Multimodal Finger Recognition Based on Asymmetric Networks With Fused Similarity
Authors:
Open Access
- 6 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 17497-17509
Abstract
Multimodal biometric system has received increasing interest as it offers a more secure and accurate authentication solution than unimodal systems. However, existing biometric fusion methods are still inadequate in dealing with correlations and redundancy of multimodal features simultaneously, causing bottlenecks in performance improvement. To overcome the above problem, this paper proposes an end-to-end multimodal finger recognition model that incorporates attention mechanisms into a similarity-aware encoder to achieve accurate recognition results for accurate identification results. Firstly, due to the different distribution of fingerprint and finger vein images, we propose a finger asymmetric backbone network (FAB-Net) for extracting discriminative intra-modal features, which reduces the network width by efficient utilization of feature maps. Then, a novel attention-based encoder fusion network (AEF-Net) with fused similarity performs dimensionality reduction-based fusion on multimodal multilevel features to alleviate performance degradation due to information redundancy. We also introduce channel attention in AEF-Net, which differs from the traditional attention mechanism by considering interdependencies between modalities to further improve performance. Extensive recognition experiments are conducted on three multimodal finger databases to verify the effectiveness of our method compared to state-of-the-art methods. Detailed ablation studies have also been carried out, which demonstrated that encoder-based reconstruction of redundant information can improve recognition performance.Keywords
Funding Information
- Heilongjiang Provincial Natural Science Foundation (LH2022F047)
- Special Fund of Fundamental Scientific Research Business Expense for Higher School of Heilongjiang Province (2021-KYYWF-0002)
This publication has 39 references indexed in Scilit:
- A fingerprint and finger-vein based cancelable multi-biometric systemPattern Recognition, 2018
- Multimodal Machine Learning: A Survey and TaxonomyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Multimodal deep learning for robust RGB-D object recognition2015
- Fusion of Band Limited Phase Only Correlation and Width Centroid Contour Distance for finger based biometricsExpert Systems with Applications, 2014
- Multiscale Local Phase Quantization for Robust Component-Based Face Recognition Using Kernel Fusion of Multiple DescriptorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Human Identification Using Finger ImagesIEEE Transactions on Image Processing, 2011
- Fingerprint verification competition 2006Biometric Technology Today, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Information fusion in biometricsPattern Recognition Letters, 2003
- Person identification using multiple cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995