Contactless Biometric System Research Articles

Contactless Biometric Based on Palm Vein Recognition Using Wavelet and Local Line Binary Patterns

To support the roadmap for coexistence with Covid-19, contactless biometrics is needed as an individual identity verification technology in daily activities such as control systems, recording attendance at offices/schools/agencies and access rights to a room. An example of contactless biometrics is palm vein-based biometrics. Because it is contactless, this biometric system does not require direct contact between the user and the sensor device, providing several advantages in terms of comfort during acquisition and is more hygienic. In the palm vein recognition system, the palm vein pattern can be considered as a texture feature. Therefore, this study proposes a contactless biometric system based on palm vein recognition using the Local Line Binary Pattern method to extract texture features of palm vein images resulting from the decomposition of the 2D Wavelet Transformation, so as to produce a small texture descriptor that is compatible with the texture characteristics of thin veins. The proposed texture feature extraction method has been tested using the fuzzy k-NN classification method on 600 palm images with a CRR accuracy of 95.0% with a computation time of 0.057 seconds.

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.

LDA-CNN: Linear Discriminant Analysis Convolution Neural Network for Periocular Recognition in the Wild

Due to the COVID-19 pandemic, the necessity for a contactless biometric system able to recognize masked faces drew attention to the periocular region as a valuable biometric trait. However, periocular recognition remains challenging for deployments in the wild or in unconstrained environments where images are captured under non-ideal conditions with large variations in illumination, occlusion, pose, and resolution. These variations increase within-class variability and between-class similarity, which degrades the discriminative power of the features extracted from the periocular trait. Despite the remarkable success of convolutional neural network (CNN) training, CNN requires a huge volume of data, which is not available for periocular recognition. In addition, the focus is on reducing the loss between the actual class and the predicted class but not on learning the discriminative features. To address these problems, in this paper we used a pre-trained CNN model as a backbone and introduced an effective deep CNN periocular recognition model, called linear discriminant analysis CNN (LDA-CNN), where an LDA layer was incorporated after the last convolution layer of the backbone model. The LDA layer enforced the model to learn features so that the within-class variation was small, and the between-class separation was large. Finally, a new fully connected (FC) layer with softmax activation was added after the LDA layer, and it was fine-tuned in an end-to-end manner. Our proposed model was extensively evaluated using the following four benchmark unconstrained periocular datasets: UFPR, UBIRIS.v2, VISOB, and UBIPr. The experimental results indicated that LDA-CNN outperformed the state-of-the-art methods for periocular recognition in unconstrained environments. To interpret the performance, we visualized the discriminative power of the features extracted from different layers of the LDA-CNN model using the t-distributed Stochastic Neighboring Embedding (t-SNE) visualization technique. Moreover, we conducted cross-condition experiments (cross-light, cross-sensor, cross-eye, cross-pose, and cross-database) that proved the ability of the proposed model to generalize well to different unconstrained conditions.

A Survey of Biometric Authentication Technologies Towards Secure And Robust Systems: A Case Study of Mount Kenya University

In response to the increased demand for more effective authentication methods, the usage of biometric authentication to secure systems against unwanted access has grown. Because of the recent COVID-19 pandemic outbreak, any direct physical contact with the system should be avoided. Furthermore, current authentication systems lack the necessary security features, making them vulnerable to cyber risks such as forgery by unethical employees and unauthorized users. The goal of this paper is to investigate the existing biometric authentication systems and propose the best security models to overcome the weaknesses of existing technologies. The study employed mixed methodology, which was qualitative and quantitative in nature and relied on primary and secondary sources of data. The researcher collected the data from a population of 300 staff of Mount Kenya University with a sample size of 169 respondents. The R2 value on the relationship between the studied dependent and independent variables was R2 = 0.792 showing a good fit of the model since is greater than 50% of the test item used in the case study. Therefore the study recommends that institutions to implement a contactless biometric system to eliminate physical contact and use multimodal system that will help overcome the existing challenges associated with unimodal systems. There are still gaps for future researchers where they need to focus on the various decision algorithms that are best efficient in verifying users before they are authenticated in the system.

Hybrid Feature Extractions and CNN for Enhanced Periocular Identification During Covid-19

The global pandemic of novel coronavirus that started in 2019 has seriously affected daily lives and placed everyone in a panic condition. Widespread coronavirus led to the adoption of social distancing and people avoiding unnecessary physical contact with each other. The present situation advocates the requirement of a contactless biometric system that could be used in future authentication systems which makes fingerprint-based person identification ineffective. Periocular biometric is the solution because it does not require physical contact and is able to identify people wearing face masks. However, the periocular biometric region is a small area, and extraction of the required feature is the point of concern. This paper has proposed adopted multiple features and emphasis on the periocular region. In the proposed approach, combination of local binary pattern (LBP), color histogram and features in frequency domain have been used with deep learning algorithms for classification. Hence, we extract three types of features for the classification of periocular regions for biometric. The LBP represents the textual features of the iris while the color histogram represents the frequencies of pixel values in the RGB channel. In order to extract the frequency domain features, the wavelet transformation is obtained. By learning from these features, a convolutional neural network (CNN) becomes able to discriminate the features and can provide better recognition results. The proposed approach achieved the highest accuracy rates with the lowest false person identification.

A contactless biometric system using multiple hand features

With the advent of modern computing technology, there is increased reliance on biometrics to provide stronger personal authentication. Among the variety of biometric solutions in the market, hand-based system is the oldest, and perhaps the most successful form of biometric technology. This paper describes a contactless hand-based biometric system by using visible and infrared imagery. An acquisition device is developed to capture both color and infrared hand images. We modify an ordinary web camera to capture the hand vein that normally requires specialized infrared sensor. The design is simple and low-cost. No additional installation of special apparatus is required. The device can capture the epidermal and subcutaneous features from the hand simultaneously. In specific, five features namely hand geometry, palm print, palmar knuckle print, palm vein, and finger vein are acquired from the hand for recognition. Rigorous experiments had been performed to testify the robustness of the system.

Fingerprint characteristic extraction by Ridge Orientation: an Approach for a Supervised Contactless Biometric System

Fingerprints are the most widely used human characteristics for the purpose of people identification. However, touchbased fingerprint systems have some drawbacks due to skin elasticity, inconsistent finger placement, contact pressure, small sensing area, environment conditions and sensor noise. In this paper, we present a contactless fingerprint system based on a supervised contactless image acquisition and a ridge minutiae extraction method based on orientation computation. The fingerprint image acquisition method requires only an ordinary camera. The ridge orientation characteristic extraction is based on a double windowing of the ridge ending points and a single windowing of the ridge bifurcation points.

Palmprint and face score level fusion: hardware implementation of a contactless small sample biometric system

Including multiple sources of information in personal identity recognition and verification gives the opportunity to greatly improve performance. We propose a contactless biometric system that combines two modalities: palmprint and face. Hardware implementations are proposed on the Texas Instrument Digital Signal Processor and Xilinx Field-Programmable Gate Array (FPGA) platforms. The algorithmic chain consists of a preprocessing (which includes palm extraction from hand images), Gabor feature extraction, comparison by Hamming distance, and score fusion. Fusion possibilities are discussed and tested first using a bimodal database of 130 subjects that we designed (uB database), and then two common public biometric databases (AR for face and PolyU for palmprint). High performance has been obtained for recognition and verification purpose: a recognition rate of 97.49% with AR-PolyU database and an equal error rate of 1.10% on the uB database using only two training samples per subject have been obtained. Hardware results demonstrate that preprocessing can easily be performed during the acquisition phase, and multimodal biometric recognition can be treated almost instantly (0.4 ms on FPGA). We show the feasibility of a robust and efficient multimodal hardware biometric system that offers several advantages, such as user-friendliness and flexibility.