1109/ACCESS.2019.2918503 ↗
22. Multimodal biometric recognition systems using deep learning based on the finger vein and finger knuckle print fusion10.1049/iet-ipr.2020.0491 ↗
23. Wen, M., Zhang, H., and Yang, J. (2021). End-To-End Finger Trimodal Features Fusion and Recognition Model Based on CNN. Chinese Conference on Biometric Recognition, Springer.10.1007/978-3-030-86608-2_5 ↗
24. Kim, W., Song, J.M., and Park, K.R. (2018). Multimodal biometric recognition based on convolutional neural network by the fusion of finger-vein and finger shape using near-infrared (NIR) camera sensor. Sensors, 18.10.3390/s18072296 ↗
25. Group sparse representation based classification for multi-feature multimodal biometrics10.1016/j.inffus.2015.06.007 ↗
26. Evangelin, L.N., and Fred, A.L. (2017, January 23–24). Feature level fusion approach for personal authentication in multimodal biometrics. Proceedings of the 2017 Third International Conference on Science Technology Engineering & Management (ICONSTEM), Chennai, India.10.1109/ICONSTEM.2017.8261272 ↗
27. Li, S., Zhang, H., Shi, Y., and Yang, J. (2019). Novel local coding algorithm for finger multimodal feature description and recognition. Sensors, 19.10.3390/s19092213 ↗
28. System for multimodal biometric recognition based on finger knuckle and finger vein using feature-level fusion and k-support vector machine classifier10.1049/iet-bmt.2016.0112 ↗
29. Wang, L., Zhang, H., and Yang, J. (2019, January 6–9). Finger multimodal features fusion and recognition based on CNN. Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China.10.1109/SSCI44817.2019.9003093 ↗
30. A Dataset and Benchmark for Multimodal Biometric Recognition Based on Fingerprint and Finger Vein10.1109/TIFS.2022.3175599 ↗
31. Simonyan, K., and Zisserman, A. (2022, April 22). Very Deep Convolutional Networks for Large-Scale Image Recognition. Available online: https://arxiv.org/abs/1409.1556.
32. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
33. Pixel-level image fusion: A survey of the state of the art10.1016/j.inffus.2016.05.004 ↗
34. Alay, N., and Al-Baity, H.H. (2020). Deep learning approach for multimodal biometric recognition system based on fusion of iris, face, and finger vein traits. Sensors, 20.10.3390/s20195523 ↗
35. Robust multimodal biometric system based on optimal score level fusion model10.1016/j.eswa.2018.08.036 ↗
36. Wang, Y., Shi, D., and Zhou, W. (2022). Convolutional Neural Network Approach Based on Multimodal Biometric System with Fusion of Face and Finger Vein Features. Sensors, 22.10.3390/s22166039 ↗
37. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
38. Soleymani, S., Dabouei, A., Kazemi, H., Dawson, J., and Nasrabadi, N.M. (2018, January 20–24). Multi-level feature abstraction from convolutional neural networks for multimodal biometric identification. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.10.1109/ICPR.2018.8545061 ↗
39. Yi, D., Lei, Z., Liao, S., and Li, S.Z. (2022, May 16). Learning Face Representation from Scratch. Available online: https://arxiv.org/abs/1411.7923.
40. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
41. A light CNN for deep face representation with noisy labels10.1109/TIFS.2018.2833032 ↗
42. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2022, June 15). SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size. Available online: https://arxiv.org/abs/1602.07360.
43. Wimmer, G., Prommegger, B., and Uhl, A. (2021, January 10–15). Finger vein recognition and intra-subject similarity evaluation of finger veins using the cnn triplet loss. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.10.1109/ICPR48806.2021.9413060 ↗
44. Joseph, R.B., and Ezhilmaran, D. (2019). An efficient approach to finger vein pattern extraction using fuzzy rule-based system. Innovations in Computer Science and Engineering, Springer.10.1007/978-981-10-8201-6_49 ↗