Fingerprint Recognition Research Articles

Enhancing Network Access Control using Multi-Modal Biometric Authentication Framework

This study presents an innovative multi-modal biometric authentication framework that integrates Deep Learning (DL) techniques with zero-trust architecture principles for enhanced network access control. The framework employs a three-tier fusion strategy (feature-level, score-level, and decision-level) incorporating facial, fingerprint, and iris recognition modalities. The system architecture implements a sophisticated multi-layered approach utilizing the ResNet-50 based Convolutional Neural Network (CNN) architecture for facial recognition, CNN-based minutiae extraction for fingerprint processing, and 2D Gabor wavelets with DL-based feature extraction for iris analysis. The experimental validation using established datasets, namely Labeled Faces in the Wild (LFW), CelebA, FVC2004, NIST SD14, CASIA Iris V4, and UBIRIS v2, demonstrates exceptional performance with 99.47% authentication accuracy, 0.02% False Acceptance Rate (FAR), and 0.15% False Rejection Rate (FRR). The framework resulted in a 68% reduction in fraudulent access attempts. It achieved a mean authentication time of 235 ms (SD=28 ms), representing a 45% improvement over traditional systems. The resource efficiency analysis showed significant reductions in system overhead: 32% in CPU utilization, 28% in memory consumption, and 45% in network bandwidth requirements. The scalability testing confirmed a linear performance scaling up to 100,000 concurrent authentication requests. The statistical test of significance through t-test confirmed the framework's significant improvements over existing solutions (p-value<0.001). This study establishes an effective framework to address network access control challenges across various sectors, particularly in high-security environments requiring robust authentication mechanisms.

A Novel Deep Learning Framework for Fingerprint Image Enhancement and Accurate Recognition

This study presents a novel hybrid approach to fingerprint recognition, combining frequency domain filtering and deep learning techniques to enhance fingerprint quality and improve recognition accuracy. The proposed method first applies frequency domain enhancement to reduce background noise and clarify essential fingerprint features such as ridges and valleys. Subsequently, a convolutional neural network (CNN) is employed to further refine and correct the binary fingerprint image, addressing any residual misrepresentations. This approach leverages the strengths of both traditional image processing and modern deep learning, resulting in a more accurate and reliable fingerprint recognition system, particularly in noisy or distorted conditions. Experimental results demonstrate the effectiveness of this method in improving fingerprint image quality and recognition performance, making it a valuable solution for biometric security applications. Key Words: Fingerprint Recognition, CNN, Image Processing, Biometric Security.

Review of gait recognition systems: approaches and challenges

Gait recognition (GR) has emerged as a significant biometric identification technique, leveraging an individual's walking pattern for various applications such as surveillance, forensic analysis, and person identification. Despite its non-intrusive nature, GR systems face challenges due to their sensitivity to pose variations, limiting functionality in real-world scenarios where people exhibit diverse walking styles and body orientations. This review paper aims to comprehensively discuss GR systems, focusing on approaches and challenges in designing accurate and robust systems capable of handling bodily variations. GR's prominence spans across domains including surveillance, security, healthcare, and human-computer interaction, positioning it as a versatile biometric modality complementary to the traditional methods like fingerprint and face recognition. The review offers an in-depth analysis of GR systems, detailing silhouette-based, model-based, and deep-learning approaches. Silhouette-based methods capture gait information by analyzing the outline and locomotion of a person’s silhouette, while model-based approaches utilize skeletal models to describe gait patterns. The paper elucidates the challenges and limitations of GR systems, encompassing factors such as walking conditions, clothing, viewpoint, and environmental influences. Additionally, it explores potential future directions in GR research, highlighting the technology’s ongoing evolution and integration into diverse applications. As a valuable resource, this review serves researchers, practitioners, and policymakers by providing insights into the current state of GR systems and avenues for further research and development. It underscores the importance of addressing challenges to enhance GR’s accuracy and robustness, ensuring its continued relevance in biometric identification across various domains.

Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model

Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model

Implement of an Automatic Class Attendance in All System using CNN-based Face Recognition

This era is a combination of modern and new technology. In this combination, many traditional problems are being solved. To solve these problems, the problems have been solved by using new technologies. Attending educational institutions has become an essential part of daily life but this work takes a lot of time, which causes a lot of trouble in the office and in such institutions, and where there are more workers, this problem increases even more and makes the person tired. Manually Biometric Present System is costly requirement for fingerprint recognition through voice and iris where as hardware support and auto present system recognition is done using face this feature is another biometric which can solve everything this time and Date also mentions which represents facial development Face Recognition and Attendance Entry Data Set Training which includes data entry with conversational technician This system can be used for daily attendance recording .It can achieve an average recognition accuracy of around 95%. The system can detect and identify faces of multiple individuals. Likes can also be recorded from the video stream, thereby avoiding human hassles and risks.

Integrating a greener RP-HPLC method and chemical pattern recognition for the identification of Acorus calamus L. and its common adulterants in Indian markets.

This work deals with the development of a greener RP-HPLC method and chemical pattern recognition for the identification of Acorus calamus L. collected from different natural sources and samples traded as 'Vacha' in Indian herbal drug markets. The simultaneous quantification of α- and β-asarone was performed using 0.10% orthophosphoric acid (A) and acetonitrile (B) as solvents in an isocratic manner (35 : 65 v/v) at 0.70 mL min-1. The developed method was found to be greener using various metrics such as AES, GAPI, NEMI, AGREE, and AGREEprep than existing methods. The LC chromatogram obtained in this study showed 11 common peaks, with β-asarone (peak 10) and α-asarone (peak 11) as major markers, which were identified at an Rt of 10.69 ± 0.08 and 10 ± 0.06 minutes, respectively, while their content varied from 0.02 ± 0.001 to 0.71 ± 0.07 and 2.76 ± 0.03 to 39.26 ± 0.14 μg mg-1, respectively. Chemical pattern recognition was applied for quality evaluation of Acorus samples, and hierarchical cluster analysis bifurcated 17 samples into two categories. Principal component analysis integrated with orthogonal partial least squares discriminant analysis showed that the first two principal components efficiently reflect the similarity and differences among populations. Further, the components P7, P10 (β-asarone) and P11 (α-asarone) will serve as 'landmark components' for quality evaluation of natural and marketed samples. Results show that traded Vacha samples share chemical similarity with authentic Acorus, while common adulterants (Costus speciosus, Typha angustifolia, and Alpinia galanga) have entirely different profiles. The integration of HPLC fingerprint and chemical pattern recognition will provide a scientific rationale for the identification of the authentic raw drug and quality control of its adulterants/substitutes.

Mid-infrared supercontinuum laser source with efficient spectral enhancement in 3.7 µm.

A 3-5 µm mid-infrared (MIR) laser has a wide range of applications in biological tissue ablation, remote spectral fingerprint recognition, and directional infrared countermeasures. However, the performance of conventional MIR lasers has long been hindered by restricted wavelength radiation, spectral power efficiency, and system stability. Here, a highly efficient, compact, and stable MIR light source is reported, which is directly generated from a supercontinuum (SC) laser with a long wavelength edge of 4.2 µm in a 7 µm core diameter fluorotellurite fiber. Based on the integration of a high-peak-power pump light source and a small-core-diameter nonlinear medium, efficient nonlinear frequency conversion from traditional near-infrared laser to mid-infrared laser has been achieved, resulting in a significantly enhanced MIR spectrum of 3.7 µm, exceeding the pump peak of 2 µm by more than 12 dB. The pump conversion efficiency is 50.8%, with 94.3% of the spectral power distributed above 2.4 µm and 71.4% above 3 µm. This study has opened up a feasible avenue for obtaining high-efficiency mid-infrared band lasers that meet practical application needs.

A Screenlock Application Using Yoruba Characters for Android Devices

A lock screen is a user interface that appears on a mobile device when it is in a locked state. The purpose of a lock screen is to prevent unauthorized access to the device and its content, such as personal contacts, photos, and other sensitives information. A lock screen typically requires the user to enter a password, pattern or use biometric authentication such as fingerprint recognition to unlock the device. English characters and patterns were often used for screen lock on mobile devices because English language is the most official language in some country most especially in Nigeria and other African countries, However, most illiterate and adult that are not familiar with these languages find it difficult to use. To combat this problem, there is need to develop a user-friendly Yoruba lock-screen app that takes Yorùbá characters as input and also allow users to unlock their android devices with this newly developed application. Moreover, Yorùbá is one of the largest ethnic groups in Nigeria. and also, there is need to promote our local language. The system was built using various programming languages and comparative study of different technique is done as per stages. The system is made flexible and versatile and application has a user-friendly screen. The application has been tested by various student (who uses Android APP) and has provided a successful result

Organic Luminescent Cocrystals Based on Benzotriazole Derivatives: Synthesis, Characterization, Crystal Structure and Fluorescence Behavior.

Organic cocrystals have garnered significant research attention owing to their distinctive properties and promising applications. However, challenges in molecular structure design and control of intermolecular interactions continue to impede further advancements. In this study, two novel cocrystals were successfully formed from a series of synthesized benzotriazole derivatives. The resulting cocrystals exhibit bright green and yellow fluorescence under 365 nm light. To elucidate the microstructure of the obtained cocrystals, systematic characterization techniques such as solid-state fluorescence emission spectroscopy, Single-crystal X-ray diffraction (SCXRD), Power X-ray diffraction (PXRD) and density functional theory (DFT) were performed. These benzotriazole-based cocrystals demonstrate distinct fluorescent responses to alkaline and acidic environments, respectively. Additionally, preliminary tests for fingerprint recognition yielded satisfactory results. These findings suggest that the two cocrystals hold potential applications in acid-alkali sensing, anti-counterfeiting labels, and smart material development, while also providing valuable insights for the design and optimization of solid-state luminescent materials.

Developing a Health Support System to Promote Care for the Elderly.

In light of the demographic shift towards an aging population, there is an increasing prevalence of dementia among the elderly. The negative impact on mental health is preventing individuals from taking proper care of themselves. For individuals requiring hospital care, those receiving home care, or as a precaution for a specific individual, it is advantageous to utilize monitoring equipment to track their biological parameters on an ongoing basis. This equipment can minimize the risk of serious accidents or severe health hazards. The objective of the present research project is to design an armband with an accurate location tracking system. This is of particular importance for individuals with dementia and Alzheimer's disease, who frequently leave their homes and are unable to find their way back. The proposed armband also includes a fingerprint identification system that allows only authorized personnel to use it. Furthermore, in hospitals and healthcare facilities the biometric identification system can be used to trace periodic medical or nursing visits. This process improves the reliability and transparency of healthcare. The test results indicate that the armband functions in accordance with the desired design specifications, with performance evaluation of the main features including fall detection, where a hit rate of 100% was obtained, a fingerprint recognition test demonstrating accuracy from 88% to 100% on high-quality samples, and a GPS tracking test determining position with a difference of between 1.8 and 2.1 m. The proposed solution may be of benefit to healthcare professionals, supported housing providers, elderly people as target users, or their family members.

Enhancing security and accuracy in biometric systems through the fusion of fingerprint and gait recognition technologies

Enhancing security and accuracy in biometric systems through the fusion of fingerprint and gait recognition technologies

Federated Learning Applications in Fingerprint and Finger Vein Recognition

Federated Learning Applications in Fingerprint and Finger Vein Recognition

Facile one-step synthesis of multifunctional carbon dots for rapid fingerprint recognition, information encryption, and Fe3+ ion detection

Facile one-step synthesis of multifunctional carbon dots for rapid fingerprint recognition, information encryption, and Fe3+ ion detection

Authentication of Musical Speech Devices Based on RF Fingerprint Recognition

Authentication of Musical Speech Devices Based on RF Fingerprint Recognition

PDDA-Assisted Synthesis of Magnetic Fluorescent Fe3O4@SiO2-CQD Composites.

Magnetic fluorescent nanomaterials have broad application prospects as taggants in fields such as anticounterfeiting identification, suspicious object tracking, and potential fingerprint recognition in forensic medicine. It is a common method to synthesize magnetic fluorescent composite nanoparticles by preparing a shell on the surface of magnetic particles to load fluorescent materials. In this work, a magnetic fluorescence nanohybrid was synthesized by in situ encapsulation of carbon quantum dots (CQDs) during the preparation of a SiO2 shell on the surface of Fe3O4 nanoparticles. The traditional Stöber method was employed to synthesize the SiO2 shell. Meanwhile, CQDs were introduced into the hydrolysis process of tetraethyl orthosilicate. To address the issue of charge repulsion between the negatively charged hydrolysis intermediate of tetraethyl orthosilicate and the negatively charged CQDs, poly(diallyldimethylammonium chloride) with positive charge was introduced in the synthesis process. The repulsive charges in the reaction system were balanced by poly(diallyldimethylammonium chloride), allowing for the successful encapsulation of CQDs in the SiO2 shell. The structure, morphology, and magnetic and fluorescence properties of the prepared Fe3O4@SiO2-CQDs were characterized by X-ray diffraction, scanning electron microscopy, transmission electron microscopy, a vibrating sample magnetometer, and a fluorescence spectrophotometer. The Fe3O4@SiO2-CQDs exhibited excellent magnetic and fluorescence properties, making them suitable for fluorescence labeling on various substrates and showing great potential in labeling, tracing, and fluorescence sensors.

Development and Implementation of an ESP32 Microcontroller and Monitoring System for Smart Door Lock Using RFID Sensor for E-KTP ID and Fingerprint Based on the Internet of Things

This study aims to improve the effectiveness and efficiency of door security systems by integrating RFID technology, fingerprint recognition, and the Internet of Things (IoT). This system not only enables automatic locking but also provides real-time access control and monitoring through a web-based application. The technology supports high-level security through dual authentication methods, using E-ID cards and fingerprint sensors. Additionally, the implementation of IoT allows users to monitor and manage door access remotely, offering added flexibility and convenience. The system's trial shows high reliability in reading RFID and fingerprint data, with significant accuracy in various conditions. The results of this study contribute to the development of modern security solutions that can be applied in various environments, such as residential homes, offices, and public facilities, with the potential to reduce overall crime rates

Quality Markers of Fufang Shenqi Oral Liquid Based on Integrated Fingerprint Analysis, Chemical Pattern Recognition, and Quantification.

Fufang Shenqi Oral Liquid (FFSQOL) is an important Chinese medicine compound preparation with a wide range of clinical applications, which is mainly used to regulate immune function, improve cardiovascular function, and have anti-inflammatory and antibacterial effects. At present, it is of great importance to establish the quality evaluation method of FFSQOL and to investigate its quality markers (Q-markers). The aim of this study is to establish a quality evaluation method for FFSQOL and screen its Q-markers to provide a scientific basis for its quality control. Fourteen batches of FFSQOL were subjected to high-performance liquid chromatography (HPLC) fingerprint and similarity analysis. The components of FFSQOL were identified, and their content was determined. This was combined with cluster analysis (CA) and principal component analysis (PCA) to determine the Q-markers of FFSQOL. In this study, an HPLC fingerprint was established for 14 batches of FFSQOL, identifying 12 common peaks and six major components. Four components were identified as stable and reproducible: gallic acid (504.94 ~ 1219.04 μg/mL), caffeic acid (452.15 ~ 783.01 μg/mL), 7-O-glucoside (1097.72 ~ 2440.41 μg/mL), and formononetin (176.2 ~ 177.51 μg/mL). Quality evaluation of the 14 batches was conducted using chemical pattern recognition analysis. CA results indicated two distinct groups, and PCA revealed that principal components 1 and 2 were the main factors influencing batch differences. A combination of HPLC fingerprint, content determination results, and chemical pattern recognition analysis was employed to identify Q-markers for FFSQOL. The markers identified were gallic acid, caffeic acid, calycosin 7-O-glucoside, and formononetin. In this study, a quality evaluation method for FFSQOL was established through the implementation of fingerprint, content determination, and chemical pattern recognition analysis, resulting in the identification of four Q-Markers of FFSQOL, which laid the foundation for the formulation of FFSQOL quality standards.

3D Hollow MoS2 Architecture Enabled Highly Sensitive SERS Detection

AbstractSurface‐enhanced Raman spectroscopy (SERS) technology boasts merits of fingerprint recognition, a low detection limit, high sensitivity, and straightforward operation, and holds a significant position in the realm of molecular detection (even at the single‐molecule level). Recently, molybdenum disulfide (MoS2), as a special SERS substrate, has demonstrated various advantages like high molecular compatibility and an anti‐fluorescence background, thus emerging as a promising non‐metal substrate. Nevertheless, so far, how to improve and achieve SERS effects comparable to metal substrates remains a challenge for MoS2 based substrates. Therefore, this work presents and acquires a 3D hollow structured MoS2, which can be achieved through a simple hydrothermal method. Fortunately, the substrate achieves a detection limit of 10−8 M and an enhancement factor of 106 for rhodamine 6G (R6G) molecules, significantly improving the performance of the non‐noble‐metal MoS2 SERS. Theoretical analysis suggests that this should be attributed to the enhanced charge transfer between the substrate and probe molecules brought by the distinct monolayer self‐assembly and oxygen substitution in the 3D MoS2 architecture. The work provides a novel method to enhance the SERS performance of 2D materials, which is readily achievable and is expected to become a key cornerstone for the development of composite substrates.

EVALUATING THE IMPACT OF MULTI FACTOR AUTHENTICATION ON CYBERSECURITY EFFECTIVENESS

In today's digital age, the convenience of online financial transactions is accompanied by rising cybersecurity risks. The shift to digital platforms for conducting daily financial activities has significantly exposed customers to cyber threats. These threats often result from unauthorized access, phishing attacks, and fraud attempts by cybercriminals. Ensuring the security of these transactions is crucial to maintain users' trust and to protect sensitive financial data. This study proposes a comprehensive security framework to strengthen the safety of online financial transactions, using a combination of multi-factor authentication (MFA) and a machine learning-based fraud detection system, termed "E-cyberboost." The framework operates on two primary layers, each designed to address a different aspect of security: identity verification and real-time fraud detection. The first layer involves multi-factor authentication, where users must verify their identity. This layer typically combines something the user knows (like a password) with something they have (such as a one-time password or OTP sent to their mobile device) or something they are (such as fingerprint or facial recognition). MFA significantly reduces unauthorized access by ensuring that even if one authentication factor is compromised, additional verification is required to gain access. The second layer introduces an advanced machine-learning component. Named "E-cyberboost," this machine learning model actively monitors ongoing transactions, detecting patterns that may indicate fraudulent activity. If the system identifies any unusual or suspicious transaction behaviour, it immediately triggers a security response, such as additional user verification or temporarily blocking the transaction. This proactive approach allows the system to address potential fraud in real time, adapting to evolving threats by learning from previous incidents and continuously improving its detection accuracy. By combining the preventive measures of MFA with the responsive capabilities of machine learning, this framework provides robust security against both common and sophisticated cyber threats. The study discusses the methodology, implementation, and effectiveness of this layered approach in reducing the risk of unauthorized transactions and protecting users' financial information. The proposed framework aims to enhance trust in online financial platforms and ensure a safer digital transaction experience for users. Index Terms—Multifactor authentication, machine learning, fraud detection, E-cyberboost

Revolutionizing Fingerprint Detection: Ce3+ Doped SiO2-Zr2O3:Sr2+ Nanocomposites with Enhanced Luminescence and Selectivity.

Even though fingerprints remain one of the most reliable methods of identification, they are often lost during the recovery process. Accurate fingerprint recognition depends on the contrast between the ridges and substrate. On tough surfaces, such as glossy, colorful, and patterned materials, the contrast is harder to establish. Photoluminescent materials play a crucial role in forensic investigations as they enable the development of procedures that enhance image quality and increase the accuracy of findings from security institutions. Due to the strong emission in the red area at 620nm, the use of trivalent Rare Earth ions (RE3+) doped materials in this work is notable. Because of the unique properties and abundance of cerium, luminous materials based on SiO2-Zr2O3: Ce3+, Sr2+ prepared via sol-gel technique present a more practical alternative for use in criminal investigations compared to current photonic materials. The sample was further co-doped with synthetic (Safranin-O and crystal violet) as well as organic (curcumin and lycopene) photoluminescent dyes. The nanocomposites were examined using X-ray diffraction analysis (XRD), energy-dispersive X-ray analysis (EDX), dynamic light scattering (DLS), scanning electron microscopy (SEM), and photoluminescence spectroscopy (PL). In conclusion, this work highlights the qualities critical to obtaining higher-resolution latent fingerprint images for potential forensic applications.