Joint Attention Network for Finger Vein Authentication

Huang, Junduan; Tu, Mo; Yang, Weili; Kang, Wenxiong

doi:10.1109/tim.2021.3109978

Cited by 37 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, the enrolled image and input image are spatially aligned with the transformation matrix generated by the particle swarm optimization algorithm [6]. The matching score of the line‐based feature between an enrolled and an input forearm vein image is defined as follows:

\begin{array}{l}{\text{Score}}_{2}=\frac{\mathrm{min}\left({n}_{1},{n}_{2}\right)}{\mathrm{max}\left({m}_{1},{m}_{2}\right)}\hfill \end{array}

where

{n}_{1}

and

{n}_{2}

are the numbers of aligned vein‐segment pixels of the enrolled and the input images, respectively;

{m}_{1}

and

{m}_{2}

are the numbers of all vein‐segment pixels in the enrolled and the input images, respectively.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…Next, the enrolled image and input image are spatially aligned with the transformation matrix generated by the particle swarm optimization algorithm [6]. The matching score of the line-based feature between an enrolled and an input forearm vein image is defined as follows:…”

Section: Extraction and Matching Of The Local Structure Descriptorsmentioning

confidence: 99%

“…In recent years, deep learning approaches have been widely used in the field of biometric recognition. Huang et al [6] proposed a network architecture based on the joint attention mechanism for finger vein authentication, which extracts discriminative identity information at the spatial dimension and channel dimension of feature maps. It adopts group convolution to reduce the computational cost and uses the channel shuffle operation to enhance the information flow on the channels between groups.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forearm multimodal recognition based on IAHP‐entropy weight combination

et al. 2022

View full text Add to dashboard Cite

Biometrics are the among most popular authentication methods due to their advantages over traditional methods, such as higher security, better accuracy and more convenience. The recent COVID‐19 pandemic has led to the wide use of face masks, which greatly affects the traditional face recognition technology. The pandemic has also increased the focus on hygienic and contactless identity verification methods. The forearm is a new biometric that contains discriminative information. In this paper, we proposed a multimodal recognition method that combines the veins and geometry of a forearm. Five features are extracted from a forearm Near‐Infrared (Near‐Infrared) image: SURF, local line structures, global graph representations, forearm width feature and forearm boundary feature. These features are matched individually and then fused at the score level based on the Improved Analytic Hierarchy Process‐entropy weight combination. Comprehensive experiments were carried out to evaluate the proposed recognition method and the fusion rule. The matching results showed that the proposed method can achieve a satisfactory performance.

show abstract

\begin{array}{l}{\text{Score}}_{2}=\frac{\mathrm{min}\left({n}_{1},{n}_{2}\right)}{\mathrm{max}\left({m}_{1},{m}_{2}\right)}\hfill \end{array}

where

{n}_{1}

and

{n}_{2}

are the numbers of aligned vein‐segment pixels of the enrolled and the input images, respectively;

{m}_{1}

and

{m}_{2}

are the numbers of all vein‐segment pixels in the enrolled and the input images, respectively.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…Next, the enrolled image and input image are spatially aligned with the transformation matrix generated by the particle swarm optimization algorithm [6]. The matching score of the line-based feature between an enrolled and an input forearm vein image is defined as follows:…”

Section: Extraction and Matching Of The Local Structure Descriptorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forearm multimodal recognition based on IAHP‐entropy weight combination

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, FV-Net [9] leveraged pretrained convolutional neural network to extract regional features of finger veins. FV-GAN [8] employed the powerful Generative Adversarial Network (GAN) to generate vein patterns, and JAFVNet [10] introduced joint attention module to further improve the ability of the network to extract discriminative identity features.…”

Section: Introductionmentioning

confidence: 99%

FV-UPatches: Enhancing Universality in Finger Vein Recognition

Chen¹,

Liu²,

Cao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many deep learning-based models have been introduced in finger vein recognition in recent years. These solutions, however, suffer from data dependency and are difficult to achieve model generalization. To address this problem, we are inspired by the idea of domain adaptation and propose a universal learning-based framework, which achieves generalization while training with limited data. To reduce differences between data distributions, a compressed U-Net is introduced as a domain mapper to map the raw region of interest image onto a target domain. The concentrated target domain is a unified feature space for the subsequent matching, in which a local descriptor model SOSNet is employed to embed patches into descriptors measuring the similarity of matching pairs. In the proposed framework, the domain mapper is an approximation to a specific extraction function thus the training is only a one-time effort with limited data. Moreover, the local descriptor model can be trained to be representative enough based on a public dataset of nonfinger-vein images. The whole pipeline enables the framework to be well generalized, making it possible to enhance universality and helps to reduce costs of data collection, tuning and retraining. The comparable experimental results to state-of-the-art (SOTA) performance in five public datasets prove the effectiveness of the proposed framework. Furthermore, the framework shows application potential in other vein-based biometric recognition as well.

show abstract

“…Finger Vein authentication schemes commonly utilized in various applications for authentication purposes [1,2]. Unlike conventional authentication tools, like PIN, password always at risk of being forgotten or stolen, but the biometric authentication provides the best convenience for the user [3,4]. Privacy is an important concern in finger vein authentication systems [5].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Elman Spike Neural Network Optimized with Glowworm Swarm Optimization for Authentication of Multiple Transaction Using Finger Vein

Mary Joans,

Leena Jasmine,

Ponsudha

2022

SSRN Journal

View full text Add to dashboard Cite

Joint Attention Network for Finger Vein Authentication

Cited by 37 publications

References 41 publications

Forearm multimodal recognition based on IAHP‐entropy weight combination

Forearm multimodal recognition based on IAHP‐entropy weight combination

FV-UPatches: Enhancing Universality in Finger Vein Recognition

Enhanced Elman Spike Neural Network Optimized with Glowworm Swarm Optimization for Authentication of Multiple Transaction Using Finger Vein

Contact Info

Product

Resources

About