Biometric Recognition System Research Articles

Bimodal biometric recognition system using Convolutional Neural Networks and fusion of deep audiovisual feature vectors

In recent years, interest has grown in the use biometric systems for identity authentication tasks in digital services, forensic and security applications. A unimodal system (employing a single biometric trait) with high performance is still vulnerable to falsification attacks such as spoofing. For this reason, research on multimodal biometrics (employing various biometric traits) has increased to reinforce security, increase recognition performance, and make false identity authentication more difficult. In this paper, we propose a bimodal system that combines speech and face modalities by concatenating their feature vectors, these vectors are extracted from two convolutional neural networks (CNN) and used for identity verification. The performance of unimodal CNNs was evaluated individually and compared to the bimodal system of concatenated vectors. A data augmentation scheme is used for both modalities to evaluate different operation conditions. Results were measured in terms of Equal Error Rate (EER).

ECG Biometric Verification Incorporating Different Physiological Conditions

The liveness detection criteria of biological signals have become one of the reasons it has been introduced as an ideal biometric recognition system. Electrocardiogram (ECG) is one of the biological signals that records the rhythms of human’s heart in the form of PQRST waves proves the uniqueness of the ECG itself making it suitable to be applied as biometric mechanisms. Previous research had shown the success of proving ECG as a biometric modality however most experimentations were done in normal conditions. Thus, to improve the current research, this work proposed a robust biometric identification by introducing ECG signals incorporating various physiological conditions. After the data collection of cycling, walking, climbing stairs, and jogging, the signals are pre-processed by using MODWT to remove unwanted noises produced during data collection process. Then, Pan Tompkins algorithm is used to segment the QRS complexes. The segmented signals are overlapped and align with each other to observe its pattern. Next, the QRS waveform is classified by using various class of SVM by considering two factors which are same physiological conditions and different physiological conditions. The subjects are compared between same and different physiological condition to validate the proposed method. The results show that the precision achieved up to 100%. In average, Gaussian SVM gives highest precision when compared to other type of SVM classifiers suggesting that Gaussian SVM is the most appropriate to be applied for person identification. Thus, the proposed method proves that biometric recognition can be performed regardless of different physiological conditions and can be applied in real life scenarios.

Behavioral biometric optical tactile sensor for instantaneous decoupling of dynamic touch signals in real time

Decoupling dynamic touch signals in the optical tactile sensors is highly desired for behavioral tactile applications yet challenging because typical optical sensors mostly measure only static normal force and use imprecise multi-image averaging for dynamic force sensing. Here, we report a highly sensitive upconversion nanocrystals-based behavioral biometric optical tactile sensor that instantaneously and quantitatively decomposes dynamic touch signals into individual components of vertical normal and lateral shear force from a single image in real-time. By mimicking the sensory architecture of human skin, the unique luminescence signal obtained is axisymmetric for static normal forces and non-axisymmetric for dynamic shear forces. Our sensor demonstrates high spatio-temporal screening of small objects and recognizes fingerprints for authentication with high spatial-temporal resolution. Using a dynamic force discrimination machine learning framework, we realized a Braille-to-Speech translation system and a next-generation dynamic biometric recognition system for handwriting.

Bio-Rollup: a new privacy protection solution for biometrics based on two-layer scalability-focused blockchain.

The increased use of artificial intelligence generated content (AIGC) among vast user populations has heightened the risk of private data leaks. Effective auditing and regulation remain challenging, further compounding the risks associated with the leaks involving model parameters and user data. Blockchain technology, renowned for its decentralized consensus mechanism and tamper-resistant properties, is emerging as an ideal tool for documenting, auditing, and analyzing the behaviors of all stakeholders in machine learning as a service (MLaaS). This study centers on biometric recognition systems, addressing pressing privacy and security concerns through innovative endeavors. We conducted experiments to analyze six distinct deep neural networks, leveraging a dataset quality metric grounded in the query output space to quantify the value of the transfer datasets. This analysis revealed the impact of imbalanced datasets on training accuracy, thereby bolstering the system's capacity to detect model data thefts. Furthermore, we designed and implemented a novel Bio-Rollup scheme, seamlessly integrating technologies such as certificate authority, blockchain layer two scaling, and zero-knowledge proofs. This innovative scheme facilitates lightweight auditing through Merkle proofs, enhancing efficiency while minimizing blockchain storage requirements. Compared to the baseline approach, Bio-Rollup restores the integrity of the biometric system and simplifies deployment procedures. It effectively prevents unauthorized use through certificate authorization and zero-knowledge proofs, thus safeguarding user privacy and offering a passive defense against model stealing attacks.

CRISPR-Based Biosensors for Medical Diagnosis: Readout from Detector-Dependence Detection Toward Naked Eye Detection.

The detection of biomarkers (such as DNA, RNA, and protein) plays a vital role in medical diagnosis. The CRISPR-based biosensors utilize the CRISPR/Cas system for biometric recognition of targets and use biosensor strategy to read out biological signals without the employment of professional operations. Consequently, the CRISPR-based biosensors demonstrate great potential for the detection of biomarkers with high sensitivity and specificity. However, the signal readout still relies on specialized detectors, limiting its application in on-site detection for medical diagnosis. In this review, we summarize the principles and advances of the CRISPR-based biosensors with a focus on medical diagnosis. Then, we review the advantages and progress of CRISPR-based naked eye biosensors, which can realize diagnosis without additional detectors for signal readout. Finally, we discuss the challenges and further prospects for the development of CRISPR-based biosensors.

A Comprehensive Study of Object Tracking in Low-Light Environments.

Accurate object tracking in low-light environments is crucial, particularly in surveillance, ethology applications, and biometric recognition systems. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as noise, color imbalance, and low contrast contribute to these challenges. This paper presents a comprehensive study examining the impact of these distortions on automatic object trackers. Additionally, we propose a solution to enhance the tracking performance by integrating denoising and low-light enhancement methods into the transformer-based object tracking system. Experimental results show that the proposed tracker, trained with low-light synthetic datasets, outperforms both the vanilla MixFormer and Siam R-CNN.

Biometric voice recognition system in the context of multiple languages: using traditional means of identification of individuals in Nigeria languages and English language

Biometric voice recognition system in the context of multiple languages: using traditional means of identification of individuals in Nigeria languages and English language

Fingerprint recognition using convolution neural network with inversion and augmented techniques

Fingerprints are considered as one of the most important and prominent feature for an individual identification. Due to their consistency and reliability in biometric feature identification, they are most widely used for biometric recognition systems. In these systems, the relevant feature extraction plays important role in achieving required classification accuracy. In recent time, deep learning techniques are being used for fingerprint recognition with more accuracy and efficient results. Major difficulty which has been reported in previous researches, is the limited size of samples. Therefore, we propose two approaches, inversion and multi augmentation to augment the sample size with newly generated images for each feature map. Besides this, multiple networks are used simultaneously for feature extraction from newly generated images in parallel mode. Deep neural network architectures are used with proposed inversion methods and multi augmentation methods to classify the samples of fingerprints for personnel identification and verification. Pre-trained deep convolutional models like VGG16, VGG19, ResNet50 and InceptionV3 are fine-tuned with new processed fingerprint images for feature extraction and classification. The collective samples of fingerprints have been classified into 10 classes. The simulation results have been obtained with different optimizers and it has been observed that VGG 19 model exhibits the accuracies of 88 % and 93 % with inversion and multi augmentation approaches respectively. Whereas, VGG16 model exhibits 93 % with inversion approach and 97 % with multi augmentation approach. Thus, the proposed approach exhibits the accuracy up to 97 % with VGG16 model which is significantly much higher than that of any other model with the same dataset FVC2000_DB4.

Feature Level Fusion of Fingerprints and IRIS for the Enhancement of Biometric System

Background:: With the growing need for information safety and security rules in every corner of the globe. The biometric innovation has been used widely all over the world in daily life. In this view, the Multimodal-based biometric technique has gained popularity and interest due to its capability to resolve various problems associated with single-model biometric identification systems Methods:: In this research, an advanced multimodal-based biometric recognition system is introduced, which depends on multilayer perceptron (MLP), and it identifies humans using biometric features of Fingerprints and IRIS. To build an efficient model, the popular model called Rest- Net50 was used, the gradient method was used and the hinge technique was used as a loss function. For the technique of fusion, different techniques are used to show the effect of fusion in our model. The recognition rate of introduced systems was assessed by experimenting with various techniques on SDUMLA-HMT datasets based on the multimodal biometric datasets. The recognition rate showed that merging two biometric features in biometric recognition systems gives the best results compared to a single biometric feature. Results:: The results obtained showed the superiority of our model with other existing techniques by obtaining a recognition rate of 99.79% with a feature-based fusion method. Conclusion:: The introduced system used the MLP deep learning technique. The feature level fusion was applied to recognize the user using IRIS and fingerprints. To the best of our belief, this is the first research to incorporate MLP and multimodal-based biometric systems using IRIS and fingerprints.

Iris Recognition based on Statistically Bound Spatial Domain Zero Crossing and Neural Networks

Purpose The iris pattern is an important biological feature of the human body. The recognition of an individual based on an iris pattern is gaining more popularity due to the uniqueness of the pattern among the people. Iris recognition systems have received attention very much due to their rich iris texture which gives robust standards for identifying individuals. Notwithstanding this, there are several challenges in unrestricted recognition environments. Methods This article discusses a highly error-resistant technique to implement a biometric recognition system based on the iris portion of the human eye. All iris recognition algorithms of the current day face a major problem of localization errors and the enormous time involved in this localization process. Spatial domain zero crossing may be the simplest and least complex method for localization. Yet, it has not been used due to its high sensitivity to erroneous edges, as a consequence of which more complex and time-consuming algorithms have taken its place. Appropriate statistical bounds imposed on this process help this method to be the least erroneous and time-consuming. Errors were reduced to 0.022% using this approach on the CASIA v1 & v2 datasets. Time consumption in this stage was the least compared to other algorithms. At the comparison stage, most algorithms use multiple comparisons to account for translation and rotation errors. This is time-consuming and very resource-hungry. Results The current approach discusses a robust method based on a single comparison, which works with a correct recognition of over 99.78% which is clearly demonstrated by tests. Conclusions The technique is to use a neural network trained to recognize special statistical and regional parameters unique to every person’s iris. The algorithm also gives sufficient attention to consider illumination errors, elliptical pupils, excess eyelash errors and bad contrast.

A standard ranking algorithm for robust iris template protection

In iris biometric recognition systems, protecting the storage and transmission of iris templates is crucial, and template protection techniques are pivotal for ensuring their security. A prevalent approach involves using indexing methods as an effective algorithm for iris template protection, leveraging the index or rank of the extracted iris code to generate a secure iris template. Meantime, many privacy threats to biometric data have emerged, necessitating heightened protection measures. Specifically, protecting the privacy of iris data is imperative within the context of iris template protection during recognition processes. As stipulated by the international standard ISO/IEC 30136, effective iris template protection must concurrently meet the criteria of irreversibility, revocability, and unlinkability. Nevertheless, existing indexing methods on iris template protection faced the formidable challenge of simultaneously fulfilling these three privacy requirements while maintaining the efficacy of iris recognition. This paper introduces a standard ranking (standardR) algorithm, named standardR, designed to enhance the security of iris templates by transforming each iris template into an irreversible representation. The experimental results on the benchmarked Casia-Iris-interval dataset, along with two additional iris datasets MMU1 and UBRIS 1, demonstrate the efficacy of the proposed algorithm. The proposed standardR algorithm achieves an equal error rate (EER) of 0.1695% and an area under the curve of 0.93011% with the Casia-Iris-Interval dataset. Furthermore, the algorithm maintains efficient recognition with a reduced iris code length of 1280 bits, a time complexity of O(n log n), and satisfies the biometric template protection (BTP) requirements in irreversibility, unlinkability, and renewability.

Biometric Authentication Based on EMG Hand Gestures Signals Using CNN

Biometric identification systems are increasingly important today compared to traditional recognition/classification systems. Electromyography (EMG) signals and person identification/classification systems are preferred for high-security systems as they include physiological and behavioural movements. This study investigates biometric EMG signals based on convolutional neural networks (CNNs) and personal identification/classification systems. Bioelectric signals were recorded at six different wrist movements from five volunteer participants with a four-channel EMG device. To determine the spectrum characteristics of EMG signals, the frequency subbands of the signals were found using the discrete wavelet transform (DWT), empirical wavelet transform (EWT), and empirical mode decomposition (EMD) methods. In addition, statistical methods are used to improve the effectiveness of the feature vector. The CNN model was used to define or classify people. The performance of the developed system was evaluated using Accuracy, Precision, Sensitivity, F-score parameters. As a result, a classification success of 95.66 % was achieved with the developed EMD-CNN method, 94.10 % with the DWT-CNN method, and 93.33 % with the EWT-CNN method. The artificial intelligence model presented in this study explains the effectiveness of EMG signals in person recognition or classification as a biometric identification system. Furthermore, the developed model shows promise for the development and design of future biometric recognition systems.

Pattern matching for the iris biometric recognition system uses KNN and fuzzy logic classifier techniques

Pattern matching for the iris biometric recognition system uses KNN and fuzzy logic classifier techniques

Enhanced multimodal biometric recognition systems based on deep learning and traditional methods in smart environments.

In the field of data security, biometric security is a significant emerging concern. The multimodal biometrics system with enhanced accuracy and detection rate for smart environments is still a significant challenge. The fusion of an electrocardiogram (ECG) signal with a fingerprint is an effective multimodal recognition system. In this work, unimodal and multimodal biometric systems using Convolutional Neural Network (CNN) are conducted and compared with traditional methods using different levels of fusion of fingerprint and ECG signal. This study is concerned with the evaluation of the effectiveness of proposed parallel and sequential multimodal biometric systems with various feature extraction and classification methods. Additionally, the performance of unimodal biometrics of ECG and fingerprint utilizing deep learning and traditional classification technique is examined. The suggested biometric systems were evaluated utilizing ECG (MIT-BIH) and fingerprint (FVC2004) databases. Additional tests are conducted to examine the suggested models with:1) virtual dataset without augmentation (ODB) and 2) virtual dataset with augmentation (VDB). The findings show that the optimum performance of the parallel multimodal achieved 0.96 Area Under the ROC Curve (AUC) and sequential multimodal achieved 0.99 AUC, in comparison to unimodal biometrics which achieved 0.87 and 0.99 AUCs, for the fingerprint and ECG biometrics, respectively. The overall performance of the proposed multimodal biometrics outperformed unimodal biometrics using CNN. Moreover, the performance of the suggested CNN model for ECG signal and sequential multimodal system based on neural network outperformed other systems. Lastly, the performance of the proposed systems is compared with previously existing works.

Iris-Based Biometric Identification Using a Combination of the Right - Left Iris Statistical Features

A combination between the information extracted for both right iris and left iris could increase the efficacy of the biometric recognition systems. In this paper, we propose a biometric identification method based on density of image patterns extracted from human iris images and the combination and comparison of the right iris and the left iris characteristics. The density of the patters approach for processed images can be a new biometric feature used to implement a biometric recognition system with high performance when a small feature dimension is used. In this way, we can maximize the retention of the effective biometric information. The experiments were conducted on the MMU Iris Database containing 225 images of the left eye and 225 images of the right eye. Two morphological Top-hat and Hit or Miss transforms were implemented to find out the particular pattern of pixels. They allow for the enhancement of detail in images. Then, a statistical feature extraction technique is employed to derive the density of the patterns in morphological transformed images. To assess the density of the patterns differences between the right and left iris data groups, the Pearson’s correlation coefficient (PCC) is computed. We reported very good results with a PCC of 0.6164 (strong and positive correlation) for Top-hat morphological operation whilst the Hit or Miss transform returns a PCC of 0.0127 so there is no relationship between the density of the patterns in the right and left irises.

A multimodal biometric database and case study for face recognition based deep learning

Recently, multimodal biometric systems have garnered a lot of interest for the identification of human identity. The accessibility of the database is one of the contributing elements that impact biometric recognition systems. In their studies, the majority of researchers concentrate on unimodal databases. There was a need to compile a fresh, realistic multimodal biometric database, nonetheless, because there were so few comparable multimodal biometric databases that were publically accessible. This study introduces the MULBv1 multimodal biometric database, which contains homologous biometric traits. The MULBv1 database includes 20 images of each person's face in various poses, facial emotions, and accessories, 20 images of their right hand from various angles, and 20 images of their right iris from various lighting positions. The database contains real multimodal data from 174 people, and all biometrics were accurately collected using the micro camera of the iPhone 14 Pro Max. A face recognition technique is also suggested as a case study using the gathered facial features. In the case study, the deep convolutional neural network (CNN) was used, and the findings were positive. Through several trials, the accuracy was (97.41%).

Biometric identification of dairy cows via real-time facial recognition

Biometrics methods, which currently identify humans, can potentially identify dairy cows. Given that animal movements cannot be easily controlled, identification accuracy and system robustness are challenging when deploying an animal biometrics recognition system on a real farm. Our proposed method performs multiple-cow face detection and face classification from videos by adjusting recent state-of-the-art deep-learning methods. As part of this study, a system was designed and installed at four meters above a feeding zone at the Volcani Institute’s dairy farm. Two datasets were acquired and annotated, one for facial detection and the second for facial classification of 77 cows. We achieved for facial detection a mean average precision (at Intersection over Union of 0.5) of 97.8% using the YOLOv5 algorithm, and facial classification accuracy of 96.3% using a Vision-Transformer model with a unique loss-function borrowed from human facial recognition. Our combined system can process video frames with 10 cows’ faces, localize their faces, and correctly classify their identities in less than 20 ms per frame. Thus, up to 50 frames per second video files can be processed with our system in real-time at a dairy farm. Our method efficiently performs real-time facial detection and recognition on multiple cow faces using deep neural networks, achieving a high precision in real-time operation. These qualities can make the proposed system a valuable tool for an automatic biometric cow recognition on farms.

A Novel Approach Towards Biometric Recognition System Using Voice and Signature

Recently, recognition systems have gained importance due to their vital role in security by identifying users while interacting with electronic devices to ensure reliability. The typical authentication systems based on PINs or passwords have revealed various issues of deceitful access. On the contrary, Biometrics can establish an apparent discrepancy between a genuine individual and a fraudulent imitator. Biometrics may be categorized as a Single Model or Multimodal System. Systems of Multimodal bio-metrics are used in Physical Access, Civil ID, Criminal ID, Network/PC Access, Kiosk/ATM, Retail/POS, Surveillance, e-commerce, and telephony. This paper proposes a novel and robust recognition system that uses voice and signatures as inputs to recognize the users. The proposed method uses (Mel Frequency Cepstral Coefficients) MFCC and (Vector Quantization) VQ as characteristic vectors to perform voice analysis, and Vertical Projection Profile (VPP), Horizontal Projection Profile (HPP), and Discrete Cosine Transform (DCT) features to design an offline signature identification system. In the design, a similarity score is obtained. False acceptance and rejection probabilities are measured based on the highest score for each uni-model system. Finally, both methods are merged to get an equal error rate, which is used to evaluate the effectiveness of the proposed approach. The results indicate that when compared with unimodal biometric systems, the proposed multi-model biometric system produces less EER, making the system more robust and reliable.

Hybrid AI-based Voice Authentication

Biometric authentication systems reveal individuals' physical or behavioral uniqueness and identify them by comparing them with existing records. Today, many biometric recognition systems, such as fingerprint reading, palm reading, and face reading, are being studied and used. The human voice is also among the techniques used for this purpose. Due to this feature, the human voice performs secure transactions and authentication in various fields. Based on these voice features, we used a dataset of 66,569 voice recordings. The voice recordings were revised to include six sentences of at least six words each from 24 different people to get the maximum benefit from the dataset. The voices in the reduced dataset were labeled as sentences belonging to the same person and sentences belonging to different people and converted into matrix form. A biometric recognition study resulted in a correlation score of 0.88. As a result of these processes, the feasibility of a voice biometric recognition system with artificial intelligence has been demonstrated.

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.