Improved Lightweight Convolutional Neural Network for Finger Vein Recognition System

Hsia, Chih-Hsien; Ke, Liang-Ying; Chen, Shengtao

doi:10.3390/bioengineering10080919

Cited by 5 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the effectiveness of our proposed model, its performance was compared with other lightweight models focusing on the Correct Identity Rate (CIR) and model parameters. The comparative analysis included the following baseline models: ResNet-50 [47], which represents a deep model architecture; Inception V3 [2], exemplifying a wider model architecture; and other state-of-the-art mobile networks such as MobileNet [36,37], MobileViT [38], EfficientNet [48], and ILCNN [30]. All of the models underwent evaluation under uniform conditions to ensure a fair comparison.…”

Section: Resultsmentioning

confidence: 99%

“…Zhao introduced a lightweight CNN that incorporates a center loss function and dynamic regularization to tackle image quality issues and expedite convergence, demonstrating decreased error rates and enhanced computational efficiency [29]. Furthermore, Hsia's [30] improved lightweight CNN (ILCNN) addresses translation-induced accuracy problems and enhances parameter efficiency using diverse branch blocks (DBB) [31], adaptive polyphase sampling (APS) [32], and a coordinate attention mechanism (CoAM) [33]. This model not only achieves high accuracy but does so with a minimal parameter count of just 1.23 million.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Zero-FVeinNet: Optimizing Finger Vein Recognition with Shallow CNNs and Zero-Shuffle Attention for Low-Computational Devices

Tran,

Pham,

Chu

et al. 2024

Electronics

View full text Add to dashboard Cite

In the context of increasing reliance on mobile devices, robust personal security solutions are critical. This paper presents Zero-FVeinNet, an innovative, lightweight convolutional neural network (CNN) tailored for finger vein recognition on mobile and embedded devices, which are typically resource-constrained. The model integrates cutting-edge features such as Zero-Shuffle Coordinate Attention and a blur pool layer, enhancing architectural efficiency and recognition accuracy under various imaging conditions. A notable reduction in computational demands is achieved through an optimized design involving only 0.3 M parameters, thereby enabling faster processing and reduced energy consumption, which is essential for mobile applications. An empirical evaluation on several leading public finger vein datasets demonstrates that Zero-FVeinNet not only outperforms traditional biometric systems in speed and efficiency but also establishes new standards in biometric identity verification. The Zero-FVeinNet achieves a Correct Identification Rate (CIR) of 99.9% on the FV-USM dataset, with a similarly high accuracy on other datasets. This paper underscores the potential of Zero-FVeinNet to significantly enhance security features on mobile devices by merging high accuracy with operational efficiency, paving the way for advanced biometric verification technologies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Zero-FVeinNet: Optimizing Finger Vein Recognition with Shallow CNNs and Zero-Shuffle Attention for Low-Computational Devices

Tran,

Pham,

Chu

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Our results demonstrate the potential of the LDA-FV model in practical applications, which offers a balance between efficiency, accuracy, and ease of deployment in real-world environments. Params (M) Semi-PFVN (28) 94.67 3.35 MMRAN (12) 96.07 3.51 LightFVN + ACE (29) 96.17 2.65 W. Liu et al (27) 98.58 5.85 LFVRN_CE + ACE (24) 99.09 4.93 EfficientNet-B0 (38) 99.70 4.64 ILCNN (39) 99.82 1.23 FV-RSA (40) 99.90 8.70 LDA-FV (This work) 99.90 1.20…”

Section: Discussionmentioning

confidence: 99%

“…Methods CIR (%) LED Laser DenseNet-121 (41) 93.06 93.19 EfficientNet-B0 (38) 95.82 92.22 ILCNN (39) 95.90 93.52 LDA-FV (This work) 97.50 97. 22…”

Section: Discussionmentioning

confidence: 99%

Finger-vein Secure Access Based on Lightweight Dual-attention Convolutional Neural Network for Quality Distance Education

Ke,

Hsia

2024

Sensors and Materials

View full text Add to dashboard Cite

As global average fertility rates decline annually, a crisis brought by declining birthrates gradually emerges, further impacting the existing education system. In response to the impact of declining birthrates on education, countries have recently accelerated the development of distance learning. Distance learning provides guaranteed access to comprehensive and quality education while encouraging continuous learning opportunities for everyone. However, the identity recognition technology used in the current distance learning platform seldom addresses the problem of inconsistent image quality in actual scenarios, making it difficult to ensure the practical application of the model. To solve these issues, we propose a lightweight dual-attention convolutional neural network (LDA-FV) constructed through a dual attention-based inverted residual block (DA-IRB) and implemented using an adaptive margin loss (AML) function for finger-vein recognition. This method not only extracts effective finger-vein features through DA-IRB but also adjusts the training difficulty in accordance with the image quality. Furthermore, owing to its lightweight design, the model can be more flexibly deployed on existing hardware devices (e.g., mouse) in distance education scenarios. The experimental results of this study indicate that the proposed method effectively enhanced the model's recognition capability using the finger-vein database of the University Sains Malaysia (FV-USM) and the PLUSVein dorsal-palmar finger-vein (PLUSVein-FV3) public database, achieving correct identification rates (CIRs) of 99.90% and 97.50%, respectively.

show abstract

“…Biometric characteristics can be divided into two categories: extrinsic characteristics and intrinsic characteristics. Biometric systems that use extrinsic characteristics usually rely on external features of the human body, such as fingerprints, faces, and irises [3]. Even though biometric systems that utilize extrinsic characteristics are less susceptible to theft than conventional methods, they are vulnerable in practice to forged input, raising privacy and security concerns [4].…”

Section: Introductionmentioning

confidence: 99%

Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling

Devkota,

Kim

2024

Electronics

View full text Add to dashboard Cite

This paper proposes SE-DenseNet-HP, a novel finger vein recognition model that integrates DenseNet with a squeeze-and-excitation (SE)-based channel attention mechanism and a hybrid pooling (HP) mechanism. To distinctively separate the finger vein patterns from their background, original finger vein images are preprocessed using region-of-interest (ROI) extraction, contrast enhancement, median filtering, adaptive thresholding, and morphological operations. The preprocessed images are then fed to SE-DenseNet-HP for robust feature extraction and recognition. The DenseNet-based backbone improves information flow by enhancing feature propagation and encouraging feature reuse through feature map concatenation. The SE module utilizes a channel attention mechanism to emphasize the important features related to finger vein patterns while suppressing less important ones. HP architecture used in the transitional blocks of SE-DenseNet-HP concatenates the average pooling method with a max pooling strategy to preserve both the most discriminative and contextual information. SE-DenseNet-HP achieved recognition accuracy of 99.35% and 93.28% on the good-quality FVUSM and HKPU datasets, respectively, surpassing the performance of existing methodologies. Additionally, it demonstrated better generalization performance on the FVUSM, HKPU, UTFVP, and MMCBNU_6000 datasets, achieving remarkably low equal error rates (EERs) of 0.03%, 1.81%, 0.43%, and 1.80%, respectively.

show abstract

Improved Lightweight Convolutional Neural Network for Finger Vein Recognition System

Cited by 5 publications

References 27 publications

Zero-FVeinNet: Optimizing Finger Vein Recognition with Shallow CNNs and Zero-Shuffle Attention for Low-Computational Devices

Zero-FVeinNet: Optimizing Finger Vein Recognition with Shallow CNNs and Zero-Shuffle Attention for Low-Computational Devices

Finger-vein Secure Access Based on Lightweight Dual-attention Convolutional Neural Network for Quality Distance Education

Finger Vein Recognition Using DenseNet with a Channel Attention Mechanism and Hybrid Pooling

Contact Info

Product

Resources

About