Optimizing different palmprint recognition models trained via transfer learning using attention mechanisms
Hao Jiang
Gunma University
Nghia ThiMai
Posts and Telecommunications Institute of Technology
Md Kamal
Gunma University
Iwanori Murakami
Gunma University
Kou Yamada
Gunma University
DOI: https://doi.org/10.59429/esta.v12i3.11367
Keywords: palmprint; recognition; attention; mechanism; transfer; learning; image processing
Abstract
Palmprint recognition is an authentication technology based on human biometrics, which has gained wide attention in the biometrics field due to its uniqueness, stability and non-invasiveness. And now it is widely used in the fields of financial payment, security monitoring, and intelligent medical treatment. Furthermore, this technology has already been widely adopted in China's daily life, particularly in mobile payment systems. This study proposes an innovative palmprint recognition method that combines data preprocessing, attention mechanism, and migration learning to optimize feature extraction and classification performance. The results show that the method in this paper outperforms traditional methods on multiple datasets, exhibiting high robustness and adaptability. It provides some ideas for future palmprint research.
References
[1] Diego Maureira, Oscar Romero, Andrés Illanes, Lorena Wil-son, Carminna Ottone, Industrial bioelectrochemistry for waste valorization: State of the art and challenges,Biotechnology Advances,Volume64,2023,108123,ISSN 0734-9750, https://doi.org/10.1016/j.biotechadv.2023.1.08123.
[2] Zhang, D., Kong, W. K., You, J., Wong, M. (2003). Online palmprint identification. IEEE Transactions on Pattern Analy-sis and Machine Intelligence, 25(9), 1041-1050.
[3] Jia, W., Zhang, B., Lu, J., Zhu, Y., Zhao, Y., Zuo, W. Ling, H. (2018). Palmprint recognition based on complete direction representation. IEEE Transactions on Image Processing, 26(9), 4483-4498.
[4] Jain, A. K., Nandakumar, K., Ross, A. (2016). 50 years of bio-metric research: Accomplishments, challenges, and opportuni-ties. Pattern Recognition Letters, 79, 80-105.
[5] Zhang, David Zuo, Wangmeng Yue, Songfeng. (2012). A Com-parative Study of Palmprint Recognition Algorithms. ACM Comput. Surv.. 44. 2. 10.1145 2071389.2071391.
[6] J.Lee, S.Jang, Y. Lee and S. Lee, "One-Stage Mobile Palmprint Recognition via Keypoint Detection Network,"2023 Interna-tional Technical Conference on Circuits/Systems, Computers, and Communications (ITC CSCC), Jeju, Korea, Republic of, 2023, pp. 16, doi: 10.1109/ITCCSCC58803.2.023.1.0212697.
[7] P.Hennings,M.Savvides and B. V. K. V. Kumar,"Palm-print Recognition with Multiple Correlation Filters Using Edge Detection for Class-Specific Segmentation,"2007 IEEE Workshop on Automatic Identification Advanced Technolo-gies, Alghero, Italy, 2007, pp. 214219, doi:10.1109/AU-TOID.2007.380622.
[8] Amrouni, Nadia, Amir Benzaoui, and Abdelhafid Zeroual. 2024. "Palmprint Recognition:ExtensiveExploration of Databases,Methodologies,Comparative Assessment,and FutureDirections"Applied Sciences14,no.1: 153. https://doi.org/10.3390/app14010153.
[9] N.A.Nainan, J.H,R.Jalan, R.S.N,K.V.C and S. P. Shankar, "Real Time Face Mask Detection Using MobileNetV2 and In-ceptionV3 Models,"2021 IEEE Mysore Sub Section Interna-tional Conference (MysuruCon), Hassan, India, 2021, pp. 341-345, doi: 10.1109/MysuruCon52639.2021.9641675.
[10] Rismiyati, S.N.Endah, Khadijah and I.N.Shiddiq, "Xception Architecture Transfer Learning for Garbage Classification,"2020 4th International Conference on Informatics and Com-putational Sciences (ICICoS), Semarang, Indonesia, 2020, pp. 1-4, doi: 10.1109/ICICoS51170.2020.9299017.
[11] Q.Zhou andY.Li, "Method for Tool Power Recognition Based on improved ResNet50 and Transfer learning,"2024 4th Inter-national Conference on Electronics, Circuits and Information Engineering (ECIE), Hangzhou, China, 2024, pp. 572-576, doi: 10.1109/ECIE61885.2.024.1.0627101.
[12] Y.Tao, "Image Style Transfer Based on VGG Neural Net-work Model,"2022 IEEE International Conference on Ad-vances in Electrical Engineering andComputer Applica-tions (AEECA), Dalian, China, 2022, pp.1475-1482, doi: 10.1109/AEECA55500.2022.9918891.
[13] Z.Zheng and N.Slam,"A VGG Fire Image Classifica-tion Model with Attention Mechanism,"2024 5th Interna-tional Conference on Computer Vision, Image and Deep Learning (CVIDL), Zhuhai, China, 2024, pp. 873-877, doi: 10.1109/CVIDL62147.2024.1.0603830.
[14] Gao,Y.;Zhang,J.;Wang,M.;Tan,Z.;Liang,M. A Lightweight Load Identification Model Update Method Based on Channel Attention. Energies 2025,18,2885. https://doi.org/10.3390/en18112885.
[15] H. Mo, Z. Yang, P. Li and Q. Wang, "The Method of Portrait Segmentation Based on Efficient Channel Attention Mecha-nism,"2024 4th International Conference on Computer Sci-ence and Blockchain (CCSB), Shenzhen, China, 2024,pp. 380-385, doi: 10.1109/CCSB63463.2.024.1.0735544.
[16] L. Shao, F. Zhu and X. Li, "Transfer Learning for Visual Categorization: A Survey,"in IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 5, pp. 1019-1034, May 2015, doi:10.1109/TNNLS.2014.2.330900. key-words:{Knowledge transfer;Visualization;Training;Training data;Adaptation models;Learnin.
[17] F. Yang, "AttenVGG: Integrating Attention Mechanisms with VGGNet for Facial Expression Recognition,"2024 5th Inter-national Conference on Electronic Communication and Artifi-cial Intelligence (ICECAI), Shenzhen, China, 2024, pp. 332-337, doi: 10.1109/ICECAI62591.2.024.1.0674809.
[18] Genovese, A., Piuri, V., Plataniotis, K. N., Scotti, F. (2016). PalmNet:Gabor-PCAconvolutional networks for touch-less palmprint recognition. IEEE Transactions on Information Forensics and Security, 11(3), 553-567.
[19] M.Z.Hossain, F.Uz Zaman and M. R. Islam, "Advancing AI-Generated Image Detection: Enhanced Accuracy through CNN and Vision Transformer Models with Explainable AI Insights,"2023 26th International Conference on Computer and Infor-mation Technology (ICCIT), Cox's Bazar, Bangladesh, 2023, pp. 1-6, doi: 10.1109/ICCIT60459.2023.1.0440990.
[20] L.Fei, G. Lu, W.Jia, S.Teng and D.Zhang, "Feature Extrac-tion Methods for Palmprint Recognition: A Survey and Eval-uation,"in IEEE Transactions on Systems, Man, and Cyber-netics: Systems, vol. 49, no. 2, pp. 346-363, Feb. 2019, doi: 10.1109/TSMC.2018.2795609.
[21] Lee, J., et al. (2023). "One-Stage Mobile Palmprint Recogni-tion via Keypoint Detection Network."ITC-CSCC.