FedFV: A Personalized Federated Learning Framework for Finger Vein Authentication

Recent advancements in finger vein recognition technology: Methodology, challenges and opportunities

The necessity for personal data protection has become increasingly critical in recent years. In this case, an identification system based on multimodal biometric integration is the best option for greatly enhancing and obtaining high performance accuracy. Finger vein is considered an extremely secure and reliable biometric modality used for authentication. Finger vein authentication is a recently developed biometric technology that has gained more attention in the past decade. The traditional methods of finger vein authentication techniques are affected by several factors, such as illumination variations and image misalignments, that lead to inefficient feature extraction. As a result, the authentication system’s overall performance suffers. A convolutional neural network (CNN) is a deep learning–based solution to finger vein authentication that solves the problems that older methods have. This research proposes a deep learning–based feature extraction methodology for finger vein pictures. A convolutional layer, a rectified linear unit (ReLU), batch normaliation, and average pooling layer, followed by a fully connected layer and a softmax layer, make up the proposed CNN. Using a separate collection of images from the SDUMLA finger vein database, the CNN is trained and evaluated, and the suggested approach achieves an overall accuracy of 99.84%.

A new image feature extraction method for face recognition called Tri-direction 2D-Fisher Discriminant Analysis (T2D-FDA) is proposed to deal with the Small Sample Size (SSS) problem in conventional 1D-Fisher Discriminant Analysis (1D-FDA). Moreover, the essence of T2D-FDA is investigated, and the equivalence of the left-multiplying 2D-FDA of the original image matrices and the left-multiplying D2D-FDA of diagonal image matrices is verified if each column is viewed as a computational unit. Different from the 1D-LDA based approaches, the T2D-FDA is based on 2D image matrices rather than column vectors, so the image matrix does not need to be transformed into a long vector before feature extraction. The advantage arising in this way is that the SSS problem does not exist anymore because within-class scatter matrices constructed is full-rank in T2D-FDA. The proposed method is applied to face recognition where only few training images exist for each subject. Experiment results show T2D-FDA outperforms the current linear subspace methods in SSS problem on four public databases: ORL, Yale, AR and FERET face databases.

The integration of finger vein authentication technology to enhance security measures within restricted zones in hospital environments, is the aim of this project. An advanced biometric technique called finger vein authentication uses each person's individual vein patterns to confirm their identification. It is especially desirable for applications where security is critical, such financial transactions, healthcare, and access control, because it provides a very safe and non-intrusive means of authentication. Although there has been considerable success with traditional finger vein authentication methods, deep learning techniques have completely changed this field. A branch of artificial intelligence called deep learning has shown impressive results in pattern recognition and picture analysis, which makes it a prime contender for improving the precision and dependability of finger vein authentication systems. Finger vein authentication utilizes biometric characteristics unique to everyone, providing a highly secure method of identity verification. By implementing this technology, hospitals can bolster access control, prevent unauthorized entry into sensitive areas, and safeguard patient information and critical resources. The project aims to implement finger vein authentication systems to regulate access to restricted areas such as operating rooms, medication storage areas, and patient information sections. Authorized personnel will undergo authentication via finger vein scans for entry, ensuring that only authorized individuals can access these zones.

Linear Discriminant Analysis (LDA) has been one of the popular subspace methods for face recognition. But this method suffers from the small sample size (SSS) problem, also known as 'curse of dimensionality'. Various techniques have been proposed in literature to overcome this limitation. But it is still unclear which method provides the best solution to SSS problem. In this paper, we have investigated the performance of some popular subspace methods such as principal component analysis (PCA), PCA + LDA, LDA via QR decomposition, Null-space LDA, Exponential Discriminant Analysis (EDA), PCA+EDA etc. Extensive experiments have been performed on five publically available face datasets viz. AR, CMU-PIE, PIX, Yale and YaleB. The performance is measured in terms of average classification accuracy. Experimental results show that the performance increases with the increase in the number of images per person in training set irrespective of the datasets. There is no clear winner among the subspace methods under investigation. But, the performance of PCA+LDA and PCA+EDA is consistent in tackling SSS problem irrespective of the dataset and can also handle the illumination variation in face recognition.

We made two contributions in this paper. First, a new method called two-dimensional fisher discriminant analysis (2D-FDA) is proposed to deal with the small sample size (SSS) problem in LDA based face recognition. Second, appearance and depth information are combined to improve face recognition rate. Different from the conventional 1D-FDA (PCA plus LDA) approaches, 2D-FDA is based on 2D image matrices rather than column vectors so the image matrix does not need to be transformed into a long vector before feature extraction. The advantage arising in this way is that the SSS problem does not exist any more because the between-class and within-class scatter matrices constructed in 2D-FDA are both of full-rank. 2D FDA and 1D FDA (PCA plus LDA) are evaluated respectively with a problem that combines appearance and depth information for face recognition. We investigate the complete range of linear combinations to reveal the interplay between these two paradigms. The recognition rate by the combination is better than either appearance alone or depth alone. It is verified that 2D-FDA outperforms 1D FDA

The use of finger veins as biometric authentication is becoming increasingly popular. However, low-quality finger vein images pose challenges, necessitating innovative approaches for accurate authentication. This research investigates the potential of deep learning techniques in addressing this issue, focusing on two prominent architectures: U-Net and the proposed Sequential Model. The study conducts a comparative analysis of the performance of these models in low-quality finger vein image authentication scenarios. U-Net, known for its image segmentation capabilities, is explored for feature extraction, while the Sequential Model, incorporating a modified VGG16 architecture, brings temporal context through LSTM layers. The research presents an in-depth evaluation of both models based on accuracy, recall, precision, and other relevant metrics. The findings shed light on the suitability of each approach for enhancing the reliability of finger vein authentication in challenging data quality contexts.

Compared with single biometric recognition, multimodal biometric recognition based on fingerprint and finger vein has been widely considered because of its convenient sample collection, high security and accurate recognition. However, according to our investigation, there is no public dataset of fingerprint and finger vein collected at the same time. The existing work uses fingerprint datasets and finger vein datasets from different sources for research, besides the researchers data from building their own equipment, which lacks consideration of practical applications. This is not conducive to the promotion of multibiometric technology based on finger. To promote research on multimodal biometric recognition based on fingerprint and finger vein, we design a finger collection device and introduce a new dataset, NUPT-FPV. It is the first public dataset to collect fingerprint and finger vein simultaneously in real-world applications. NUPT-FPV obtained 840 finger information from 140 volunteers, each finger was collected 20 times (collected in two sessions), and 33600 fingerprint and finger vein images were obtained. In addition, we propose a novel multimodal fusion method based on a convolutional neural network as a benchmark. Extensive experiments were conducted to verify the necessity of our dataset. Through the released dataset and benchmark, we hope to further promote the development of multimodal biometrics based on fingerprint and finger vein.

A finger vein authentication system is proposed in this research. Biometrics is the science of determining a person's identity based on physiological or behavioral characteristics. Physical characteristics like fingerprints, a face or a retina, as well as personal characteristics like a signature, are included in these characteristics. Biometric features are significantly more difficult for attackers to replicate or fabricate than traditional methods, and they are extremely rare to lose. Biometric traits are used in the identification system, which increases security and dependability. The technology to verify vein patterns is still relatively new, compared with other human characteristics. The proposed work focuses on developing a contactless sensor to retrieve features from the hand's finger vein pattern using a Deep attribute Representation based Fractional Firefly method (DAR-FFF). Vein pattern identification scans the blood for hemoglobin using an infrared light source. After the participant's palm is placed over the sensing device, an infrared region beam from the device measures the orientation of the arteries. These ultraviolet wavelengths are absorbed by liquid hemoglobin in the vasculature, resulting in dark streaks on the map. The hand's finger has more intricate circulatory pathways and a variety of distinguishing characteristics. Image enhancement, skeletonization, and vein pattern chain code comparison are all processes in this procedure.

Fall is a major threat to stroke survivors with the problems of gait and balance disorders in the rehabilitation phase following severe consequences on quality of life and a heavy burden to their families. Many solutions have been proposed to assess fall risk for elders based on inertial sensor-based signals, however, there still exists a great challenge of transferring them from elderly populations to the stroke-survivors populations as gait disorder patterns are significant difference between elders and stroke survivors. In this study, we conduct a pilot study to collect inertial sensor-based signals from stroke survivors when they performed the timed up and go test, and build an automatic fall risk assessment model with the architecture of Siamese network, with a merit of mitigating the problem of small sample size. Specifically, the proposed automatic fall risk assessment model consists of two parallel convolutional neural networks, each of which is composed of three convolutional layers, two max-pooling layers, and three fully connected layers. To utilize the space relation among accelerator-based and gyroscope-based signals, two-dimensional discrete wavelet transform extracts image-like features, wavelet coefficients, from inertial sensor-based signals as the input. Experimental results show that the proposed fall risk assessment model has achieved a promising results, which outperform cutting-edge methods with a big margin. The proposed fall risk assessment model with low computational complexity and limited memory consuming can be deployed on an embedded system to provide fall risk assessment service for stroke survivors in point-of-care environments or community settings.

Simple sound transmission loss measurements using a modified impedance tube technique

Due to the noise accompanied with fault signals, it is challenging to identify the discriminant information and the local geometric feature from the complex fault data for enhancing fault diagnosis accuracy. To address this challenge, this work proposed an anti-noise algorithm based on locally linear embedding integrated with diffusion distance and maximum correntropy criterion (DMLLE). In DMLLE, diffusion distance was adopted instead of the Euclidean distance for neighborhood construction. Meanwhile, the optimal weights were updated to reveal local geometry information based on the loss function of the maximum correntropy criterion. Subsequently, DMLLE is eventually developed to further restrain noise embedding into raw signals and obtain low dimensional features. Furthermore, weighted extreme gradient boosting is used to map the low dimensional features to the types of faults, which easily implements fault pattern recognition. Finally, two synthetic manifold datasets and fault data acquired from the transmit/receive (T/R) module are used to validate the performance of the proposed diagnosis methodology. Compared with the existing methods, the proposed diagnosis methodology generates a smoother flow structure by preserving the local neighborhood of the dataset with noises and realizes a higher accuracy of 94.41% on the T/R module dataset, which outperforms 3%–9% better than other classification models. Therefore, it can be concluded that the proposed diagnosis methodology can effectively extract intrinsic fault features by weakening the influence aroused by noise and achieve superior accuracy in fault diagnosis by addressing the problem of small sample size.

Underwater image recognition is a very challenging task. To overcome the problems of small sample size and poor image quality, we propose a new deep support vector machine (DSVM) algorithm. The method reduced the feature dimensions and eliminated noise. Moreover, the different kernel functions in the network ensemble are conducive to adapting to the feature distribution of multiple types of targets. In this paper, we firstly proposed a new DSVM network. Then, we use ensemble and “one-to-one”(O-v-O) method to achieve multi-classification. Finally, to evaluate the effectiveness of the proposed method, we conducted verification experiments on three data sets. The experimental results show that the proposed DSVM algorithm can effectively avoid over-fitting and improve the recognition rate in the recognition of multiple types of underwater target images.KeywordsDSVMEnsemble learningMulti-class SVMUnderwater image recognition

ObjectiveEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice.MethodsResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized.ResultsBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics.ConclusionResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.

At present, the study on the pathogenesis of Alzheimer's disease (AD) by multimodal data fusion analysis has been attracted wide attention. It often has the problems of small sample size and high dimension with the multimodal medical data. In view of the characteristics of multimodal medical data, the existing genetic evolution random neural network cluster (GERNNC) model combine genetic evolution algorithm and neural network for the classification of AD patients and the extraction of pathogenic factors. However, the model does not take into account the non-linear relationship between brain regions and genes and the problem that the genetic evolution algorithm can fall into local optimal solutions, which leads to the overall performance of the model is not satisfactory. In order to solve the above two problems, this paper made some improvements on the construction of fusion features and genetic evolution algorithm in GERNNC model, and proposed an improved genetic evolution random neural network cluster (IGERNNC) model. The IGERNNC model uses mutual information correlation analysis method to combine resting-state functional magnetic resonance imaging data with single nucleotide polymorphism data for the construction of fusion features. Based on the traditional genetic evolution algorithm, elite retention strategy and large variation genetic algorithm are added to avoid the model falling into the local optimal solution. Through multiple independent experimental comparisons, the IGERNNC model can more effectively identify AD patients and extract relevant pathogenic factors, which is expected to become an effective tool in the field of AD research.