Fingerprint Recognition Research Articles

Multi-layer Anti-Theft System with an Intruder System

Abstract: People are more concerned about the safety of their valuables like jewelry, money, important documents, etc. which is why safe deposit boxes are the safest place to keep them. The advent of rapidly growing technologies enables users to operate high security systems with electronic identification options. In this work, a design of a multilayer security system is proposed. The safety concern parameters like user password, RF identification, and fingerprint recognition, use of one time password and a motion detection and alert system are in place. An email notification of the motion detection image near the safe may also be received by a user. Our system may be considered as a useful multi layered security anti-theft product.

Machine Learning Based Non Live Finger Print Detection

In recent days, liveness detection of finger print image has become very essential in finger print recognition systems because fake finger prints are used in lieu of real finger prints. Many machine learning(ML) techniques have been widely used for non live finger print image detection because these techniques provide high accurate identification and also cost effective. These techniques also enhance the accuracy of classification of real and spoof finger print images. In this article , literature review is done about machine learning (ML) and its algorithms used for the detection of non live finger print. The main objective of this article is to compare and analyse various ML techniques used for spoof detection. It also provides an overview of performance merits and limitations of ML algorithms used in non live finger print detection . Index Terms— Non live finger print, liveness detection , Machine learning, anti spoofing, spoof detection

Wykorzystywanie systemów sztucznej inteligencji (SI) na zewnętrznych granicach Unii Europejskiej. Możliwości, zagrożenia i wyzwania

The European Union and its Member States are increasingly turning to artificial intelligence (AI) technologies to enhance border controls. This is one of the manifestations of a broader trend of moving towards the so-called smart borders of the Union. This article presents EU initiatives on the development and implementation AI-based digital technologies to improve the control and security of the Union’s external borders. The main directions of the use of AI were analyzed, i.e. in the field of automatic recognition of fingerprints and faces, emotion detection, algorithmic profiling and monitoring, analysis and forecasting of migration. The aim of the article is, on the one hand, to show that the careful implementation and use of AI-based technology for border control can bring many benefits. On the other hand, however, these benefits must be balanced with the significant threat posed by these technologies to the protection of the fundamental rights of the individual.

Low-cost, mass-producible nanostructured surface on flexible substrate with ultra-thin gold or silver film for SERS applications

Surface Enhanced Raman Spectroscopy has emerged as a powerful analytical technique for fingerprint recognition of molecular samples with high sensitivity. The Surface Enhanced Raman Scattering (SERS) effect has been extensively studied for the past few decades. However, only recently the commercialization of portable Raman spectrometers has taken SERS a step closer to real-world applications. Swift and convenient testing of analytes for point-of-care, environmental as well as food quality control and safety applications, is very lucrative. This can be realized with the use of low-cost, mass producible and environmentally friendly SERS active substrates in combination with portable Raman spectrometers. In this study, we demonstrate one approach to accomplish such a SERS-active substrate using nanostructured latex coated paperboard as a base substrate. The nanostructure is accomplished by applying a reverse gravure coater in combination with a short-wavelength infrared (IR) heater. The whole process is easily up-scalable. The SERS functionality is then obtained by physical vapor deposition of an ultra-thin layer of Au or Ag. The surface nanostructure was confirmed by atomic force microscopy, showing an additional nanoscale graininess after the deposition of Au or Ag. The successful metal deposition was confirmed by X-ray photoelectron spectroscopy and deposition homogeneity was also analyzed. To confirm the SERS effect, two model compounds; crystal violet and rhodamine 6G were tested in the concentration range of 1–1000 μM. The results confirmed that the nanostructured, flexible, paper-based substrate can perform as a SERS-active substrate with negligible background noise.

Heart ID: Biometric Identification Using Wearable MIMO RF Heart Sensors

Biometric identification (ID) has become increasingly prevalent in the digital era. Static biometric methods, such as fingerprint and facial recognition are widely accepted, yet generally vulnerable to targeted presentation attacks. Current development has expanded to dynamic biometrics, such as gait and electrocardiogram, that enable continuous authentication and are significantly more resistant to presentation attacks. However, dynamic biometrics often involve cumbersome acquisition which restricts their widespread use. Here, we introduce Heart ID, a novel dynamic biometric system that uses near-field coherent sensing (NCS) with a multiple-in multiple-out (MIMO) radio-frequency (RF) antenna setup to non-invasively acquire detailed recordings of internal cardiac dielectric boundary motion over clothing. NCS couples localized energy to the heart to derive interpersonal structural differences, while MIMO significantly increases the biometric entropy compared to single-point observation. We performed a human study of 20 subjects as well as 2 longitudinal evaluations, and employed an unsupervised feature extraction method to explore the ID performance of this new biometric. We found an ensemble classification approach using features derived from unsupervised learning can achieve accuracy exceeding 99% at a 40-second epoch.

DIGITAL AUTHENTICATION USING FACE RECOGNITION

Security is the main concern in any of the web application or apps. To ensure security, biometricsystem is used for higher secure system. Usually manyof the security based devices uses fingerprint authentication for access. Finger Print recognition based devices have a large demand for security concerns. On March 11, 2020 the World Health Organization has declared the situation with a worldwide pandemic of Corona virus (COVID-19). The World Health Organization characterizes this sickness as a pandemic since all residents of the world are possibly presented to COVID-19 disease. With thefoundation of the worldwide pandemic status, WHO additionally affirmed that COVID-19 was a global crisis. The pattern of digitalization is turning into another business pattern to create and make due amidst an emergency because of this pandemic. However some portals and software system requires the direct contact of fingerprint or entering the password for authentication. Authentication is a significant issue in system control. It renders in the high security of any software system. Due to pandemic most of us are away from the working or educational places where we personally use the fingerprint for the authentication or attendance. Many of the security based devices are fingerprint recognition based but the COVID-19 has left a drawback with this fingerprint based secure systems as the people are not physically available for the authentication. In order to overcome this we can use the contactless biometric system methods like face recognition system. In this paper we give a solution of face recognition for login system to access the information where usually fingerprint isused for authentication.

Artificial Neural Network-Based Fingerprint Classification and Recognition

Artificial Neural Network-Based Fingerprint Classification and Recognition

Novel development of zinc oxide–coated carbon nanoparticles from pineapple leaves using sol gel method for optimal adsorption of Cu2+ and reuse in latent fingerprint application

This study underlines a latest approach of preparing nitrogen carbon nanoparticles fused on zinc oxide nanoparticle nanocomposite (N-CNPs/ZnONP nanocomposite) for the uptake of copper ions (Cu2+) from wastewater using a sol gel method. The metal loaded adsorbent was then applied in the latent fingerprint application. N-CNPs/ZnONP nanocomposite proved to be a good sorbent for the optimal adsorption of Cu2+ at pH 8 and 1.0 g/L dosage. Langmuir isotherm best fitted the process with the maximum adsorption capacity of 285.71 mg/g that was superior to most values reported in other studies for the removal of Cu2+. At 25 °C, the adsorption was spontaneous and endothermic. Furthermore, Cu2+-N-CNPs/ZnONP nanocomposite revealed to be sensitive and selective for latent fingerprint (LFP) identification on a variety of porous surfaces. As a result, it is an excellent identifying chemical for latent fingerprint recognition in forensic science.Graphical

Representation of fingerprint recognition system based on geometric and statistical features of distance and angle of minutiae points

Representation of fingerprint recognition system based on geometric and statistical features of distance and angle of minutiae points

Application of fingerprint image fuzzy edge recognition algorithm in criminal technology

Abstract In the context of the rapid development of science and technology and the modernization of the legal system, criminal activities are becoming more and more intelligent and technological, which also puts forward higher requirements for criminal technology. The current criminal technology equipment is relatively backward, and the technical level is not high enough, resulting in a low utilization rate of trace material evidence extraction, which directly affects the role of criminal technology in the investigation and solving of cases. In recent years, fingerprint recognition algorithms and image edge detection algorithms have been widely used in various fields. This work studied the application of fingerprint image fuzzy edge recognition algorithm in criminal technology, in order to improve the level of criminal technology and the utilization rate of physical evidence extraction. The criminal technology system is upgraded and optimized by combining fingerprint recognition algorithm and image edge detection algorithm. And fuzzy theory is added to ensure the feasibility of the research. The experimental results show that the fuzzy edge recognition algorithm of fingerprint image can improve the level of criminal technology and the utilization rate of material evidence to a certain extent. The utilization rate is increased by 7.04%. The recognition accuracy of the fuzzy recognition method is also 13.2% higher than that of the methods in the literature.

Optical Waveguide Fingerprint Recognition Device with Two‐Stage Dual‐Function Gratings

AbstractIn the under‐screen fingerprint recognition of smart cell phones, the tiny image signals are easily deteriorated by the protective membranes of screens. To solve this issue, an optical waveguide comprising two stage dual‐function gratings is proposed to supply extra lighting. The first stage is formed by two adjacent gratings possessing a cross angle of 120°, which serve as couplers and beam splitters to trap and split the incident light into two paths within the optical waveguide film, respectively. The second stage gratings, possessing a 60° included angle to the first stage, act as beam orientators and expanders by consecutively redirecting a portion of the light beams towards the sensing zone. By covering the waveguide film outside on an organic light emitting diode display screen and setting a camera and a laser under the screen, this slim construction shows high efficiency and large area under‐screen fingerprint recognition with high signal contrast. The design inspires a novel method for efficiently and flexibly controlling photons by arranging a series of gratings with the proper orientations and locations on a chip, which is highly demanded in displays and optical communication.

Enhancing Security and Access Control: A Biometric-Based Campus Area Network (CAN) Design for North Eastern Mindanao University (NEMSU) - Tagbina Campus

In this rapidly changing landscape of modern institutions, biometric technology has become a crucial part of strengthening security, enhancing productivity, and refining the overall campus experience. This study focuses on the implementation of a Campus Area Network (CAN) at the North Eastern Mindanao State University (NEMSU) - Tagbina Campus, with a specific emphasis on leveraging biometric technology for non-teaching and teaching personnel. By employing advanced methods such as fingerprint recognition and facial identification, institutions can ensure precise attendance records in real-time, replacing error-prone traditional methods. The proposed Campus Area Network (CAN) will serve as an integrated structure that establishes connectivity in both geographically separated Local Area Networks (LANs) and Metropolitan Area Networks (MANs) facilitating efficient data transfer and communication among various campus facilities. The primary goal of this study is to not only streamline administrative operations but also to establish a safer and more accountable educational environment, which will benefit both professors and students in the long run

Implementation security system using motorcycle fingerprint identification and notification Telegram

A motorcycle security system using fingerprint recognition and Telegram notification is a solution to solve motorcycle safety problems and reduce motorcycle loss cases by using fingerprint sensors attached to the owner’s motorcycle and Telegram application as a monitor connected to the motorcycle. The microcontroller used is the Wemos D1 mini connected to the Telegram application as a communication line between the user and the motorcycle. The sensor used is the fingerprint sensor. There are differences in data obtained from the fingerprint sensor response results and the response of the Telegram notification system by testing fingerprints that have been registered and that are not registered on the fingerprint sensor with the measurement results using the stopwatch. Measurement differences on the fingerprint sensor have errors with an average time dispute of 0.27 seconds. Measurement differences in Telegram notifications have errors with an average dispute time of 1 second. Hygiene conditions on the fingerprint sensor influence the difference in reading duration. If there is fingerprint oil before it, then the reading tends to be slow. The difference in measurements obtained is small enough that it can be used as a reference.

A multi-evaluating strategy for raw and processed Veratrum nigrum L.: Fingerprinting combined with quantitative analysis based on multivariate chemometric methods

Veratrum nigrum L. (VN) is a well-known herbal medicine and rich in chemical components with multiple pharmacological activities including antihypertensive, anticancer, and antifungal effects. In the current experiment, the quality of VN from different habitats was evaluated based on combinative method of fingerprint, multi-component quantification and chemical pattern recognition. Fifteen batches of VN were collected, and intrinsic chemical composition were identified using ultra-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry, which is a method for analyzing the similarity between samples, coupled with fingerprint of traditional Chinese medicine. The fingerprint similarity model show that 22 common peaks were selected covering 15 batches of and the similarity > 0.963. The total of 22 joint components were tentatively identified by comparison with standard substances or literature. A ultra-high performance liquid chromatography coupled with triple quadrupole mass spectrometry method for simultaneous determination of 8 compounds was established to evaluate the contents of raw and processed Veratrum nigrum L. Multivariate analysis was then applied to compare different batches of herbs based on ultra-high performance liquid chromatography coupled with triple quadrupole mass spectrometry data. All raw and processed samples were classified by partial least squares discriminant analysis based on the 8 analyzed compounds. The findings suggested that veratramine and polydatin with a variable importance for the project (VIP) > 1 were identified as significant constituents, the presence of which can be used to differentiate between raw and processed Veratrum nigrum L. samples. These results indicate that processing methods show important effects on the composition of Veratrum nigrum L..

Classification Of Hand Images by Person, Age and Gender with The Median Robust Extended Local Binary Model

Biometric technologies try to automatically recognize individuals by considering the physiological and behavioral characteristics of individuals. Although the methods used here are very diverse, the personal qualities used also vary. Facial features, finger and vein prints, iris, retina, ear, hand, and finger recognition are only some of the physiological features. It may be preferred to use one or more of these personal features to reduce the margin of error that may arise depending on the security level in the applications used. Biometric recognition systems have varying requirements in security systems applications. Fingerprint and iris recognition work well in applications that require high security levels, while applications that require low security levels are not suitable due to privacy concerns. On the other hand, identification from hand images is more accepted based on the idea that it does not have a very high distinctiveness. But it is sufficient for medium security applications. Apart from these, palm images have many advantages such as reliability, stability, user-friendliness, non-intrusiveness, and flexible use. In this study, it is aimed to identify people, determine their ages, and determine their gender by using both upper surface and inner surface images of right-left hand data of hand shape. For this purpose, images of both the inner surface of the hand (10) and the outer surface of the hand (10) of 100 different people were collected. This was done separately for the right and left hands, and a total of 3955 images were obtained. The features of these images were extracted using the Median Robust Extended Local Binary Model (MRELBP). Images are classified for person, age and gender. The results were 91.4%, 85.9% and 92.6%, respectively.

Electrocardiogram (ECG)-Based User Authentication Using Deep Learning Algorithms.

Personal authentication security is an essential area of research in privacy and cybersecurity. For individual verification, fingerprint and facial recognition have proved particularly useful. However, such technologies have flaws such as fingerprint fabrication and external impediments. Different AI-based technologies have been proposed to overcome forging or impersonating authentication concerns. Electrocardiogram (ECG)-based user authentication has recently attracted considerable curiosity from researchers. The Electrocardiogram is among the most reliable advanced techniques for authentication since, unlike other biometrics, it confirms that the individual is real and alive. This study utilizes a user authentication system based on electrocardiography (ECG) signals using deep learning algorithms. The ECG data are collected from users to create a unique biometric profile for each individual. The proposed methodology utilizes Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) to analyze the ECG data. The CNNs are trained to extract features from the ECG data, while the LSTM networks are used to model the temporal dependencies in the data. The evaluation of the performance of the proposed system is conducted through experiments. It demonstrates that it effectively identifies users based on their ECG data, achieving high accuracy rates. The suggested techniques obtained an overall accuracy of 98.34% for CNN and 99.69% for LSTM using the Physikalisch-Technische Bundesanstalt (PTB) database. Overall, the proposed system offers a secure and convenient method for user authentication using ECG data and deep learning algorithms. The approach has the potential to provide a secure and convenient method for user authentication in various applications.

TPB-DMTP@S-CDs/MnO2 Fluorescence Composite on a Dual-Emission-Capture Sensor Module for Fingerprint Recognition of Organophosphorus Pesticides

Residues of organophosphorus pesticides (OPs) raise considerable concern, while identifying OPs from unknown sources is still a challenge to onsite fluorescence techniques. Herein, a dual-emission-capture sensor module, based on a TPB-DMTP@S-CDs/MnO2 fluorescence composite, is developed for OP fingerprint recognition. TPB-DMTP@S-CDs/MnO2, synthesized by a hydrothermal method and self-assembly, is spectrographically validated as a dual-wavelength fluorescence source. OP-sensitive catalysis (acetylcholinesterase on acetylthiocholine chloride) is designed to regulate fluorescence by decomposing quenchable MnO2. A flexibly fabricated sensor module supports the optimal dual-wavelength fluorescence excitations and captures and converts fluorescence emissions into equivalent photocurrents for feasible access. The most prominent finding is that dual-fluorescence emissions alternatively respond to levels, species, and multi-pH pretreatments of OPs due to varied MnO2 sizes and distributions. Therefore, OP fingerprint recognition is conducted by refining the multidimensional information from fluorescence-triggered photocurrents and preset hydrolyzation using principal component analysis and the rule of maximum covariance. The recommended method provides a wide dynamic range (1 × 10-6 ∼ 12 μg mL-1), a good limit of detection (7.9 × 10-7 μg mL-1), 15-day stability, and good selectivity to guarantee fingerprint recognition. For laboratory and natural samples, this method credibly identifies a single kind of OPs from multiple species at trace levels (10-5 μg mL-1) and performs well in two-component and multicomponent analyses.

Artificial Multisensory Neuron with a Single Transistor for Multimodal Perception through Hybrid Visual and Thermal Sensing.

An artificial multisensory device applicable to in-sensor computing is demonstrated with a single-transistor neuron (1T-neuron) for multimodal perception. It simultaneously receives two sensing signals from visual and thermal stimuli. The 1T-neuron transforms these signals into electrical signals in the form of spiking and then fires them for a spiking neural network at the same time. This feature makes it feasible to realize input neurons for multimodal sensing. Visual and thermal sensing is achieved due to the inherent optical and thermal behaviors of the 1T-neuron. To demonstrate a neuromorphic multimodal sensing system with the artificial multisensory 1T-neuron, fingerprint recognition, widely used for biometric security, is implemented. Owing to the simultaneous sensing of heat as well as light, the proposed fingerprint recognition system composed of multisensory 1T-neurons not only identifies a genuine pattern but also judges whether or not it is forged.

Biometric authentication security enhancement under quantum dot light-emitting diode display via fingerprint imaging and temperature sensing

We improved biometric authentication security using dual recognition based on fingerprint image detection and skin-temperature-change sensing under quantum dot light-emitting diode (QLED) displays. QLEDs are more advantageous than organic light-emitting diodes (OLEDs) in terms of the contrast classification of patterns such as those in fingerprint recognition, owing to their narrow full-width-half-maximum. In this work, scattered, transmitted, and reflected light was captured from the top of the QLED, improving the digital luminance by 25%, as compared with that of OLEDs, because the electroluminescence spectra of the QLED were sustained, whereas those of the OLED were distorted by the generated noise peaks. A QLED with eight apertures sized up to tens of micrometers, mimicking the actual wiring structure of commercialized smartphones, was implemented to detect human fingerprints. The QLED using reduced graphene oxide as the temperature sensor detected temperature changes instantaneously upon finger touch, showing a 2% temperature response based on the human body temperature; however, the temperature change was less than 0.1% for spoof fingerprints printed on paper. Thus, this study successfully enhanced biometric authentication security, through fingerprint recognition based on image sensing using an optical system with micrometer-sized apertures and skin-temperature detection under QLED displays.

Crack-inducing Strain Sensor Array using Inkjet-Printed Silver Thin Film for Underplate and Off-centered Force Sensing Applications.

The change in resistance upon bending in metal films as thick as 1 mm used for underpanel force touch applications is limited by the low sensitivity, thus requiring high-performance readout circuitry. In this paper, we report inkjet-printed silver thin films having crack-inducing underlayers, which further increases the sensitivity of their resistance changes under deformation. This allows for detecting weak vertical forces even through the plates (force-receiving layer), such as 0.4 or 1.2 mm thick polyethylene terephthalate or 0.4 mm thick glass. The underplate sensors will detect a force level as low as 10 gf, which corresponds to the amount of force required for fingerprint recognition. Furthermore, such highly sensitive strain sensors can potentially solve the inaccuracy issue of wearable devices, which can occur when misplaced sensors detect relatively weak biosignals, such as heart rate and blood pressure. The sensor detects the accurate pulse patterns of the wrist artery even though it is off-centered from the artery by 6 mm or larger. The crack-based strain sensor and its usage as a hidden underplate force sensing device will create various wearable and user-machine interface applications.