Biometric Methods Research Articles

Individual Identification in Facial Appearance Biometrics Based on Macroscopical Comparison.

Individual identification is one of the research hotspots in the practice of forensic science, and the judgment is usually built on the comparison of the unique biological characteristics of the individual, such as fingerprints, iris and DNA. With the dramatic increase in the number of cases related to video image investigations, there is an increasing need for the technology to identify individuals based on the macroscopic comparison of facial appearance biometrics. At present, with the introduction of computer three-dimensional (3D) modeling and 3D superimposition comparison technology, considerable progress has been made in individual identification methods based on macroscopic comparison of facial appearance biometrics. This paper reviews individual facial appearance biometric methods based on macroscopical comparison, comprehensively analyzes the advantages and limitations of different methods, and puts forward recommendations and prospects for subsequent research.

A Two-Stage Siamese Network Model for Offline Handwritten Signature Verification

Offline handwritten signature verification is one of the most prevalent and prominent biometric methods in many application fields. Siamese neural network, which can extract and compare the writers’ style features, proves to be efficient in verifying the offline signature. However, the traditional Siamese neural network fails to represent the writers’ writing style fully and suffers from low performance when the distribution of positive and negative handwritten signature samples is unbalanced. To address this issue, this study proposes a two-stage Siamese neural network model for accurate offline handwritten signature verification with two main ideas: (a) adopting a two-stage Siamese neural network to verify original and enhanced handwritten signatures simultaneously, and (b) utilizing the Focal Loss to deal with the extreme imbalance between positive and negative offline signatures. Experimental results on four challenging handwritten signature datasets with different languages demonstrate that compared with state-of-the-art models, our proposed model achieves better performance. Furthermore, this study tries to extend the proposed model to the Chinese signature dataset in the real environment, which is a significant attempt in the field of Chinese signature identification.

Liveness control in face recognition with deep learning methods

Today, automatic identification of individuals from biometric features is widely used in identification and authentication, security, and monitoring applications. Since facial recognition is a more user-friendly and comfortable method than other biometric methods, it has grown rapidly in recent years. However, most facial recognition systems are vulnerable to spoofing attacks. Therefore, face liveness detection (FLD) methods are of great importance. On the other hand, unlike traditional methods, deep learning techniques promise to significantly increase the accuracy of facial liveness detection systems and eliminate the difficulties of the real-world implementation of these systems. Therefore, in this paper, the application of some deep learning models to detect face liveness is reviewed and compared with each other.

Human identification based on accelerometer sensors obtained by mobile phone data

In order to achieve secure usage digitally, many different methodologies (i.e., pin code, fingerprint, face recognition) have been employed. In this study, a novel way of user identification, which can be expressed as a biometrical method, has been proposed. The proposed approach was based on the characteristics of mobile phone usage (position changes in carrying, talking, and other actions). To assess and validate the proposed method, a dataset, which consists of millions of data collected from users with the help of accelerometers for several months during their ordinary smartphone usage, was obtained. This large dataset was reduced by randomly taking 3000 samples from each of the 387 devices in the dataset. The arbitrarily selected signals were labeled according to “one against all” (or “one vs. all”) strategies. Extracted features were classified by the k nearest neighbor (kNN) and the randomized neural network (RNN), machine learning methods. It has been seen that behavior-based biometric recognition can be accomplished with mobile phone accelerometer data, with 99.994% success rates for kNN and 99.97% for RNN.

The livestock farming digital transformation: implementation of new and emerging technologies using artificial intelligence.

Livestock welfare assessment helps monitor animal health status to maintain productivity, identify injuries and stress, and avoid deterioration. It has also become an important marketing strategy since it increases consumer pressure for a more humane transformation in animal treatment. Common visual welfare practices by professionals and veterinarians may be subjective and cost-prohibitive, requiring trained personnel. Recent advances in remote sensing, computer vision, and artificial intelligence (AI) have helped developing new and emerging technologies for livestock biometrics to extract key physiological parameters associated with animal welfare. This review discusses the livestock farming digital transformation by describing (i) biometric techniques for health and welfare assessment, (ii) livestock identification for traceability and (iii) machine and deep learning application in livestock to address complex problems. This review also includes a critical assessment of these topics and research done so far, proposing future steps for the deployment of AI models in commercial farms. Most studies focused on model development without applications or deployment for the industry. Furthermore, reported biometric methods, accuracy, and machine learning approaches presented some inconsistencies that hinder validation. Therefore, it is required to develop more efficient, non-contact and reliable methods based on AI to assess livestock health, welfare, and productivity.

PerAE: An Effective Personalized AutoEncoder for ECG-Based Biometric in Augmented Reality System.

With the development of the Augmented and Virtual Reality (AR/VR) technologies, massive biometric data are collected by different organizations. These data have great significance but also worsen the privacy risks. Electro-CardioGram (ECG)-based Identity Recognition (EIR) is a popular Biometric technology. An ECG record is an internal Biology feature of a person and has time continuity. Thus, compared with traditional Biometric methods like face recognition, EIR may be less vulnerable to attack. We propose an Autoencoder-based EIR system, called Personalized AutoEncoder (PerAE). PerAE maintains a small autoencoder model (called Attention-MemAE) for each registered user of a system. The Attention-MemAE enhances the autoencoder by using a memory module and two attention mechanisms. A user's Attention-MemAE classifies the hearbeats of other users as anomalies. An Attention-MemAE can be updated when the distribution of the user's ECG data is changed. By using personalized autoencoder, PerAE can improve the time efficiency and reduce the memory overhead. It improves the adaptability, scalability, and maintainability of EIR systems. Experiment results show that to train an Attention-MemAE with 90 % identification accuracy for a user, we can just take five minutes to collect the user's ECG data (around 500 heartbeat samples).

МЕТОДЫ УСИЛЕНИЯ ПРОЦЕДУРЫ ИДЕНТИФИКАЦИИ ПОЛЬЗОВАТЕЛЕЙ НА ОСНОВЕ ТЕХНОЛОГИИ LIVENESS DETECTION

Biometric identification and access control systems contain methods for recognizing a subject'spersonality based on his unique physiological and behavioral characteristics. The purpose ofthis work is to develop a system for secure interaction (authentication) of participants in gamifiededucational projects, which includes countering security threats that arise when using biometric usercharacteristics. A comparative analysis of the efficiency of recognition of fake biometric samples byliveness detection methods based on the detection of sample substitution using a photo, video on adisplay, a 3D model, and a mask has been performed. During research a method of using the livenessdetection for include to a gamified educational environment system was proposed. A modification ofthe liveness detection method (hybrid method) has been proposed and a biometric identification systemin real time has been designed using the proposed method. A two-stage hybrid biometric identificationmethod has been developed based on the joint use of passive and active software methods fordetecting fake biometric samples. The method is adapted for use with a minimum number of additionaldevices, the only biometric feature scanner is a 2D-camera. The network of types two-layerperceptron, three-layer perceptron and convolutional neural network was tested. The network wastrained on the author's training examples. The position of the announcer when recording trainingexamples: the distance of the face from the camera is 60cm, the recording modes when the head isturned by 0 (look directly into the camera), 30 (the head is slightly turned to the side) and 45 (thehead is turned strongly to the side) degrees. Based on the testing results, the best recognition rateswere found in a convolutional neural network with 3 convolutional layers and 1 fully connected one.Accuracy of recognition of the spoken word is obtained up to 100% when the user's head is turned upto 30° and up to 70% - when the user's head is turned up to 45°. The FAR value of this system was1%, the FRR value was 0% for testing on 1000 samples.

Использование мультикомплекса при выращивании бычков черно-пестрой породы

Abstract. Purpose is to determine the influence of the biologically active additive “Belavit-FORTE” on the formation of meat productivity of black-and-white bulls in the Michurin Collective Farm of the Udmurt Republic where was was carried research and production experience. Methods. The object of the study was black-and-white bulls at the final stage of fattening. Studies to determine the economic efficiency of using the multi-complex “Belavit-FORTE” in the production of beef were carried out on the basis of classical zootechnical, economic and biometric methods. Results. The hematological parameters of the blood of experimental animals were within the physiological norm, but at the age of 16 months, the content of leukocytes in the blood of experimental bulls was higher by 30.7 %, and hemoglobin and red blood cells were lower by 2.36 % and 4.8 %, respectively. Heavy carcasses were obtained from the bulls of the experimental group, the weight of which was on average 4.1 % higher than in the control group. The bulls that received the multicomplex surpassed the control peers in slaughter yield by 0.7 %. Beef obtained from experimental bulls favorably differed in technological properties: the moisture-retaining and moisture-binding abilities of the pulp were higher than the similar control values by 0.5 and 3.2 %, respectively. According to the pH level of the sample of the muscle tissue of the analyzed bulls, it can be identified as a raw material with NOR signs. The scientific novelty. For the first time in the conditions of the Michurin Collective Farm, Vavozhsky District, the influence of the “Belavit-FORTE” preparation in the diets of black-and-white bulls in the final fattening period on the formation of meat productivity and technological qualities of beef was assessed.

Implementation of Smart Election System using IoT

In Indian Democracy, Voting is the essential fundamentals of each citizens. Building a secure balloting system has been a challenge for a due course of time. In this modern scenario, vote casting system has a few troubles with it. One of the most important problems in existing vote casting system EVM (Electronic Voting Machine), is confidentiality of voter, loss of secrecy of ballot, voter anonymity etc. In this paper, we proposed a biometric method which will resolve the problem of the modern-day voting system. Here, we added the concept of getting the fingerprint impact of a voter which is entered as input to the system. Then, compared with the collected information in the database. If the precise pattern suits with the reachable record, then casting a vote is permitted. Then the quick result is on the spot and counting is performed by means of IoT.

Origami dynamics based soft piezoelectric energy harvester for machine learning assisted self-powered gait biometric identification

The biometric method based on self-powered sensing technology can realize identity recognition without an external power supply. Compared with traditional biometric technology, it is more convenient to deploy and more reliable to operate. In this paper, a pedal self-powered gait sensor is developed with energy harvesting technology, which can transform the motion of human walking to biometric information. The gait sensing device combines flexible polyvinylidene fluoride (PVDF) piezoelectric film with kresling origami structure to design a new piezoelectric kresling origami generator, which can achieve high-efficiency and broadband energy harvesting performance. The finite element is introduced to simulate the folding process of the kresling origami, in which stress concentration is observed at the creases. The electromechanical coupling model of piezoelectric kresling origami generator is established to optimize the parameters and achieve higher output power. The correctness of the electromechanical coupling model is verified by dynamic and static experiments. The harvested power and voltage of a single mountain crease can respectively reach 95.65 μw and 17.77 V. Due to the nonlinear properties of kresling origami structure, the half-power bandwidth reaches 41.55 Hz. The harvested power becomes 418.16 μw through connecting six piezoelectric films in series. To test the feasibility of identity recognition, we select three students to walk through the pedal self-powered gait sensor. The features of the voltage signals output by the generator are extracted and input into the neural network for training and testing. The results show that three different students’ gait information recognition accuracy is 100%. Our work provides a new method for realizing secretive and privacy-protected biological information sensing and recognition.

Identification of a Person by Appearance and Biometrics Methods

The article considers the identification of a person by the signs of his external appearance in the aspect of the possibility of using biometrics methods. Attention is drawn to the formation of methods of the biometrics system based on the classification of anthropometric parameters of a person’s face. Retrospectively, the development of methods for classifying human facial features is traced, based on the needs of searching for and distinguishing a person among many other persons. The results of such differentiation are evaluated from the point of view of identifying a specific individual. The thesis is substantiated that it is impossible to replace forensic portrait identification with biometric and neural network search, which is carried out based on human images formed in a variety of conditions. Attention is drawn to the fact that the results of an automated search for a specific person among many other people are carried out in order to recognize him in this environment. Forensic portrait examination allows you to establish an individual-specific identity of a person according to the most diverse representations of a person.

Secure biometric hashing against relation-based attacks via maximizing min-entropy

With its irreversibility, low computational cost, and high storage efficiency, biometric hashing is widely used in privacy-preserving biometric recognition systems, yet its security has been recently challenged due to the emergence of relation-based attacks (RA). To address this issue, we model and analyse the RA, and discover that maximizing the conditional min-entropy of the signs of inter-class distance differences in the original space and hash space can minimize the leakage of the distance relation on the original biometric. Consequently, we develop a Secure Biometric Hashing scheme against Relation-Based Attacks (SBH-RA). SBH-RA maximizes the conditional min-entropy by using the cosine function as a distance mapping function. Meanwhile, it learns hash codes by a classification loss and quantization loss to ensure the accuracy of recognition. Our study demonstrates that SBH-RA not only offers higher security but also yields comparable or even superior recognition performance over existing biometric hashing methods experimentally and theoretically. Given 1024 bits hash codes from SBH-RA, it brings a decrease of 21% in Equal Error Rate on face dataset LFW compared with widely used Biohashing. Besides, even under white-box attacks, the probability of a successful attack is smaller than 1.69×2−346.

Effect of Facial Shape Information Reflected on Learned Features in Face Spoofing Detection

<p>Face recognition is a convenient and non-contact biometric method used widely for secure personal authentication. However, the face is an exposed body part, and face spoofing attacks, which compromise the security of systems that use face recognition for authentication, are frequently reported. Previous face spoofing attack detection studies proposed texture-analysis-based methods using handcrafted features or learned features to prevent spoofing attacks. However, it is unclear whether spoofing attack images reflect the face distortion resulting from failing to reflect the three-dimensional structure of a real face. To resolve this problem, we compared and analyzed the face spoofing attack detection performances of two typical convolutional neural network models, namely ResNet-18 and DenseNet-121. CASIA-FASD, Replay-Attack, and PR-FSAD were used as the training data. The classification performance of the model was evaluated based on four protocols. DenseNet-121 exhibited better performance in most scenarios. DenseNet-121 reflected facial shape information well by uniformly applying the learned features of both the initial and final layers during training. It is expected that this study will support the realization of spoofing technology with enhanced security.</p> <p> </p>

A Research Paper on Biometric based ATM System

Abstract: Biometrics-based authentication is a potential alternative to password-based authentication. Of all biometric methods, face-based identification is one of the most convenient one. In ATM systems, facial images are captured using a high resolution camera. Bank security measures can play an important role in preventing customer attacks. These measures are of paramount importance in addressing the weaknesses of civil lawsuits. Banks must meet the criteria to provide their customers with a secure banking environment. This paper focuses on the increased vulnerability and criminal activity of automated teller machines (ATMs), not the bank themselves. Both customers and bankers. Keywords: Automated Teller Machine (ATM), Camera, Verification, Crime, E-Banking.

Biometric authentication utilizing fuzzy extractor with PSO based security ensuring the data security mechanism as Trio in Cloud

Cloud computing is widely preferred by various organizations due to its numerous advantages such as lower costs, better security, and faster processing times. The most critical data stored in the remote servers are protected by firewalls and encryption, at the same time, the user’s essential data may be accessed from the remote cloud server without their control. This kind of data storage facility introduces various security complications. In order to prevent these issues, we have proposed a method that uses a Biometric authentication method with PSO to provide high-level security. The method combines a pseudo-integer authentication scheme with a secret OTP that can be used to authenticate an individual. A Tri-level security mechanism model is proposed to store three types of data classification namely, No Privacy, Privacy with Trusted Provider and Privacy with Non-PNR. The proposed method provides a uniform security scheme for all the classifications using Adaptive ElGamal with Menezes-Qu-Verstone, that prevents data loss and corruption caused by insiders in the cloud. Further Seed Block is utilized to recover and extract data without loss. It does so by effectively extracting the data from the formatted disks. It is then followed with the decryption process, as if the data are requested by the user. Our framework aims to provide a secure and authenticated environment for accessing data. It features an improved authentication process and reduced complexity.

Voice Biometric Systems for User Identification and Authentication – A Literature Review

Purpose: Biometric trends are used in many systems because of security aspects. The cryptosystem is such an example which uses a biometric. But due to stored biometric data for the authentication, this can be a dangerous issue. Therefore, in comparison to conventional used biometric system, voice biometric system provides an efficient safety, security and unique identity. Among various speech recognition or processing methods, there is one called automated speech conversion methods, which also used to convert the recorded voice into text format. The overall concept of voice reorganization and voice biometric system is based on the acoustic modelling. Therefore, for getting the perfect speech detection, robust acoustic modelling is required. Our analysis describes the advancement and usage of voice biometric system for user identification and authentication. This paper provides a descriptive review of different voice biometric systems, their advancement and applications in different fields. Methodology: The core principles of the research issue have been well discussed in the literature review on speech biometrics. During this process, selected journals from a variety of secondary data sources, such as research papers published in a variety of reputed journals periodicals that are related to the topic are studied in the methodology. Findings/Result: A vocal biometric system is a biological system that captures an individual's voice and assigns it a unique characteristic for authentication purposes. This speech biometric method is primarily used to provide secure, quick, and frictionless access to various electronic devices. In the last three years, rapid technological advancements in neural networks have improved the deployment of speech biometric systems in a variety of industries. The majority of speech biometric system designs are based on the CPU, necessary power, and memory concepts. The advancement of software and hardware interface has been dramatically enhanced and implemented for many applications in the last few years, including smart watches, mobile phones, and car locking systems, where the interface between humans and electronics devices is critical. Banking security, attendance system, file access system, security control, and forensic development system are some of the other commercial applications. Originality: Following the literature study, the findings were utilized to conclude that, despite advances in biometric technology, there is still a significant gap in practical application, particularly for voice biometric systems. When building and developing a voice biometric system, it is necessary to integrate it with an IoT system. Paper Type: Literature Review.

Gait phase recognition of lower limb exoskeleton system based on the integrated network model

Exoskeleton robots have become an emerging technology in medical, industrial and military applications. Human gait phase recognition is the crucial technology for recognizing movement intention of the exoskeleton wearer and controlling the exoskeleton robot. As a new biometric recognition method, gait phase recognition also plays an important role in clinical disease diagnosis, rehabilitation training and other fields. This paper proposes an integrated network model SBLSTM that combines sparse autoencoder (SAE), bidirectional long short-term memory (BiLSTM) and deep neural network (DNN) aiming at gait phase recognition during human movement. The model can accurately identify four phases in the gait cycle, including heel strike (HS), foot flat (FF), heel off (HO) and swing phase (SW). Normalization and feature extraction of collected sensor signals are performed to enhance the accuracy of recognition during the gait identification process. The processed data are input into the SBLSTM model. The introduction of SAE into the model can extract key information from gait characteristics. BiLSTM is used to learn temporal patterns and periodic changes in gait data. DNN is adopted to identify gait phases and output classification results. Different algorithms such as DNN, LSTM and SBLSTM are applied to the gait phase detection of subjects. The experimental results show that the SBLSTM algorithm is effective in gait recognition. The accuracy and F-score are outperformed by other algorithms, which verifies the effectiveness of the SBLSTM in practice.

Face Recognition Based Door Lock System

Today we deal with safety and safety problems in every element. So, we have to deal with these problems by utilizing upgraded innovation. In this job, we are utilizing the Deal with acknowledgment component to catch human pictures and to suit with kept data source pictures. If it suits with the licensed individual after that the system will open the door by an electro-magnetic secure. The require for face acknowledgment system that's quick and precise that constantly enhancing which can spot intruders and limits all unapproved individuals from extremely protected locations and helps in reducing human mistake. Deal with acknowledgment is throughout a one amongst the primary Protected System compared to biometric pattern acknowledgment method which is utilized in a big range of applications. The moment and precision element are considered regarding the primary issue which defines the efficiency of automated deal with acknowledgment in real-time atmospheres. Different services have been suggested utilizing multicore systems. By thinking about today difficulty, this offers the total building develop and suggests an evaluation for a real-time deal with acknowledgment system with Ficherface formula. In this formula, it transforms the picture from shade to greyscale picture and splits into pixels and it'll be assigned throughout a matrix develop and people pictures will be kept in the data source. If a photo is spotted after that microcontroller will send out power to the electric motor chauffeur system after that the electro-magnetic secure will open the door and it'll secure once again when there's no power provide to that system. Lastly, this paper wraps up for the progressed applications accomplished by incorporating installed system designs versus the convention.

Екстер’єрно-конституційні особливості корів-первісток молочних порід

Goal. To study the exterior features of cows of different genotypes obtained by purebred breeding and crossbreeding. Methods. Analysis of experimental research on the application of effective breeding methods, theoretical analysis, formulation of hypotheses, genealogical, biometric and statistical methods, and assessment of productive qualities of animals. Results. It was established that the breeders of Holstein, Montbeliard, and Norwegian red breeds were sufficiently consolidated in terms of exterior features and influenced the formation of the desired characteristics in their offspring. High rates of single milk yield of experimental cows indicated good development of the parenchyma and capacitive system of the udder. The bath-shaped form of the udder had mostly (73.7–76.7%) first-born cows obtained from Holstein breeders. This udder was quite close to the abdomen of the animals, forming only a small corner of the line of the abdomen and the front of the udder. Among the local firstborns of the genus 1/2UCheR1/2M, 63.4% of cows had a bath-shaped udder, and 33.4% — were cup-shaped. The conditional udder volume of first-born cows was almost the same and averaged from 2561.3±93.66 to 2985.4±94.48 cm3, respectively. This made it possible to obtain average daily milk yields of 26.6±1.54-31.0±1.94 kg from first-borns during 2 times milking. With the average degree of reliability (P>0.99) milk yield of cows correlated with measurements of the girth of the chest behind the shoulders (r=+0.210+0.254), oblique length of the torso (r=+0.212+0.241), and width in the macula (r=+0.137+0.185). A high degree of correlation was found between the amount of milk and udder measurements: width (r=+0.514+0.587; P>0.999), girth (r=+0.506+0.587; P>0.999), and volume (r=+0.504+0.650); P>0.999). Conclusions. The use of genetic material from the Norwegian Red and Holstein breeds contributed to the formation of an array of animals with a well-defined milk type. The possibility of first-borns with a rough, massive skeleton and polymastia in the herd should be taken into account when selecting breeders of Montbeliard breeds. There is a close relationship between milk productivity and udder measurements, which indicates the possibility of indirect selection of cows for milking at the beginning (1–2 months) of the first lactation.

A wavelet-based capsule neural network for ECG biometric identification

Electrocardiogram (ECG) signals have received a high level of attention from the biometric research community due to their unique nature for each person, which makes them suitable for developing accurate and reliable human identification systems. Although most existing ECG-based biometric recognition methods have received prominent results, several consecutive heartbeat segments are used in their approaches to achieve high accuracy, which is challenging to apply in biometric systems deployed in real-world applications. This paper proposes a new approach for human identification via ECG, based on a combination of Continuous Wavelet Transform (CWT), Discrete Wavelet Transform (DWT) along with a novel kind of deep learning technique known as Capsule network. The CWT is used to transform a single heartbeat signal into the time–frequency domain, and the DWT is adopted to extract spectral information of 2D frequency-time scalogram images to further improve accuracy. The discrete wavelet coefficients are then used as input to the capsule network promoting the recognition performance due to its high learning capacities. To support real-life practicality of ECG biometric identification system, the effectiveness and efficiency of our approach were evaluated over four databases that include normal and abnormal ECG records: PTB Diagnosis ECG (PTB), MIT-BIH Arrhythmia, MIT-BIH Normal Sinus Rhythm (NSRDB), and the MIT-BIH ST Change (STDB) databases. Experimental results demonstrate that our proposed method was able to achieve high identification accuracies and outperforming other state-of-the-art methods, by achieving an accuracy of 99.5%, 98.1%, 98.2%, and 100% on the PTB, MIT-BIH arrhythmia, STDB, and NSRDB respectively. Furthermore, the approach showed very good generalization ability since the training and test sets were completely different, which demonstrates the feasibility to promote the application of our approach in practice.