Double Quantification of Template and Network for Palmprint Recognition
-
Published:2023-05-29
Issue:11
Volume:12
Page:2455
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Lin Qizhou1ORCID, Leng Lu1ORCID, Kim Cheonshik2ORCID
Affiliation:
1. Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang 330063, China 2. Department of Computer Engineering, Sejong University, Seoul 05006, Republic of Korea
Abstract
The outputs of deep hash network (DHN) are binary codes, so DHN has high retrieval efficiency in matching phase and can be used for high-speed palmprint recognition, which is a promising biometric modality. In this paper, the templates and network parameters are both quantized for fast and light-weight palmprint recognition. The parameters of DHN are binarized to compress the network weight and accelerate the speed. To avoid accuracy degradation caused by quantization, mutual information is leveraged to optimize the ambiguity in Hamming space to obtain a tri-valued hash code as a palmprint template. Kleene Logic’s tri-valued Hamming distance measures the dissimilarity between palmprint templates. The ablation experiments are tested on the binarization of the network parameter, and the normalization and trivialization of the deep hash output value. The sufficient experiments conducted on several contact and contactless palmprint datasets confirm the multiple advantages of our method.
Funder
National Natural Science Foundation of China Technology Innovation Guidance Program Project Innovation Foundation for Postgraduate Student of Nanchang Hangkong University
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference41 articles.
1. Jia, W., Huang, S., Wang, B., Fei, L., Zhao, Y., and Min, H. (2021, January 4–7). Deep Multi-loss Hashing Network for Palmprint Retrieval and Recognition. Proceedings of the 2021 IEEE International Joint Conference on Biometrics (IJCB), Shenzhen, China. 2. Qin, H., Gong, R., Liu, X., Shen, M., Wei, Z., Yu, F., and Song, J. (2020, January 13–19). Forward and Backward Information Retention for Accurate Binary Neural Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. 3. Lin, Q., Leng, L., and Khan, M.K. (2022, January 21–23). Deep Ternary Hashing Code for Palmprint Retrieval and Recognition. Proceedings of the 2022 The 6th International Conference on Advances in Artificial Intelligence, Birmingham, UK. 4. Online Palmpint Identification;Zhang;IEEE Trans. Pattern Anal. Mach. Intell.,2003 5. Kong, A.W.K., and Zhang, D. (2004, January 26). Competitive Coding Scheme for Palmprint Verification. Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Research On Palmprint Recognition Based On Mechanism And Data;Proceedings of the International Conference on Computer Vision and Deep Learning;2024-01-19
|
|