Hand Vein Recognition Research Articles

Deep learning techniques for hand vein biometrics: A comprehensive review

Biometric authentication has garnered significant attention as a secure and efficient method of identity verification. Among the various modalities, hand vein biometrics, including finger vein, palm vein, and dorsal hand vein recognition, offer unique advantages due to their high accuracy, low susceptibility to forgery, and non-intrusiveness. The vein patterns within the hand are highly complex and distinct for each individual, making them an ideal biometric identifier. Additionally, hand vein recognition is contactless, enhancing user convenience and hygiene compared to other modalities such as fingerprint or iris recognition. Furthermore, the veins are internally located, rendering them less susceptible to damage or alteration, thus enhancing the security and reliability of the biometric system. The combination of these factors makes hand vein biometrics a highly effective and secure method for identity verification.This review paper delves into the latest advancements in deep learning techniques applied to finger vein, palm vein, and dorsal hand vein recognition. It encompasses all essential fundamentals of hand vein biometrics, summarizes publicly available datasets, and discusses state-of-the-art metrics used for evaluating the three modes. Moreover, it provides a comprehensive overview of suggested approaches for finger, palm, dorsal, and multimodal vein techniques, offering insights into the best performance achieved, data augmentation techniques, and effective transfer learning methods, along with associated pretrained deep learning models. Additionally, the review addresses research challenges faced and outlines future directions and perspectives, encouraging researchers to enhance existing methods and propose innovative techniques.

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Improved Unsupervised Deep Boltzmann Learning Approach for Accurate Hand Vein Recognition

Boosting hand vein recognition performance with the fusion of different color spaces in deep learning architectures

Boosting hand vein recognition performance with the fusion of different color spaces in deep learning architectures

Dorsal hand vein biometrics with a novel deep learning approach for person identification

Hand dorsal biometric recognition system proposed in this study combines the strength of information in regions of dorsal vein biometric trait in a deep learning based Convolutional Neural Networks (CNN) model. The approach divides each dorsal image into five overlapping regions; consequently, five different training and test sets are obtained for each image, modeling a multi-modal biometric system while using only one trait. The test outputs are combined by score-level fusion. Experimental results on FYO, Bosphorus and Badawi datasets indicate the efficiency of the proposed method and its comparability with other recognition systems. The results are also compared with the state-of-the-art dorsal hand vein recognition systems to show the ability of the proposed biometric architecture to perform well in different conditions that may affect dorsal vein pattern acquisition and have con-sequent effect on the efficiency of the recognition system.

Recognition of Dorsal Hand Vein in Small-Scale Sample Database Based on Fusion of ResNet and HOG Feature

As artificial intelligence develops, deep learning algorithms are increasingly being used in the field of dorsal hand vein (DHV) recognition. However, deep learning has high requirements regarding the number of samples, and current DHV datasets have few images. To solve the above problems, we propose a method based on the fusion of ResNet and Histograms of Oriented Gradients (HOG) features, in which the shallow semantic information extracted by primary convolution and HOG features are fed into the residual structure of ResNet for full fusion and, finally, classification. By adding Gaussian noise, the North China University of Technology dataset, the Shandong University of Science and Technology dataset, and the Eastern Mediterranean University dataset are extended and fused to from a fused dataset. Our proposed method is applied to the above datasets, and the experimental results show that our proposed method achieves good recognition rates on each of the datasets. Importantly, we achieved a 93.47% recognition rate on the fused dataset, which was 2.31% and 26.08% higher than using ResNet and HOG alone.

Dorsal hand vein recognition based on transmission-type near infrared imaging and deep residual network with attention mechanism

Dorsal hand vein recognition based on transmission-type near infrared imaging and deep residual network with attention mechanism

Robust Vein Recognition against Rotation Using Kernel Sparse Representation

Sparse representation due to advantages such as noise-resistant and, having a strong mathematical theory, has been noticed as a powerful tool in recent decades. In this paper, using the sparse representation, kernel trick, and a different technique of the Region of Interest (ROI) extraction which we had presented in our previous work, a new and robust method against rotation is introduced for dorsal hand vein recognition. In this method, to select the ROI, by changing the length and angle of the sides, undesirable effects of hand rotation during taking images have largely been neutralized. So, depending on the amount of hand rotation, ROI in each image will be different in size and shape. On the other hand, because of the same direction distribution on the dorsal hand vein patterns, we have used the kernel trick on sparse representation to classification. As a result, most samples with different classes but the same direction distribution will be classified properly. Using these two techniques, lead to introduce an effective method against hand rotation, for dorsal hand vein recognition. Increases of 2.26% in the recognition rate is observed for the proposed method when compared to the three conventional SRC-based algorithms and three classification methods based sparse coding that used dictionary learning.

Improvement of confusion matrix for Hand Vein Recognition Based On Deep- Learning multi-classifier Decisions

In this paper, recognition of the hand vein patterns approach is proposed employing the Convolutional Neural Network (CNN). This approach is routinely well-learned in what way to get features from the main pattern using Region of Interest (ROI). Though, the poor quality of the hand vein image still attitudes an unlimited strain to the extension leads of its usability. Firstly, by applying the method of Generative adversarial networks (GAN) data augmentation the performance gain of adding GAN generated data exceeds that of adding more true images, and apply ROI in a hand vein image feature extraction is studied initially. Secondly, the suggested approach is tested on the data sets of hand veins to decrease the overfitting in the fully connecting layer of CNN which this model proves the most effective one. In total, 1575 hand vein images from 100 subjects are applied to authorize the proposed approach for hand vein. A high accuracy (>99.8%) and low False Rejection Rate(FRR) (<0.99%) were achieved by applying the suggested approach, when compared with the existing CNN classifiers, indicating the efficiency of the suggested approach.

Dorsal Hand Vein Recognition Using Very Deep Learning

AbstractDesigning a deep neural network for multiclass classification is a challenging task in comparison to binary classification. In this paper, a very deep learning model for dorsal hand vein recognition is presented. Deep learning models may contain hundreds of hidden layers. The increase in layers makes a model complex and it takes much time to train especially on CPU instead of GPU. The proposed model consists of network of Convolution layers and ReLU layers followed by one Global Average Pooling layer and two dense layers. To keep the model stable, batch normalization is applied on input and hidden layers and Adam optimizer is used to optimize the model. For the training and testing purpose two self‐constructed datasets are used, first having 1200 dorsal hand vein images of children of age ranging from 5 to 12 years and second having 2000 dorsal hand vein images from 100 adults. The accuracy of the proposed model is compared with two recent contributions, which also used self‐constructed datasets. The accuracy of the proposed system observed is 98.33% when trained and tested with children' dataset, and 100% when trained and tested with adults' dataset.

Hand vein recognition with rotation feature matching based on fuzzy algorithm

The Bodily motion or emotion, which can be obtained for example from a hand or a face, originates gestures. Every individual has a unique pattern of dorsal hand veins. The vein pattern's orientation changes when one rotates their hand in a particular direction. This study focused on hand-gesture recognition using dorsal hand veins. The aim of this work is a novel technique to track and recognizing hand vein rotation using fuzzy neural network, and the change in orientation was considered as a gesture and measured. The algorithms were tested over various rotations ranging from $-45^{circ}$ to $+45^{circ}$. We successfully detected various rotations in both clockwise and anti-clockwise directions, achieving $93%$ accuracy and a reasonable time execution. This problem can be solved because a person can steer a car wheel merely by rotating his/her hand. An infrared camera captured the rotation of hand veins, so car wheel steering was unnecessary.

Real-Time Dorsal Hand Recognition Based on Smartphone

The integration of biometric recognition with smartphones is necessary to increase security, especially in financial transactions such as online payments. Vein recognition of the dorsal hand is superior to other methods such as palm, finger, and wrist, as it has a wide area to be captured and does not have any wrinkles. Most current systems that depend on dorsal hand vein recognition do not work in real-time and have poor results. In this paper, a dorsal hand recognition system working in real-time is proposed to achieve good results with a high frame rate. A contactless device consists of a universal serial bus (USB)camera and infrared LEDs and is connected to a smartphone used to collect our dataset. The dataset contained 2200 images collected from both hands of 100 individuals. The captured images were processed with light algorithms to improve the real-time performance and increase the frame rate. The feature detection and extraction algorithm is oriented FAST and rotated BRIEF (ORB) with K-nearest neighbors (K-NN) matching to match features. Another benchmark, called the Poznan University of Technology (PUT) dataset, is used to measure the efficiency of the proposed system. The results obtained from experimental testing showed that the proposed system had a low equal error rate (EER) of 4.33% and a high frame rate of 29 frames per second.

A Recognition System for Partially Occluded Dorsal Hand Vein Using Improved Biometric Graph Matching

Some portions of dorsal hand may be occluded due to injuries, pigmentation, or tattoos, which significantly affects the performance of dorsal hand vein recognition systems. Biometric graph matching is a common shape-based feature extraction algorithm for vein recognition. However, this method does not consider edge attributes, which can provide additional discrimination ability. We present an improved biometric graph matching method that includes edge attributes for graph registration and a matching module to extract discriminating features. Moreover, we propose a recognition system for partially occluded dorsal hand vein. A database of normal hand vein images, three databases of images with artificially occluded dorsal hand vein with occlusions in different positions and ratios, and a database of images with tattooed hands are established to verify the validity of the proposed method. The experimental results demonstrated that the equal error rates and the accuracies were 0.0202 and 98.09% ± 0.28%, respectively for the normal hand vein images, 0.0453 and 96.58% ± 0.34%, respectively for images of artificially occluded dorsal hand vein with occlusion at all positions and area ratios (0 - 20%, mean occluded area ratio = 9.3%), and 0.0343 and 97.14% ± 0.29%, respectively for the images of tattooed hands.

An Efficient Dorsal Hand Vein Recognition Security System Using Arduino And Gsm Technology

With the onset of maximum power, modest figuring and more prominent unpredictability, biometric verification has turned out to be conceivable at each scale in light of its more secure nature and furthermore easy to use conduct. Compare to other biometrics, vein biometric is a decent verification characteristic among others. The dorsal hand vein recognition is an emerging biometric procedure which is utilized for verification purposes in many applications. In this work pre-processing is done by median filter and region of interest such as veins separated from the muscles and bones through adaptive K-means clustering algorithm.The proposed method extracts the dorsal hand vein pattern features by using LBP and Repeated Line Tracking algorithm.Finally recognition and authentication is done using Artificial Neural Network. Arduino and GSM technology is used in this work to set security preference for the particular user.In order to validate the proposed work , a total of 480 images of dorsal hand veins is involved in this work. In a comparison with four existingverification algorithms, the proposed method achieves thehighest accuracy with lowest error rate.

Hand Vein Recognition Algorithm Based on NMF with Sparsity and Clustering Property Constraints in Feature Mapping Space

Most of the existed vein features are lack of robustness to light intensity variation, and some algorithms rely on the specified vein data sets, which leads to the limitation of real applications. To solve the problems, we propose a novel vein recognition algorithm based on Nonnegative matrix factorization (NMF) with double regularization terms. The innovations of our algorithm are mainly reflected in the following two aspects: in order to improve feature robustness, a novel feature mapping function is designed to map the initial Histogram of oriented gradient (HOG) feature to a new space; to enhance the recognition performance, an effective NMF model is presented, which not only reduces feature dimension, but also optimizes the feature sparsity and clustering property simultaneously. Experiments show that the proposed algorithm can achieve satisfactory results in terms of False rejection rate (FRR) and False acceptance rate (FAR), which indicates that our algorithm is valuable for other classification problems.

Zernike moment invariants for hand vein pattern description from raw biometric data

We propose an invariant description method based on Zernike moments to classify hand vein patterns from raw infrared (IR) images. Orthogonal moments provide linearly independent descriptors and are invariant to affine transformations, such as translation, rotation, and scaling. A mathematical expression is given to derive a set of moment invariants. The obtained features have all the properties of moment invariants with the additional feature of image contrast invariance. For dorsal hand vein pattern acquisition, an IR imaging system is implemented. Also, a public database is used for a palm vein recognition task. A correct rate classification (CRC) above 99.9% is achieved using a set of rotation, scale, and intensity Zernike moment invariants. Additionally, multilayer perceptron and K-nearest neighbors are used as classifiers having as input data the Zernike normalized moments. A discriminative feature evaluation of the image moments allows the reduction of the number of descriptors while maintaining a high classification rate of 99%. The efficiency of the moment descriptors is evaluated in terms of accuracy and reduced computational cost by (a) avoiding the necessity of a preprocessing stage and (b) reducing the feature vector dimension. Experimental results show that Zernike moment invariants are able to achieve hand vein recognition without image preprocessing or image normalization with respect to change of size, rotation, and intensity.

Recognition of Dorsal Hand Vein Based Bit Planes and Block Mutual Information.

The dorsal hand vein images captured by cross-device may have great differences in brightness, displacement, rotation angle and size. These deviations must influence greatly the results of dorsal hand vein recognition. To solve these problems, the method of dorsal hand vein recognition was put forward based on bit plane and block mutual information in this paper. Firstly, the input gray image of dorsal hand vein was converted to eight-bit planes to overcome the interference of brightness inside the higher bit planes and the interference of noise inside the lower bit planes. Secondly, the texture of each bit plane of dorsal hand vein was described by a block method and the mutual information between blocks was calculated as texture features by three kinds of modes to solve the problem of rotation and size. Finally, the experiments cross-device were carried out. One device was used to be registered, the other was used to recognize. Compared with the SIFT (Scale-invariant feature transform, SIFT) algorithm, the new algorithm can increase the recognition rate of dorsal hand vein from 86.60% to 93.33%.

Dorsal Hand Vein Recognition by Convolutional Neural Networks: Feature Learning and Transfer Learning Approaches

Dorsal Hand Vein Recognition by Convolutional Neural Networks: Feature Learning and Transfer Learning Approaches

Hand vein biometric recognition approaches based on wavelet, SVM, artificial neural network and image registration

This paper describes in detail different hand vein recognition methods based on Wavelet-SVM, Wavelet-ANN and Image Registration. A new image segmentation and processing algorithm is proposed to efficiently locate vein regions and suitable for feature extraction (wavelet coefficients and normalized vein imagens) and classification (SVM, ANN and Image Registration). For real time recognition and high recognition rate, we proposed an integrated system which combines three above mentioned classification methods. The simulation results reveal that the proposed integrated system achieves 1% false rejection rate (FRR) and 0.02% false acceptance rate.

Towards application of dorsal hand vein recognition under uncontrolled environment based on biometric graph matching

Dorsal hand vein recognition is a kind of biometric technique that has emerged in the last two decades. Owing to its safety, accuracy, and effectiveness, more and more researchers are involved in the study. Here, the authors presented a dorsal hand vein recognition system under uncontrolled environments based on biometric graph matching (BGM). Firstly, the authors establish two hand vein databases under natural indoor lighting conditions, i.e. XJTU-A and XJTU-B, with the hand not fixed. Secondly, the authors focus on optimising the image preprocessing steps in terms of region of interest (ROI) extraction, vein segmentation, and vein skeleton extraction. An `open' operation with a large parameter is carried out to make the ROI extraction more abundant based on the maximum inscribed circle. In vein segmentation, the authors use the curvature point algorithm to better extract the vein skeleton. Thirdly, BGM algorithm is adopted to obtain distance measurements. The authors use single distance measure and multiple distance measures to obtain the threshold for recognition, respectively. Finally, the proposed dorsal hand vein recognition system is tested in three databases, and experiment results show that the improvement of the entire algorithms leads to high accuracy and strong robustness of the recognition system, whether under uncontrolled or controlled conditions.

Single-sensor hand-vein multimodal biometric recognition using multiscale deep pyramidal approach

Biometrics has emerged as a powerful technology for person authentication in various scenarios including forensic and civilian applications. Deployment of biometric solutions that use cues from multiple modalities enhances the reliability and robustness of authentication necessary to meet the increasingly stringent security requirements. However, there are two drawbacks typically associated with multimodal biometrics. Firstly, the image acquisition process in such systems is not very user-friendly, primarily due to the time and effort required to capture biometric samples belonging to multiple modalities. Secondly, the overall cost is higher as they employ multiple biometric sensors. To overcome these drawbacks, we employ a single NIR sensor-based image acquisition in the proposed approach for hand-vein recognition. From the input hand image, a palm-vein and four finger-vein subimages are extracted. These images are then enhanced by CLAHE and transformed into illumination invariant representation using center-symmetric local binary pattern (CS-LBP). Further, a hierarchical non-rigid matching technique inspired by the architecture of deep convolutional networks is employed for matching the CS-LBP features. Finally, weighted sum rule-based matching score-level fusion is performed to combine the palm-vein and the four finger-vein modalities. A set of rigorous experiments has been performed on an in-house database collected from the left and right hands of 185 subjects and the publicly available CASIA dataset. The proposed approach achieves equal error rates of 0.13% and 1.21%, and rank-1 identification rates of 100% and 100% on the in-house and CASIA datasets, respectively. Additionally, we compare the proposed approach with the state-of-the-art techniques proposed for vascular biometric recognition in the literature. The important findings are (1) the proposed approach outperforms all the existing techniques considered in this study, (2) the fusion of palm-vein and finger-vein modalities consistently leads to better performance for all the feature extraction techniques considered in this work. (3) Furthermore, our experimental results also suggest that considering the constituent palm-vein and finger-vein images instead of the entire hand-vein images achieves better performance.