Biometric Recognition System Research Articles

Score Level and Rank Level Fusion for Kinect-Based Multi-Modal Biometric System

Abstract Computational intelligence firmly made its way into the areas of consumer applications, banking, education, social networks, and security. Among all the applications, biometric systems play a significant role in ensuring an uncompromised and secure access to resources and facilities. This article presents a first multimodal biometric system that combines KINECT gait modality with KINECT face modality utilizing the rank level and the score level fusion. For the KINECT gait modality, a new approach is proposed based on the skeletal information processing. The gait cycle is calculated using three consecutive local minima computed for the distance between left and right ankles. The feature distance vectors are calculated for each person’s gait cycle, which allows extracting the biometric features such as the mean and the variance of the feature distance vector. For Kinect face recognition, a novel method based on HOG features has been developed. Then, K-nearest neighbors feature matching algorithm is applied as feature classification for both gait and face biometrics. Two fusion algorithms are implemented. The combination of Borda count and logistic regression approaches are used in the rank level fusion. The weighted sum method is used for score level fusion. The recognition accuracy obtained for multi-modal biometric recognition system tested on KINECT Gait and KINECT Eurocom Face datasets is 93.33% for Borda count rank level fusion, 96.67% for logistic regression rank-level fusion and 96.6% for score level fusion.

Automatic Ear Detection and Segmentation over Partially Occluded Profile Face Images

Automated, non invasive ear detection in images and video is becoming increasingly required in several contexts, including nonivasive biometric identification, biomedical analysis, forensics, and many others. In biometric recognition systems, fast and robust ear detection is a crucial step within the recognition pipeline. Existing approaches to ear detection are susceptible to fail in the presence of typical everyday situations that prevent a crisp imaging of the ears, like partial occlusions, ear accessories, or uncontrolled camera and illumination conditions. Even more, most of the proposed solutions work efficiently only within a previously detected rectangular region of interest, which limits their applicability and lowers the accuracy of the overall detection. In this paper we evaluate the use of Convolutional Neural Networks (CNNs) together with Geometric Morphometrics (GM) for automatic ear detection in the presence of partial occlusions, and a Convex Hull algorithm for the ear area segmentation. A CNN was trained with a set of ear images landmarked by experts using GM to achieve high consistency. After training, the CNN is able to detect ears over profile faces, even in the presence of partial occlusions. We analyze the performance of the proposed ear detection and segmentation method over partially occluded ear images using the CVL Dataset

Multimodal biometric system for ECG, ear and iris recognition based on local descriptors

Combination of multiple information extracted from different biometric modalities in multimodal biometric recognition system aims to solve the different drawbacks encountered in a unimodal biometric system. Fusion of many biometrics has proposed such as face, fingerprint, iris…etc. Recently, electrocardiograms (ECG) have been used as a new biometric technology in unimodal and multimodal biometric recognition system. ECG provides inherent the characteristic of liveness of a person, making it hard to spoof compared to other biometric techniques. Ear biometrics present a rich and stable source of information over an acceptable period of human life. Iris biometrics have been embedded with different biometric modalities such as fingerprint, face and palm print, because of their higher accuracy and reliability. In this paper, a new multimodal biometric system based ECG-ear-iris biometrics at feature level is proposed. Preprocessing techniques including normalization and segmentation are applied to ECG, ear and iris biometrics. Then, Local texture descriptors, namely 1D-LBP (One D-Local Binary Patterns), Shifted-1D-LBP and 1D-MR-LBP (Multi-Resolution) are used to extract the important features from the ECG signal and convert the ear and iris images to a 1D signals. KNN and RBF are used for matching to classify an unknown user into the genuine or impostor. The developed system is validated using the benchmark ID-ECG and USTB1, USTB2 and AMI ear and CASIA v1 iris databases. The experimental results demonstrate that the proposed approach outperforms unimodal biometric system. A Correct Recognition Rate (CRR) of 100% is achieved with an Equal Error Rate (EER) of 0.5%.

Low‐cost biometric recognition system based on NIR palm vein image

Palm vein recognition is motivated by the advantages of high security and liveness detection, but its popularity is prevented by the cost of palm vein capture devices. This study proposes a low-cost and practical palm vein recognition system. First, the authors' system captures near-infrared (NIR) palm vein image with complementary metal-oxide-semiconductor camera in lieu of an NIR charge-coupled device camera. The goal is to reduce the cost of palm vein capture devices greatly. Second, this study adopts thenar area on the palm as the region of interest (ROI) for further palm vein recognition. The goal is to get the rich vessel and avoid the effect of palmprint. Finally, the discriminate palm vein features are extracted based on Haar-wavelet decomposition and partial least squares algorithm on the ROI image. The goal is to increase the recognition accuracy, though the resolution of the image is low. A database with 1500 palm vein images from 250 samples is setup with the capture device. Experiments in the self-built database and a public database show the effectiveness of the scheme.

A multi-instance multi-sample palmprint identification system

<span>The multibiometric recognition system considered more reliable than the unimodal biometric recognition system due to the addition of an extra information that increases the discrimination between the classes. In this paper, a multi-sample multi-instance biometric recognition system is proposed. The aim of the proposed system is to increase the robustness of the identification. the proposed system also addresses the overfitting to the train samples problem of a feature extraction algorithm, named 2-Dimensional Linear Discriminant analysis (2D-LDA). The samples in the proposed method are bootstrapped and the 2D-LDA performed on each group during the offline phase. While in the online phase, the tested class will be transformed into subspaces using different eigenvectors that obtained from different samplings, and the results matched with templates in the corresponding subspace. To evaluate the proposed method, two palmprint databases are used which are IIT Delhi Touchless Palmprint Database and PolyU palmprint database, and different rank-level fusion algorithms are investigated. The results of the proposed method show improvement in the identification rate.</span>

Multimodal Face and Iris Recognition with Adaptive Score Normalization Using Several Comparative Methods

Objectives: To combine several biometric methods used for face and iris simultaneous recognition of an individual in order to enhance the performance. Methods/Analysis: For every methodology, four approaches are used for features extraction: discrete wavelet transform, singular value decomposition, discrete cosine transform and principal component analysis. Then, matching is employed by different distance measurements: City block, Euclidean, Seuclidien, Cosine, Chebychevand Correlation. Findings: The most widely used normalization method such as min-max and a new method using geometric mean is presented. The data fusion is performed at the score level with two methods: simple sum and weighted sum. The obtained comparison results show that PCA (face) and PCA (iris) fusion scenario associated with simple sum rule and the proposed new normalization method (geometric mean) have given the best recognition rate. Application/Improvements: This new normalization method helps considerably to enhance other methods in a multimodal biometric recognition system. Keywords: Distances, Face, Fusion, Geometric Mean, Iris, Multimodal Biometrics, Recognition Rate

Visible-Light Camera Sensor-Based Presentation Attack Detection for Face Recognition by Combining Spatial and Temporal Information.

Face-based biometric recognition systems that can recognize human faces are widely employed in places such as airports, immigration offices, and companies, and applications such as mobile phones. However, the security of this recognition method can be compromised by attackers (unauthorized persons), who might bypass the recognition system using artificial facial images. In addition, most previous studies on face presentation attack detection have only utilized spatial information. To address this problem, we propose a visible-light camera sensor-based presentation attack detection that is based on both spatial and temporal information, using the deep features extracted by a stacked convolutional neural network (CNN)-recurrent neural network (RNN) along with handcrafted features. Through experiments using two public datasets, we demonstrate that the temporal information is sufficient for detecting attacks using face images. In addition, it is established that the handcrafted image features efficiently enhance the detection performance of deep features, and the proposed method outperforms previous methods.

Biometric human recognition system based on ECG

The ECG (electrocardiogram) is an emerging technology for biometric human identification. In this paper, the performance of an ECG biometric recognition system is evaluated. Signal processing techniques are utilized to extract the ECG features. In preprocessing stage, digital filters eliminate the noises and hence improve the signal to noise ratio. The process of ventricular complex (QRS Complex) detection depends on Pan and Tompkins approach that achieves an efficient QRS detection, and hence enhancing the feature extraction process. The main classifiers applied to the extracted features are Neural Network (NN), Fuzzy Logic (FL), Nearest Mean Classifier (NMC), Linear Discriminant Analysis (LDA), and Euclidean Distance (ED) are utilized to classify QRS fragments. ECG of an unknown subject is acquired; the classifiers are applied to wavelet coefficient features set between the unknown subject and all enrolled subjects. The Performance of the different approaches is evaluated by utilizing Sensitivity, Specificity, and efficiency, EER (Equal Error Rate) and ROC (Receiver Operating Characteristic) curve. The experiments are conducted on 112 individuals MIT-BIH database and the accuracy is up to 98.99%.

A Generic Template Update Framework: The Solution for Intra-Class Variations in Biometric Systems

It is already a consensus that intra-class variations will decline the performance of biometric systems. Many studies have explained how intra-class variations affect the biometric systems, while few approaches have proposed the effective solutions of template update. Since template update is a crucial procedure in biometric recognition systems, the problem is challenging because the newly selected templates must be representative of a large amount of intra-class variations such as posture changes and lighting conditions. To this end, existing techniques proposed to perform template update by periodically selecting new representative templates. However, all of them are designed for specific biometric traits rather a generic framework, and they are either ineffective because selected templates are less representative or prone to selection errors due to the presence of outliers. In this paper, we propose a novel generic template update framework. We use pass tables to accumulate information for outlier removal and representative templates selection, and further, propose a novel criterion to select the optimal template set according to current templates and similarity threshold. To confirm the effectiveness of our method, we carry out several experiments on synthetic and real datasets from different biometric traits. The results show that the proposed method is more robust than existing ones, and at the same time, achieves a higher accuracy according to the specified performance indicator. It also demonstrated the superiority of our method to random selection for different biometric traits.

An accurate hand-based multimodal biometric recognition system with optimised sum rule for higher security applications

This paper presents a multimodal biometric recognition system using palm print, finger geometry and dorsal palm vein modalities. A specific image acquisition system is designed, fabricated and database of 150 users is created. DWT technique for features extraction is used for palm print and dorsal palm vein modalities. Performance analysis for individual modality is done using receiver operating characteristics and accuracies of 98.775%, 98.45% and 97.60% are obtained respectively for PP, FG and DPV modalities. Further the multimodal system is proposed along with a novel basis for optimally choosing the weights. The score level fusion is done using these optimised weights. Testing, validation and benchmarking of the algorithms are done using our own database, as well as the standard database available on the net. The proposed multimodal system gives enhanced accuracy of 99.80% with very low FAR level of 0.0001.

Implementation of a Multimodal Biometrics Recognition System with Combined Palm Print and Iris Features

Implementation of a Multimodal Biometrics Recognition System with Combined Palm Print and Iris Features

MobileNet Convolutional Neural Networks and Support Vector Machines for Palmprint Recognition

Due to the ease of handling with low resolution images, low cost hardware and high recognition accuracy, palmprint recognition has been attracting in the recent years. Many different features extracted of the palmprint image have been employed to perform the recognition tasks. Most of the recognition efforts consequently has been put on the designing and obtaining a relevant set of effective hand-crafted features which is considered to be the drawback of the traditional image based biometric recognition systems. To overcome the aforementioned problem, in this paper we explore the applicability of MobileNet V2 deep convolutional neural networks on palmprint recognition by fine-tuning a pretrained MobileNet neural networks. We also explore the performance of dropout support vector machines (SVM) by training them on the deep features of the similar pretrained networks. The experiments are carried out using datasets provided by Hong Kong Polytechnic University of Science and Technology. The dataset consists of 6000 grayscale images of 128x128 pixels from 500 different palms. It is demonstrated that the proposed schemes exhibit state-of-the-art performance on the datasets. The second scheme, MobileNet V2 based features with SVM classifier, is able to achieve best average testing and validation accuracy rate of 100% outperforming the best previous reported results.

A Framework for Iris Partial Recognition based on Legendre Wavelet Filter

An increasing need for biometrics recognition system has grown substantially to address the issues of recognition and identification especially in highly dense areas such as airport, train stations and for financial transaction. Evidences of these can be seen in some airports and also the implementation of these technologies in our mobile phones. Among the most popular biometric technologies include facial, fingerprints and iris recognition. The iris recognition is considered by many researchers to be the most accurate and reliable form of biometric recognition, because iris can neither be surgically operated with a chance of losing slight nor change due to ageing. However, presently most iris recognition system available can only recognize iris image with frontal-looking and high-quality images. Angular image and partially capture image cannot be authenticated with existing method of iris recognition. This research investigates the possibility of developing a framework for recognition partially captured iris image. The research also adopts the Legendre wavelet filter for the iris feature extraction. Selected iris images from CASIA, UBIRIS and MMU database were used to test the accuracy of the introduced framework. A threshold for the minimum iris image required was established.

Finger Vein Recognition using Straight Line Approximation based on Ensemble Learning

Human identity recognition and protection of information security are current global concerns in this age of increasing information growth. Biometrics approach of defining identity is considered as one of the highly potential approaches due to its internal feature that is difficult to be artificially recreated, stolen and/or forgotten. The new recognition system based on finger vein is a unique method depending on physiological traits and parameters of the vein patterns for the human. Published works on finger vein identification have hitherto ignored the power of aggregating different types of features and classifiers in improving the performance of the biometric recognition system. In this paper, we developed a novel feature approach named as straight line approximator (SLA) for extending the feature space of vein pattern using a public data set SDUMLA-HMT comprising about 3,816 images of finger vein for 160 persons. Furthermore, we applied a set of extreme learning machine (ELM) and support vector machine (SVM) classifier in different kernels. Then, we used the combination rules to improve the performance of the system. The experiment result of the proposed method achieved an accuracy of 87% using (DS and GWAR) rules at rank 1, while the accuracy of DS rule 93% and GWAR rule 92% at rank 5.

Exploiting superior CNN-based iris segmentation for better recognition accuracy

CNN-based iris segmentations have been proven to be superior to traditional iris segmentation techniques in terms of segmentation error metrics. To properly utilize them in a traditional biometric recognition systems requires a parameterization of the iris, based on the generated segmentation, to obtain the normalised iris texture typically used for feature extraction. This is an unsolved problem. We will introduce a method to parameterize CNN based segmentation, bridging the gap between CNN based segmentation and the rubbersheet-transform. The parameterization enables the CNN segmentation as full segmentation step in any regular iris biometric system, or alternatively the segmentation can be utilized as a noise mask for other segmentation methods. Both of these options will be evaluated.

Utilizing Transfer Learning and Homomorphic Encryption in a Privacy Preserving and Secure Biometric Recognition System

Biometric verification systems have become prevalent in the modern world with the wide usage of smartphones. These systems heavily rely on storing the sensitive biometric data on the cloud. Due to the fact that biometric data like fingerprint and iris cannot be changed, storing them on the cloud creates vulnerability and can potentially have catastrophic consequences if these data are leaked. In the recent years, in order to preserve the privacy of the users, homomorphic encryption has been used to enable computation on the encrypted data and to eliminate the need for decryption. This work presents DeepZeroID: a privacy-preserving cloud-based and multiple-party biometric verification system that uses homomorphic encryption. Via transfer learning, training on sensitive biometric data is eliminated and one pre-trained deep neural network is used as feature extractor. By developing an exhaustive search algorithm, this feature extractor is applied on the tasks of biometric verification and liveness detection. By eliminating the need for training on and decrypting the sensitive biometric data, this system preserves privacy, requires zero knowledge of the sensitive data distribution, and is highly scalable. Our experimental results show that DeepZeroID can deliver 95.47% F1 score in the verification of combined iris and fingerprint feature vectors with zero true positives and with a 100% accuracy in liveness detection.

Finger kunckcle patterns based person recognition via bank of multi-scale binarized statistical texture features

This paper proposes a novel finger knuckle patterns (FKP) based biometric recognition system that utilizes multi-scale bank of binarized statistical image features (B-BSIF) due to their improved expressive power. The proposed system learns a set of convolution filters to form different BSIF feature representations. Later, the learnt filters are applied on each FKP traits to determine the top performing BSIF features and respective filters are used to create a bank of features named B-BSIF. In particular, the presented framework, in the first step, extracts the region of interest (ROI) from FKP images. In the second step, the B-BSIF coding method is applied on ROIs to obtain enhanced multi-scale BSIF features characterized by top performing convolution filters. The extracted feature histograms are concatenated in the third step to produce a large feature vector. Then, a dimensionality reduction procedure, based on principal component analysis and linear discriminant analysis techniques (PCA + LDA), is carried out to attain compact feature representation. Finally, nearest neighbor classifier based on the cosine Mahalanobis distance is used to ascertain the identity of the person. Experiments with the publicly available PolyU FKP dataset show that the presented framework outperforms previously-proposed methods and is also able to attain very high accuracy both in identification and verification modes.

Social Behavioral Information Fusion in Multimodal Biometrics

The goal of a biometric recognition system is to make a human-like decisions on individual's identity by recognizing their physiological and/or behavioral traits. Nevertheless, the decision-making process by either a human or a biometric recognition system can be highly complicated due to low quality of data or an uncertain environment. Human brain has an advantage over computer system due to its ability to perform a massive parallel processing of auxiliary information, such as visual cues, cognitive and social interactions, contextual, and spatio-temporal data. Similarly to a human brain, social behavioral cues can aid the reliable decision-making of an automated biometric system. In this paper, a novel person recognition approach is presented, that relies on the knowledge of individuals' social behavior to enhance the performance of a traditional biometric system. The social behavioral information of individuals' has been mined from an online social network and fused with traditional face and ear biometrics. Experimental results on individual's and semi-real databases demonstrate significant performance gain in the proposed method over traditional biometric system.

A comprehensive overview of feature representation for biometric recognition

The performance of any biometric recognition system heavily dependents on finding a good and suitable feature representation space where observations from different classes are well separated. Unfortunately, finding this proper representation is a challenging problem which has taken a huge interest in machine learning and computer vision communities. In the this paper we present a comprehensive overview of the different existing feature representation techniques. This is carried out by introducing simple and clear taxonomies as well as effective explanation of the prominent techniques. This is intended to guide the neophyte and provide researchers with state-of-the-art approaches in order to help advance the research topic in biometrics.

Face Recognition Using Location Averaging and Intensity’s Position Estimation Techniques for Human Authentication

Face recognition is an effective tool in the biometric human recognition system. In this competitive world, several techniques and systems are emerging to satisfy the needs of the face recognition system’s performance. To obtain the high-performance ratio novel techniques are combined and created a new face recognition system. Spatial domain techniques like Gray averaging technique, Location averaging technique and Intensity’s position estimation technique are united with frequency domain technique like Discrete Cosine Transform. Intensity’s position estimation is a novel feature extraction and classification technique proposed in this work. Three standard face databases are tested using this system. Accuracy and runtime are major parameters used to validate the obtained results. The maximum accuracy rate of about 86% is obtained.