Biometric Recognition Techniques Research Articles

Federated learning for biometric recognition: a survey

Recently, deep learning (DL) has achieved great success in biometric recognition. The application of DL has also led to a high demand for biometric data. However, as people attach more importance to privacy protection, biometric data have become increasingly difficult to obtain and access, leading to significant limitations in the development and application of DL-based biometric recognition. Federated learning (FL), a distributed learning technique with privacy protection, provides a potential solution to this problem. Several researchers have attempted to integrate FL into biometric recognition. These studies have shown that the introduction of FL not only solves the conflict between privacy and accessibility of biometric data but also improves the accuracy and generalizability of local recognition systems. Therefore, the combination of FL and biometric recognition techniques has become a new research hotspot. In this survey, we comprehensively review the latest advances regarding the application of FL to biometric recognition, biometric presentation attack detection and the related fields to provide new researchers with a quick and systematic overview of this emerging cross-disciplinary field. This paper also summarizes the future opportunities and challenges of this field. To our knowledge, this is the first survey that systematically organizes and analyses federated biometric recognition and related fields to provide suggestions and references for future research.

Advances in Biometric Recognition Techniques: A Review of Finger and Hand Vein Identification Methods

Advances in Biometric Recognition Techniques: A Review of Finger and Hand Vein Identification Methods

Hybrid Feature Extractor Using Discrete Wavelet Transform and Histogram of Oriented Gradient on Convolutional-Neural-Network-Based Palm Vein Recognition.

Biometric recognition techniques have become more developed recently, especially in security and attendance systems. Biometrics are features attached to the human body that are considered safer and more reliable since they are difficult to imitate or lose. One of the popular biometrics considered in research is palm veins. They are an intrinsic biometric located under the human skin, so they have several advantages when developing verification systems. However, palm vein images obtained based on infrared spectra have several disadvantages, such as nonuniform illumination and low contrast. This study, based on a convolutional neural network (CNN), was conducted on five public datasets from CASIA, Vera, Tongji, PolyU, and PUT, with three parameters: accuracy, AUC, and EER. Our proposed VeinCNN recognition method, called verification scheme with VeinCNN, uses hybrid feature extraction from a discrete wavelet transform (DWT) and histogram of oriented gradient (HOG). It shows promising results in terms of accuracy, AUC, and EER values, especially in the total parameter values. The best result was obtained for the CASIA dataset with 99.85% accuracy, 99.80% AUC, and 0.0083 EER.

An artificial intelligence based multimodal biometric recognition using Fully Convolutional Residual Neural Network

The protection of biometric information is rapidly becoming an increasingly significant challenge in the field of data security. In recent years, there has been a precipitous growth in the number of research endeavours being performed in biometrics. This surge in research endeavours has been driven by a growing interest in the discipline. It is still difficult to solve the problem of developing a multimodal biometric system (MBS) with improved accuracy and recognition rate for use in smart cities. The numerous works have all used MBSs, which has led to a reduction in the security criteria that are required. Because of this, the major focus of this study is centred on the creation of a multimodal biometric recognition system (MBRS) via the utilisation of deep learning Fully Convolutional Residual Neural Network (FCRN) classification. A Gaussian filter is first applied to the images obtained from the ear, face, fingerprint, iris, and palmprint databases. This step is performed at the very beginning of the process. This causes the photos to go through pre-processing, which gets rid of the many kinds of noise that were presented. In addition, the grey level co-occurrence matrix, also known as the GLCM, is used to derive the multimodal properties. Following that, Particle Swarm Optimization (PSO) and Principal Component Analysis (PCA) are utilized so that the total number of features can be reduced to the smallest possible amount. The PSO is utilised so that features can be picked and selects the characteristics from the available set that are the most helpful. Finally, the FCRN classifier is used so that the biometric recognition technique can be carried out by using the training PSO features from the test dataset. In conclusion, the findings of the simulation reveal that the implementation of the suggested MBRS-FCRN led to a reduction in losses and an improvement in accuracy in comparison to previous approaches. The proposed MBRS-FCRN achieved an accuracy of 98.179%, sensitivity of 98.346%, and specificity of 98.186% compared to existing methods.

Hybrid feature extraction and LLTSA-based dimension reduction for vein pattern recognition

ABSTRACT In information and security, the personal identification of individuals becomes much more important. For improving security, several biometric recognition techniques are implemented. However, in finger vein recognition, it faces the critical problem of fake finger vein images, security and less accuracy. To conquer this problem, Hybrid Feature Extraction with Linear Local Tangent Space Alignment-based dimension reduction and Support Vector Machine classifier (HFE–LLTSA–SVM) is proposed. In this hybrid, FE is considered as the combination of histogram of oriented gradients (HOG), grey-level co-occurrence matrix (GLCM), stationary wavelet transform (SWT), and local binary pattern (LBP) for extracting the hybrid feature. LLTSA perform dimension reduction in the outputs of HFE from HOG, GLCM, and LBP. Furthermore, SVM is used for classification which gives authentication based on error-correcting code. Finally, the performance parameters were calculated and the proposed method achieved better accuracy of 99.75%, when compared with existing methods.

Privacy Preserving Ear Recognition System Using Transfer Learning in Industry 4.0

This paper presents an Industry 4.0 compliant ear biometric recognition technique using DenseNet, a well-known convolutional neural network model. Compared to other biometric traits, ear recognition has been a challenge due to the unavailability of a large number of images and, therefore, the improvements due to deep learning application are still unexplored. Additionally ear biometrics has the natural advantage of privacy preservation through excellent feature encoding which is not yet explored. In this article, the performance of DenseNet is initially tested on typically challenging benchmarks such as SVHN, CIFAR and ImageNet, achieving state-of-the-art results and requiring minimal computation time and memory. All the experiments are performed on six popular ear databases namely AMI, AWE, Extended AWE (AWE-X), CVLE, IITD, and WPUT, indicating that the proposed algorithm achieves better performance over state-of-the-art. Due to less trainable parameters and fast processing, this Industry 4.0 compliant proposed recognition method can be widely used over Internet of Biometric Things, ensuring the privacy preservation.

A New Post-Processing Proposal for Improving Biometric Gait Recognition Using Wearable Devices.

In this work, a novel Window Score Fusion post-processing technique for biometric gait recognition is proposed and successfully tested. We show that the use of this technique allows recognition rates to be greatly improved, independently of the configuration for the previous stages of the system. For this, a strict biometric evaluation protocol has been followed, using a biometric database composed of data acquired from 38 subjects by means of a commercial smartwatch in two different sessions. A cross-session test (where training and testing data were acquired in different days) was performed. Following the state of the art, the proposal was tested with different configurations in the acquisition, pre-processing, feature extraction and classification stages, achieving improvements in all of the scenarios; improvements of 100% (0% error) were even reached in some cases. This shows the advantages of including the proposed technique, whatever the system.

Gait Recognition for 2-Second Walks Using Viewpoint Normalization and SlidingWindow Process

Many events, such as robberies, missing people, and other suspicious activities, are often captured by cameras. However, these videos are, more often than not, short and not from an optimal angle. Biometric recognition techniques such as facial or iris recognition are inadequate for situations like this. Gait recognition techniques are more suitable than other types of biometrics in such situations. In this work, we propose a new gait recognition technique using viewpoint normalization and a sliding window process. The proposed technique is designed to handle short walking videos captured from any angle. The proposed technique consists of 3 steps. First, a 2-second walk is preprocessed using the sliding window process. This step allows us to generate more gait data in a form of a set of sliding windows from only a 2-second walk. Then sliding windows are transformed into the optimal viewpoint using <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ViewNet</i> , a proposed neural network designed for finding and transforming sliding windows into the optimal viewpoint angle. Finally, local joint movement information is extracted from sliding windows and used to identify a person using <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">IdenNet</i> , a proposed neural network designed for identifying a person from local joint movements. Four evaluation methods, the top <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> accuracy test, the precision-recall curves, the cumulative matching characteristic curves, and the gallery-size test, are used to assess the proposed technique. The experimental results show that the proposed technique outperforms existing techniques on all four tests. In particular, the proposed technique can provide a small group, not more than 5, of suspects with a chance above 90% that the real person of interest is in the group. Moreover, the proposed technique still maintains high accuracy even when used with a larger pool of people.

FCML-gait: fog computing and machine learning inspired human identity and gender recognition using gait sequences.

Security threats are always there if the human intruders are not identified and recognized well in time in highly security-sensitive environments like the military, airports, parliament houses, and banks. Fog computing and machine learning algorithms on Gait sequences can prove to be better for restricting intruders promptly. Gait recognition provides the ability to observe an individual unobtrusively, without any direct cooperation or interaction from the people, making it very attractive than other biometric recognition techniques. In this paper, a Fog Computing and Machine Learning Inspired Human Identity and Gender Recognition using Gait Sequences (FCML-Gait) are proposed. Internet of things (IoT) devices and video capturing sensors are used to acquire data. Frames are clustered using the affinity propagation (AP) clustering technique into several clusters, and cluster-based averaged gait image(C-AGI) feature is determined for each cluster. For training and testing of datasets, sparse reconstruction-based metric learning (SRML) and Speeded Up Robust Features (SURF) with support vector machine (SVM) are applied on benchmark gait database ADSC-AWD having 80 subjects of 20 different individuals in the Fog Layer to improve the processing. The performance metrics, for instance, accuracy, precision, recall, F-measure, C-time, and R-time have been measured, and a comparative evaluation of the projected method with the existing SRML technique has been provided in which the proposed FCML-Gait outperforms and attains the highest accuracy of 95.49%.

Photoplethysmographic biometrics: A comprehensive survey

• The first literature review on PPG-based biometric recognition approaches. • The paper describes application scenarios and acquisition techniques. • The paper presents a classification of state-of-the-art methods. • The paper summarizes the performance of state-of-the-art methods. • The paper describes open research problems. The wide diffusion of wearable sensors and mobile devices encouraged the study of biometric recognition techniques that require a low level of cooperation from users. Among them, the analysis of cardiac information extracted from plethysmographic (PPG) signals is attracting the research community due to the possibility of performing continuous authentications using low-cost devices that can acquire signals without any action required from the users. Although PPG-based biometric systems are relatively recent technologies, machine learning techniques and deep learning strategies have shown accuracy in heterogeneous application scenarios. This paper presents the first literature review of PPG-based biometric recognition approaches. First, we describe the application contexts suitable for PPG-based biometrics. Second, we analyze the systems in the literature, describe the acquisition sensors, and present a classification of the processing methods. Third, we summarize the available public datasets and the results achieved by recent state-of-the-art approaches. Finally, we analyze the open problems in this research field.

“O poder da voz”

Voice is a feature that individualizes and identifies us. Also, a voice is a biometric data, which means that once a voice has been processed, its owner can be identified. This allows us to state that the voice can be used as a means to authenticate the signature of an electronic contract. Therefore, biometric voice recognition techniques will make it possible to identify the owner of the voice, who will thus be giving his contractual consent. The issue could become more complicated when not only the “voiceprint” is used as a signature, but also the counterpart is a virtual voice assistant. These assistants, designed to both “answer” and “listen”, should contain strong privacy policies regarding the processing of the voices interacting with them. The purpose of this paper is to analyze the consent given both for electronic contracting by voice and for the processing of these voices by virtual assistants.

TBIOM Special Issue on “Best Reviewed Papers From IJCB 2020—Editorial”

Recent years have seen considerable advances in biometric recognition techniques leading to a wide-spread deployment of biometric technology across a number of application domains, ranging from security, border control, and criminal investigations to entertainment, social media, autonomous driving and even health services. To highlight some of these advancements and present the latest research achievements related to biometrics, the 4th IEEE/IAPR International Joint Conference on Biometrics (IJCB) was organized in 2020. IJCB combines two major biometrics research conferences, the IEEE International Conference on Biometrics Theory, Applications and Systems (BTAS) conference, and the International Conference on Biometrics (ICB) and is made possible through a special agreement between the IEEE Biometrics Council and the IAPR TC-4. Because IJCB has (so far) only been organized every three years, it represents a particularly prestigious and selective event, where only the highest-quality research is presented.

Artificial Neural Network Based Amharic Language Speaker Recognition

In this artificial intelligence time, speaker recognition is the most useful biometric recognition technique. Security is a big issue that needs careful attention because of every activities have been becoming automated and internet based. For security purpose, unique features of authorized user are highly needed. Voice is one of the wonderful unique biometric features. So, developing speaker recognition based on scientific research is the most concerned issue. Nowadays, criminal activities are increasing day to day in different clever way. So, every country should have strengthen forensic investigation using such technologies. The study was done by inspiration of contextualizing this concept for our country. In this study, text-independent Amharic language speaker recognition model was developed using Mel-Frequency Cepstral Coefficients to extract features from preprocessed speech signals and Artificial Neural Network to model the feature vector obtained from the Mel-Frequency Cepstral Coefficients and to classify objects while testing. The researcher used 20 sampled speeches of 10 each speaker (total of 200 speech samples) for training and testing separately. By setting the number of hidden neurons to 15, 20, and 25, three different models have been developed and evaluated for accuracy. The fourth-generation high-level programming language and interactive environment MATLAB is used to conduct the overall study implementations. At the end, very promising findings have been obtained. The study achieved better performance than other related researches which used Vector Quantization and Gaussian Mixture Model modelling techniques. Implementable result could obtain for the future by increasing number of speakers and speech samples and including the four Amharic accents.

Deep Learning Algorithms based Voiceprint Recognition System in Noisy Environment

Voiceprint Recognition (VPR) is the mechanism by which a user’s so-called identity is determined using characteristics taken from their voice, where this-technique is one of the world’s most useful and common biometric recognition techniques particularly the fields-relevant to security. These can be used for authentication, monitoring, forensic identification of speakers, and a variety of related activities. In this work, an attempt is applied to create a system that recognizes human speaker identity using Convolutional Neural Network (CNN). Two methods are used in this work which are MFCC-CNN and RW-CNN. The first method is standard method using MFCC, to use the features in the audio, where these features are will be entered into CNN to perform a process. The training CNN will take input as a picture and then the process of training via the proposed CNN is beginning. The second method, RW-CNN, the same steps as the first method, but without going through the MFCC phases where direct entry to CNN. In which, the same CNN structure was used in both methods. In this work, a 96% accuracy gained for both RW-CNN and MFCC-CNN. Both methods are similar in their results, either with or without noise, but the performance is mixed. This system can deep learn a large amount of human voices with high accuracy and minimum processes requirement.

User Authentication System Based on Speech and Cascade Hybrid Facial Feature

With the increasing demand for security in many fastest growing applications, biometric recognition is the most prominent authentication system. User authentication through speech and face recognition is the important biometric technique to enhance the security. This paper proposes a speech and facial feature-based multi-modal biometric recognition technique to improve the authentication of any system. Mel Frequency Cepstral Coefficients (MFCC) is extracted from audio as speech features. In visual recognition, this paper proposes cascade hybrid facial (visual) feature extraction method based on static, dynamic and key-point salient features of the face and it proves that the proposed feature extraction method is more efficient than the existing method. In this proposed method, Viola–Jones algorithm is used to detect static and dynamic features of eye, nose, lip, Scale Invariant Feature Transform (SIFT) algorithm is used to detect some stable key-point features of face. In this paper, a research on the audio-visual integration method using AND logic is also made. Furthermore, all the experiments are carried out using Artificial Neural Network (ANN) and Support Vector Machine (SVM). An accuracy of 94.90% is achieved using proposed feature extraction method. The main objective of this work is to improve the authenticity of any application using multi-modal biometric features. Adding facial features to the speech recognition improve system security because biometric features are unique and combining evidence from two modalities increases the authenticity as well as integrity of the system.

A proposed Iris Recognition Model for Authentication in Mobile Exams

Mobile learning is an extended version of e-learning. The revolution of handheld devices had encouraged design courses to be compatible with different mobiles versions, brands and platforms. Mobile exams need more attention to strengthen mobile learning certificates. A major issue with mobile exam is student authentication and identification before and during exam session. With no presence of proctor, more techniques are available to ensure student identification. In this paper, we proposed a model that uses a traditional username and password in addition to the biometric iris recognition technique to verify student identity before and during mobile exams.

Hybridization for Classification and Identification of Individuals using Multimodal Biometric Systems

Biometric recognition systems use certain human characteristics such as voice, facial features, fingerprint, iris or hand geometry to identify an individual or verify their identity. These systems have been developed individually for each of these biometric modalities until they achieve remarkable levels of performance. Biometrics is a measure of biological characteristics for the identification or authentication of an individual based on some of its characteristics. Although biometric recognition techniques promise to be very effective, At present, we can not guarantee an excellent identification rate based on a single biometric signature with unimodal biometric systems. Thus the error rates of unimodal biometric systems are relatively high due to all these practical problems, which makes them impractical for the use of critical safety applications. To resolve these problems, a solution is used in the same system in several biometric modalities, called a multimodal biometric system (MBS). MBSs combine different modalities in a unique recognition system. The multimodal fusion allows improving the results obtained by a single biometric characteristic and making the system more robust to noise and interference and more resistant to possible attacks. Fusion may be carried out at the level of signals acquired by the different sensors, of the parameters obtained for each modality, of the scores provided by unimodal experts or of the decision taken by said experts. In the case of fusion, the features obtained from the various biometric methods must be homogenized before the process of fusion is accomplished. This article describes the evolution of a multi-modal biometric identification system depends on 3 biometrics-face, iris &amp; fingerprint. Feature extraction is done using the Gabor Wavelet method and classification is accomplished using the Random Forest classifier. This proposed method is applicable in real-life applications to identify biometric for offices, hospitals, and colleges/universities and so on.

Face Recognition Door Unlock System

Face recognition system is widely used for human identification particularly for security functions. The project deals with the look and implementation of secure automatic door unlockby using Raspberry Pi. Web camera for capturing the images from the video frame is operated and controlled by raspberry pi using Open CVPython library to train and store human faces for recognition. In this project we are using Raspberry Pi as face recognition module to capture human images and it will compare with stored data base images. If it matches with authorized user then system allows to supply power to electromagnetic lock to create magnetic field for unlocking the door. The need for facial recognition system that is fast and accurate is continuously increasing which can detect intruders and restricts all unauthorized users from highly secured areas and aids in minimizing human error. Face recognition is one of the most Secured System than the biometric pattern recognition technique which is used in a large spectrum of applications.The time and accuracy factor is considered about the major problem which specifies the performance of automatic face recognition in real time environments. Various solutions have been proposed using multicore systems. By considering present challenge, this provides the complete architectural design and proposes an analysis for a real time face recognition. Thus, the image extracted and allowed to match with the database pictures. If the images are matched, the door unlocks mechanically. the planning of the face recognition system exploitation Raspberry pi will create the smaller, lighter and with lower power consumption, therefore it's a lot of convenient than the PC-based face recognition system. Principle element analysis LBPH (Local Binary Pattern Histogram) algorithmic program is employed for the face recognition and detection method. Then acknowledgement are send through Zigbee module from transmitter to receiver. If image isn't detected in database then it'll ask for manual four digit pin for unlocking the door.The developed theme is affordable, fast, and extremely reliable and provides enough flexibility to suits any environment of various systems. Problem Statement:In theworld of emerging technology, security became an essential component in day to day life. Information theft, lack of security and violation of privacy etc. are the essential components which are needed to be protected. Using smart secure systems for door lock and unlocking became popular nowadays. This is system is being adapted by many countries and first grade countries such as USA, Japan etc., already makes use of this system. This system provides either a facial recognition security feature or a keypad is provided to enter the passcode which unlocks the door. Although, it provides security to the doors, it also has somelimitations and drawbacks: Firstly, if the system mainly uses a facial recognition module, there might be a slight chance that sometimes the face may not be detected and hence the door cannot be unlocked. Secondly, if the system uses a

CNN-based anti-spoofing two-tier multi-factor authentication system

Many hybrid and multimodal biometric recognition techniques have been presented to provide secure and authentic systems, incorporating both soft and hard biometric schemes. This article proposes a new hybrid technique which ensures the authenticity of the user to the system, as well as monitors whether the user has passed the biometric system as a normal or spoofed one. The proposed scheme is two-fold: Tier I integrates fingerprint, palm vein print and face recognition to match with the corresponding databases, and Tier II uses fingerprint, palm vein print and face anti-spoofing convolutional neural networks (CNN) based models to detect spoofing. In first stage, the hash of a fingerprint is compared with the fingerprint database. After a successful match of the fingerprint, it is tested on a CNN-based model of the fingerprint to verify whether it is a spoof or real. A similar process is repeated for the palm and face, and based on collective evidence, the system permits the user to login the system. Experimental results over five benchmark datasets verified the effectiveness of the proposed system in providing efficient and robust verification, overcoming the limitations in normal authentication and spoofing practices.

Fusion of hand-shape and palm-print traits using morphology for bi-modal biometric authentication

This paper presents a bimodal biometric recognition technique fusing hand-shape and palm-print traits of a human hand for personal authentication. In this fusion scheme, a novel feature extraction based on morphology, called broken mirror method, is designed and two-stage recognition is proposed. We utilise the image morphology and concept of Voronoi diagram to slice the image of the front of the whole palm into several strips in which each strip is then decomposed into irregular blocks in accordance with the hand geometry. Furthermore, statistic characteristics of the grey level in each of the blocks are employed as feature values. In the final stage, a coarse recognition followed by a fine recognition will be adopted to recognise the identity. The experimental results show that the proposed biometric fusion system has an encouraging performance on recognition. The false acceptance rate (FAR) and false rejection rate (FRR) are reduced efficiently down to 0.0035% and 5.7692%, respectively. Our approach achieves the EER of about 7% which is better than that of other methods.