Finger Vein Presentation Attack Detection Using Convolutional Neural Networks

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

In the recent years, finger vein biometrics has been gaining traction in commercial uses. Despite its wide deployment for user authentication, there is still a risk associated with insecure biometric capture process known as presentation attacks where the attacker uses fake finger vein pattern to spoof the finger vein sensor. This raises the need for an efficient method to detect spoofed finger vein images to ensure the security of the system. In this paper, a multi-scale histogram of oriented gradients representation is proposed for presentation attack detection (PAD) with minimal pre-processing step involved. The results are evaluated with a benchmark dataset and compared with the other PAD methods with promising results.

Finger vein biometric has become most promising recognition method due to its accuracy, reliability and security. This paper discusses a novel technique for finger veins features extraction using Discrete Wavelet Packet Transform (DWPT) based method. The DWPT without HH subband decomposition is applied on ROI of 96×64 size finger veins image up to third level. The average standard deviation and average energy of each decomposition level are used for the creation of features vector database. The Euclidean, City Block and Canberra distance classifiers are used for the classification of finger veins images. The performance of proposed method is evaluated on the standard finger veins image ROI database of SDUMLA Shandong University. Experimental results show that the proposed method gives better results as compare to the standard Discrete Wavelet Transform (DWT) and DWPT Methods.

In this work, we propose an efficient joint Bayesian model that expanded with soft biometric traits for finger vein recognition, which is different from the existing mainstream finger vein recognition methods that extract features from the region of interest (ROI) of finger vein images. First, a two-branch convolutional neural networks (CNNs) is designed to extract feature simultaneously from finger shape images and ROI vein images, respectively, the aim of which is to extract more information from different parts of fingers. Then, two different features are fused by concatenating. Finally, a joint Bayesian recognition loss is used to train the proposed two-branch CNN which is to promote intra-class variance minimization and inter-class variation maximization. Further, in our framework, a end-to-end learning method of CNNs and joint Bayesian recognition loss is achieved to optimize the parameters. Experiments performed on two public finger vein databases demonstrate that the proposed model is efficient and achieves better performance than state-of-the-art methods.

Recent years have seen a plenty of personal identification methods with different biometrics such as finger pattern, face, palm-print and vein. The majority of these methods focus on complex image data projections and transforms in Fourier space, wavelet space or other domains, which usually bring heavy load in computation and difficult understanding in perceptual intuition. Moreover, these methods, oriented to multiple samples learning, are constricted usually in application. Among so much biometrics, vein, as a living feature with high anti-counterfeiting capability, has attracted considerable attention. In this paper, we propose a structured personal identification approach using finger vein Location and Direction Coding(LDC). First of all, we design a finger vein imaging device with near-infrared(NIR) light source, by which a database for finger vein images is established. Subsequently, we make use of the brightness difference in the finger vein image to extract the vein pattern. Furthermore, finger vein LDC is proposed and performed, which creates a structured feature image for each finger vein. Finally, the structured feature image is utilized to conduct the personal identification on our image database for finger vein, which includes 440 vein images from 220 different fingers. The equal error rate of our method for this database is 0.44%.

To carry out the finger vein recognition effectively and quickly, according to the characteristics of horizontal and vertical two-dimensional linear discriminant analysis ((2D)2LDA) reducing the dimensions, an algorithm of finger vein recognition is proposed. The algorithm is two direction weighted (2D)2LDA ((W2D)2LDA) based on preprocessing image of the figure vein image. Firstly, the original finger vein image is pre-processed. Secondly, the normalized vein image is gotten. Finally, the algorithm of this paper is used to be recognized. The effect of the rate of cumulate eigenvalue for 2DLDA and (2D)2LDA is analyzed. The effect of the weighted value and the rate of cumulate eigenvalue on W2DLDA, W(2D)2LDA and (W2D)2LDA are analyzed as well. Experimental results on our database of finger vein images show that the method presented achieves high recognition accuracy. The redundant information of eigenvectors extracted by (2D)2LDA is restrained strongly, and the bi-direction weighted effect is better than the one direction weighted effect. The average recognition rate of (W2D)2LDA is higher than 2DLDA, W2DLDA, (2D)2LDA and W(2D)2LDA.

Finger-vein recognition, a new and advanced biometrics recognition method, is attracting the attention of researchers because of its advantages such as high recognition performance and lesser likelihood of theft and inaccuracies occurring on account of skin condition defects. However, as reported by previous researchers, it is possible to attack a finger-vein recognition system by using presentation attack (fake) finger-vein images. As a result, spoof detection, named as presentation attack detection (PAD), is necessary in such recognition systems. Previous attempts to establish PAD methods primarily focused on designing feature extractors by hand (handcrafted feature extractor) based on the observations of the researchers about the difference between real (live) and presentation attack finger-vein images. Therefore, the detection performance was limited. Recently, the deep learning framework has been successfully applied in computer vision and delivered superior results compared to traditional handcrafted methods on various computer vision applications such as image-based face recognition, gender recognition and image classification. In this paper, we propose a PAD method for near-infrared (NIR) camera-based finger-vein recognition system using convolutional neural network (CNN) to enhance the detection ability of previous handcrafted methods. Using the CNN method, we can derive a more suitable feature extractor for PAD than the other handcrafted methods using a training procedure. We further process the extracted image features to enhance the presentation attack finger-vein image detection ability of the CNN method using principal component analysis method (PCA) for dimensionality reduction of feature space and support vector machine (SVM) for classification. Through extensive experimental results, we confirm that our proposed method is adequate for presentation attack finger-vein image detection and it can deliver superior detection results compared to CNN-based methods and other previous handcrafted methods.

Recently, finger vein sensors have been embedded in all kinds of electronic devices for personal identification, such as intelligent door locks and attendance machines. The embedded sensors are generally small, thus capturing only part of the finger vein. However, prior studies have focused on near-full finger vein recognition, without considering the partial finger vein image caused by the small imaging window of the finger vein sensor. This paper aims to study personal identification based on partial finger vein images, known as small-area finger vein recognition. The effect of the small-area finger vein on recognition performance is first analyzed by cutting out the local part from the near-full finger vein image to model a small-area finger vein image. Second, a small-area finger vein database is built using a commercial finger vein imaging device, in which the vein pattern from approximately one-third of one adult finger is captured. To explore more discriminative information from small-area finger vein images, we propose a locality-constrained consistent dictionary learning (LCDL) method to fuse multiple features for small-area finger vein recognition. Finally, the proposed method is evaluated on the self-built small-area finger vein database and four synthetic small-area finger vein databases. Experimental results show the promising recognition performance of the proposed method.

Finger vein recognition has received more attention in recent years due to its high security and promising development potential. However, extracting complete vein patterns and obtaining features from the original images suffer from the low contrast of finger vein images, which dramatically restrains the performance of finger vein recognition algorithms. Inspired by this motivation, we propose an explicit and implicit feature fusion Network (EIFNet) for finger vein verification. It can extract more comprehensive and discriminative features by complementarily fusing the features extracted from binary vein masks and gray original images. We design a feature fusion module (FFM) acting as a bridge between mask feature extraction module (MFEM) and contextual feature extraction module (CFEM) to achieve the optimal fusion of features. To obtain more accurate vein masks, we develop a novel finger vein pattern extraction method and provide the first finger vein segmentation dataset THUFVS. We solve the difficulty of building finger vein segmentation datasets in a simple but effective way, and develop a complete process encompassing dataset creation, data augmentation refinement and network design, which refers to the Mask Generation Module (MGM), for the deep learning based finger vein pattern extraction method. Experimental results demonstrate the superior verification performance of EIFNet on three widely used datasets compared with other existing methods.

Finger vein recognition is a promising biometric authentication technique that depends on the unique features of vein patterns in the finger for recognition. The existing finger vein recognition methods are based on minutiae features or binary features such as LBP, LLBP, PBBM etc. or from the entire vein pattern. However, the minutiae-based features cannot accurately represent the structural or anatomical aspects of the vein pattern. These issues with the minutia feature led to increased false matches. Recognition based on binary features have limitations such as increased false matches, sensitivity to the translation and rotation, security and privacy issues etc. A feature representation based on the anatomy of vein patterns can be an alternative solution to improve the recognition performance. In the IJCB 2020 conference, we showed that every finger vein image contains one or more of a kind of 4 special vein patterns which we refereed as Fork, Eye, Bridge, and Arch (FEBA). In this paper, we further enlarge this set to 6 vein patterns (F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> EB <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> B <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> A) by identifying two variations in the Fork and Bridge vein patterns. Based on 6 anatomical features of the possible 6 vein patterns in a vein image, we define a 6 × 6 feature matrix representation for finger vein images. Since this feature representation is based on the anatomical properties of the local vein patterns, it provides template security. Further we show that, the proposed feature representation is invariant to scaling, translation, and rotation changes. The experimental results using two open datasets and an in-house dataset show that the proposed method has a better recognition performance when compared to the existing approaches with an EER around 0.02% and an average recognition accuracy of 98%.

Exploring finger vein based personal authentication for secure IoT

Among the many biometric recognition techniques, finger vein recognition has many advantages, such as in-vivo recognition, high anti-counterfeiting, high acceptability, and high stability, etc., but the structure of finger vein is simple and the available information is less. The traditional feature extraction method is not fully used to extract finger vein structure information. In this paper, discrete separable shearlet transformation (DSST) are used to extract finger vein features. DSST is used to decompose the image of finger vein, and the decomposition coefficient is obtained and analyzed. The experimental results show that this method can provide an effective and sparse feature description of the original finger vein image, and also obtain a good recognition effect when the quality of some images is poor.

Today, face biometric systems are becoming widely accepted as a standard method for identity authentication in many security settings. For example, their deployment in automated border control gates plays a crucial role in accurate document authentication and reduced traveler flow rates in congested border zones. The proliferation of such systems is further spurred by the advent of portable devices. On the one hand, modern smartphone and tablet cameras have in-built user authentication applications while on the other hand, their displays are being consistently exploited for face spoofing. Similar to biometric systems of other physiological biometric identifiers, face biometric systems have their own unique set of potential vulnerabilities. In this work, these vulnerabilities (presentation attacks) are being explored via a biologically-inspired presentation attack detection model which is termed “BIOPAD.” Our model employs Gabor features in a feedforward hierarchical structure of layers that progressively process and train from visual information of people's faces, along with their presentation attacks, in the visible and near-infrared spectral regions. BIOPAD's performance is directly compared with other popular biologically-inspired layered models such as the “Hierarchical Model And X” (HMAX) that applies similar handcrafted features, and Convolutional Neural Networks (CNN) that discover low-level features through stochastic descent training. BIOPAD shows superior performance to both HMAX and CNN in all of the three presentation attack databases examined and these results were consistent in two different classifiers (Support Vector Machine and k-nearest neighbor). In certain cases, our findings have shown that BIOPAD can produce authentication rates with 99% accuracy. Finally, we further introduce a new presentation attack database with visible and near-infrared information for direct comparisons. Overall, BIOPAD's operation, which is to fuse information from different spectral bands at both feature and score levels for the purpose of face presentation attack detection, has never been attempted before with a biologically-inspired algorithm. Obtained detection rates are promising and confirm that near-infrared visual information significantly assists in overcoming presentation attacks.

The vulnerability of finger vein recognition to spoofing attacks has emerged as a crucial security problem in the recent years mainly due to the high security applications where biometric technology is used. Recent works shown that finger vein biometrics is vulnerable to spoofing attacks, pointing out the importance to investigate counter-measures against this type of fraudulent actions. The goal of the 1st Competition on Counter Measures to Finger Vein Spoofing Attacks is to challenge researchers to create counter-measures that can detect printed attacks effectively. The submitted approaches are evaluated on the Spoofing-Attack Finger Vein Database and the achieved results are presented in this paper.

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.