Multi-biometric Recognition Research Articles

A Computational Approach for Score-Level Fusion Decision-Making of Multi-biometric Recognition System Using Ant Colony Optimisation

This study presents a novel deep learning approach for improving the performance of a multi-biometric recognition system using Ant Colony Optimisation (ACO) at the score level. The proposed method integrates three biometric characteristics, the face, palm, and iris, into a single recognition input. A deep learning model, convolutional neural networks (CNNs), is employed to extract discriminative features from each attribute. The ACO algorithm optimizes the score-level fusion procedure, in which recognition scores from the combined input are combined to make the final determination. The experimental results show the method's efficacy in selecting the score level fusion method per the input biometric and implementation parameters. The ACO-based score-level fusion improves system performance by leveraging complementary information from multiple biometric characteristics, providing a promising solution for robust and accurate multi-biometric recognition in various applications, including access control and identity verification.

Optimization Techniques for Human Multi-Biometric Recognition System

Researchers are increasingly using multimodal biometrics to strengthen the security of biometric applications. In this study, a strong multimodal human identification model was developed to address the growing problem of spoofing attacks in biometric security systems. Through the use of metaheuristic optimization methods, such as the Genetic Algorithm(GA), Ant Colony Optimization(ACO), and Particle Swarm Optimization (PSO) for feature selection, this unique model incorporates three biometric modalities: face, iris, and fingerprint. Image pre-processing, feature extraction, critical image feature selection, and multibiometric recognition are the four main steps in the workflow of the system. To determine its performance, the model was evaluated on the SDUMLA-HMT dataset, which contains a variety of biometric features from various individuals. The system outperformed existing techniques in the literature with an excellent recognition accuracy of 99.4%. Although this result is encouraging, further research on larger and more varied datasets is necessary to confirm its applicability across many circumstances. This study highlights how multimodal biometrics strengthened by metaheuristic algorithms can considerably increase biometric security against spoofing assaults, thereby opening a promising new direction for future development in the field.

Efficient Clustering-Based electrocardiographic biometric identification

The correct identification of individuals through different biometric traits is becoming increasingly important. Apart from traditional biomarkers (like fingerprints), many alternative measures have been proposed during the last two decades: electrocardiogram (ECG) and electroencephalogram (EEG) signals, iris or facial recognition, conductual traits, etc. Several works have shown that ECG-based recognition is a feasible alternative, either for stand-alone or multi-biometric recognition systems. In this paper, we propose a novel framework for ECG-based biometric identification, consisting of a simple and robust feature extraction approach and a clustering-based feature reduction method, that enables for an efficient and scalable biometric identification. The proposed feature reduction approach is a two phase method: it uses a clustering algorithm to group features according to their similarities first, and then clusters are represented in terms of a prototype vector and associated to the available subjects. On its side, the proposed time-domain feature extraction method is a semi-fiducial procedure, where the well-known Pan–Tompkins algorithm is first used to detect the R wave peaks of the QRS complexes, and then fixed-width time segments are selected for further dimensionality reduction and feature extraction. The resulting combined methods are efficient, robust, scalable and attain excellent results (with up-to 98.6% sensitivity) on all the subjects of the Physikalisch-Technische Bundesanstalt (PTB) database, regardless of their pathological or healthy status. Additionally, we also show how the existing Auto Correlation/Discrete Cosine Transform (AC/DCT)-based non-fiducial feature extraction method can be integrated within our framework, allowing us to attain up to 90.6% sensitivity on the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Since this database is much noisier and has a much lower sampling rate (360 Hz instead of 1000 Hz), we claim that this is a very good result.

Efficient cancellable multi-biometric recognition system based on deep learning and bio-hashing

Efficient cancellable multi-biometric recognition system based on deep learning and bio-hashing

Jointly learning multi-instance hand-based biometric descriptor

Multibiometric recognition has become one of the most important solutions for enhancing overall personal recognition performance due to several inherent limitations of unimodal biometrics, such as nonuniversality and unacceptable reliability. However, most existing multibiometrics fuse completely different biometric traits based on addition schemes, which usually require several sensors and make the final feature sets large. In this paper, we propose a joint multi-instance hand-based biometric feature learning method for biometric recognition. Specifically, we first exploit the important direction data from multi-instance biometric images. Then, we simultaneously learn the discriminative features of multi-instance biometric traits and exploit the collaborative representations of multi-instance biometric features such that the final joint multi-instance feature descriptor is compact. Moreover, the importance weights of different biometric instances can be adaptively learned. Experimental results on the baseline multi-instance finger-knuckle-print and palmprint databases demonstrate the promising effectiveness of the proposed method.

A hybrid fusion model of iris, palm vein and finger vein for multi-biometric recognition system

Biometric system has been widely adopted for human verification or identification, so inherently it requires the characteristics like high security, accuracy and acceptability. However, most of existing unimodal biometric systems provide low-middle security and are vulnerable to attacks. Therefore, multimodal biometric system fuses information from multiple modalities to break these limitations. This paper presents a novel hybrid fusion model for a multimodal biometric system. The hybrid fusion model includes an improved feature fusion algorithm and a novel weighting vote strategy. It captures canonical characteristics with multi-set structure and utilizes score distribution information to help guiding decision-making. The system was examined on databases from CASIA, PolyU and SDU respectively, which provided high precision and strong robustness over previous work. Experimental results showed that the proposed approach achieved an average accuracy of 99.33%, which outperformed other fusion strategies in multimodal biometric systems.

Feature Level Fusion of Face and voice Biometrics systems using Artificial Neural Network for personal recognition

Lately, human recognition and identification has acquired much more attention than it had before, due to the fact that computer science nowadays is offering lots of alternatives to solve this problem, aiming to achieve the best security levels. One way is to fuse different modalities as face, voice, fingerprint and other biometric identifiers. The topics of computer vision and machine learning have recently become the state-of-the-art techniques when it comes to solving problems that involve huge amounts of data. One emerging concept is Artificial Neural networks. In this work, we have used both human face and voice to design a Multibiometric recognition system, the fusion is done at the feature level with three different schemes namely, concatenation of pre-normalized features, merging normalized features and multiplication of features extracted from faces and voices. The classification is performed by the means of an Artificial Neural Network. The system performances are to be assessed and compared with the K-nearest-neighbor classifier as well as recent studies done on the subject. An analysis of the results is carried out on the basis Recognition Rates and Equal Error Rates. Index Terms: Bioinformatiscs, Face, voice, Multibiometric recognition system, fusion at feature level, Artificial Neural Network(ANN).

Cryptographic Algorithm based Feature Level Fusion of Fingerprint and Iris in a Multi-Biometric Recognition System

Biometric encryption is one of the developing exploration area, which is a strategy for merging biometric features with cryptographic keys. Biometric Recognition is based on the anatomical and behavior attributes of the individuals. Multibiometric is the combination of various biometrics like Fingerprint, Iris, and Face, Fingervein etc. Experts are concentrating on the most proficient method to give security to the framework, the template which was produced from the biometric should be ensured. The main objective of this paper is to protect the multi biometric template by creating a protected sketch by deploying bio cryptosystem. Once the biometric template is stolen it turns into a major issue for the security of the framework and furthermore for client protection. In this way, a bio-crypto framework ensures the confidentiality of the information. In this paper bio cryptosystem is proposed to improve the security of multimodal frameworks by producing the biocrypto key from Finger print and iris. Gray level co-occurrence matrix (GLCM) based Haralick features, local binary pattern (LBP), triplet half-band filter bank (THFB) and dynamic features (DF) are extracted from fingerprint and iris. The high dimensionality space of the features are reduced using kernel principal component analysis (KPCA. Finally, the encoding process is matted with biometric key utilizing symmetric RSA (Rivest-Shamir-Adleman) cryptographic algorithm.

Design of Multi-Biometrics for Fake Fingerprint Detection through Body Odor

This work proposes the modernistic multi-biometric recognition system for detecting artificial fingerprints and new biometric recognition system to use it in some real-time scenarios. In the recent studies of multi-biometrics, the usage of fingerprint and body odor recognition system stays untouched. This proposed design of a multi-biometric system includes a body odor recognition system along with a fingerprint recognition system that will improve the results in terms of accuracy. The reason behind proposing this model is to detect artificial fingerprints by differentiating the odor of human skin from other materials that are employed in the preparation of artificial fingerprints. This multi-biometric system can be used in forensic labs to identify criminals and to improve the standards of security in authentication of an individual. This multi-biometric system will completely eradicate the use of fake fingerprints and this proposed work will make a remarkable place in real-time applications and the history of multi-biometric systems.

A Multi Biometric IRIS Recognition System based on a Profound Learning Method

Biometrics is the estimation of natural qualities which are one of a kind to a person for recognizing and confirming the person. The estimations incorporate fingerprints, retinal outputs, iris checks, voice designs, facial qualities, palm prints, and so forth.., Biometric frameworks have been especially effective in distinguishing an obscure individual via looking through a database of attributes and by confirming the case of a person by contrasting his/her trademark with that put away in a database. To expand the heartiness of the framework and to make it more secure, different attributes of a similar individual are utilized. This is alluded to as multimodal biometrics. In this paper we talked about a portion of the multimodal biometric frameworks. Here a bi-modular biometric acknowledgment framework in light of iris, palm-print. Wavelet and curve let change and Gabor-edge channel are utilized to extricate includes in various weighing machine moreover introductions starting iris as well as palm print, finer points taking out in addition to arrangement is utilized in favour of coordinating. diverse combination calculations together with achieve based, positionbased plus choice depend on techniques are utilized to-join the consequences of two constituents. We additionally recommend another rank-based combination calculation Bio Maximum Inverse Rank (BMIR) which is vigorous as for varieties in scores and furthermore awful positioning from a module. IITD iris databases and CASIA datasets for palm print and unique mark are utilized in this investigation. The examinations demonstrate the adequacy of our combination strategy, profound learning, neural systems and our Bi-modular biometric acknowledgment framework in contrast with existing multi-modular acknowledgment frameworks.

A multi-instance multi-sample palmprint identification system

<span>The multibiometric recognition system considered more reliable than the unimodal biometric recognition system due to the addition of an extra information that increases the discrimination between the classes. In this paper, a multi-sample multi-instance biometric recognition system is proposed. The aim of the proposed system is to increase the robustness of the identification. the proposed system also addresses the overfitting to the train samples problem of a feature extraction algorithm, named 2-Dimensional Linear Discriminant analysis (2D-LDA). The samples in the proposed method are bootstrapped and the 2D-LDA performed on each group during the offline phase. While in the online phase, the tested class will be transformed into subspaces using different eigenvectors that obtained from different samplings, and the results matched with templates in the corresponding subspace. To evaluate the proposed method, two palmprint databases are used which are IIT Delhi Touchless Palmprint Database and PolyU palmprint database, and different rank-level fusion algorithms are investigated. The results of the proposed method show improvement in the identification rate.</span>

Multi biometric Template Protection using Hybrid Technique

Recently, multi-biometrics system has been the important identification system for providing authentication mechanism. In this pa-per, the multi-biometric recognition system uses multiple traits (face, iris and fingerprint) for authentication. The features are extracted from the traits and feature level fusion technique is applied to the individual features traits to form a fused feature. Protection of these biometrics features against various attacks points is an important concern for authentication process. One such attack is the modification of stored template, which largely affects the performance of biometric recognition system. This paper addresses this concern, by apply-ing template protection algorithm to the biometric features. An improved hybrid template protection algorithm is proposed to protect the biometric template.The experimental results show that the proposed algorithm works better than the existing algorithms available. The proposed algorithm provides better protection to the template. Further, attacks are performed on the proposed system which provide strong resistant against the attacks.

Multi Modal Biometric Security for Mobile Ad-hoc Networks and Its Applications

Objectives: We have proposed a plan of blending multimodal biometric confirmation and interruption identification to enhance the security model in Mobile Adhoc Networks. Methods/Statistical analysis: Technicalities basically based arrangement of principles is used by the unique mark processor, which offers overhauls in general execution. Face acknowledgment is another most recent progression in biometrics. Iris acknowledgment is additionally utilized as a part of verification procedure. To upgrade upon this idea, Dempster–Shafer idea has been utilized for IDS and sensor combination considering more than one apparatus is utilized at on each event opening. The device goes to a choice regardless of whether man verification (or IDS) is required and which biosensors (or IDS) must be chosen, depending on the security wished. The decisions are made in a completely dispersed way by each confirmation apparatus and IDS. Findings: The multi model biometric verification plans and interruption recognition for MANETs from the demeanor of an armed force situation. Joining consistent verification and interruption discovery might be a powerful strategy to improve the security general execution in high wellbeing MANETs. Application/Improvements: In this proposed plan blast the high well being in armed force utility and likewise utilized as a part of security reason in managing an account area.

Genetic Algorithm and Ensemble Systems for Multi-biometric Cancellable Recognition

Genetic Algorithm and Ensemble Systems for Multi-biometric Cancellable Recognition

Predictive models for multibiometric systems

Recognizing a subject given a set of biometrics is a fundamental pattern recognition problem. This paper builds novel statistical models for multibiometric systems using geometric and multinomial distributions. These models are generic as they are only based on the similarity scores produced by a recognition system. They predict the bounds on the range of indices within which a test subject is likely to be present in a sorted set of similarity scores. These bounds are then used in the multibiometric recognition system to predict a smaller subset of subjects from the database as probable candidates for a given test subject. Experimental results show that the proposed models enhance the recognition rate beyond the underlying matching algorithms for multiple face views, fingerprints, palm prints, irises and their combinations.

Cascaded multimodal biometric recognition framework

A practically viable multi-biometric recognition system should not only be stable, robust and accurate but should also adhere to real-time processing speed and memory constraints. This study proposes a cascaded classifier-based framework for use in biometric recognition systems. The proposed framework utilises a set of weak classifiers to reduce the enrolled users’ dataset to a small list of candidate users. This list is then used by a strong classifier set as the final stage of the cascade to formulate the decision. At each stage, the candidate list is generated by a Mahalanobis distance-based match score quality measure. One of the key features of the authors framework is that each classifier in the ensemble can be designed to use a different modality thus providing the advantages of a truly multimodal biometric recognition system. In addition, it is one of the first truly multimodal cascaded classifier-based approaches for biometric recognition. The performance of the proposed system is evaluated both for single and multimodalities to demonstrate the effectiveness of the approach.

Investigating fusion approaches in multi-biometric cancellable recognition

Cancellable biometrics has recently been introduced in order to overcome some privacy issues about the management of biometric data, aiming to transform a biometric trait into a new but revocable representation for enrolment and identification (verification). Therefore, a new representation of original biometric data can be generated in case of being compromised. Additionally, the use multi-biometric systems are increasingly being deployed in various biometric-based applications since the limitations imposed by a single biometric model can be overcome by these multi-biometric recognition systems. In this paper, we specifically investigate the performance of different fusion approaches in the context of multi-biometrics cancellable recognition. In this investigation, we adjust the ensemble structure to be used for a biometric system and we use as examples two different biometric modalities (voice and iris data) in a multi-biometrics context, adapting three cancellable transformations for each biometric modality.

An Evaluation Survey of Score Normalization in Multibiometric Systems

Multibiometric fusion is an active research area for many years. Score normalization is to transform the scores from different matchers to a common domain. In this paper, we give a survey of classical score normalization techniques and recent advances of this research area. The performance of different normalization functions, such as MinMax, Tanh, Zscore, PL, LTL, RHE and FF are evaluated in XM2VTS Benchmark. We evaluated the performance with four different measures of biometric systems such as EER, AUC, GAR(FAR=0.001) and the threshold of EER. The experimental results show that there is no single normalization technique that would perform the best for all multibiometric recognition systems. PL and FF normalization outperform other methods in many applications.

A Parametric Copula-Based Framework for Hypothesis Testing Using Heterogeneous Data

We present a parametric framework for the joint processing of heterogeneous data, specifically for a binary classification problem. Processing such a data set is not straightforward as heterogeneous data may not be commensurate. In addition, the signals may also exhibit statistical dependence due to overlapping fields of view. We propose a copula-based solution to incorporate statistical dependence between disparate sources of information. The important problem of identifying the best copula for binary classification problems is also addressed. Computer simulation results are presented to demonstrate the feasibility of our approach. The method is also tested on real-data provided by the National Institute of Standards and Technology (NIST) for a multibiometric face recognition application. Finally, performance limits are derived to study the influence of statistical dependence on classification performance.

임베디드 직렬 다중 생체 인식 시스템 개발에 관한 연구

The recent fingerprint recognition system has unstable factors, such as copy of fingerprint patterns and hacking of fingerprint feature point, which mali cause significant system error. Thus, in this research, we used the fingerprint as the main recognition device and then implemented the multi-biometric recognition system in serial using the speech recognition which has been widely used recently. As a multi-biometric recognition system, once the speech is successfully recognized, the fingerprint recognition process is run. In addition, speaker-dependent DTW(Dynamic Time Warping) algorithm is used among existing speech recognition algorithms (VQ, DTW, HMM, NN) for effective real-time process while KSOM (Kohonen Self-Organizing feature Map) algorithm, which is the artificial intelligence method, is applied for the fingerprint recognition system because of its calculation amount. The experiment of multi-biometric recognition system implemented in this research showed 2 to lower FRR (False Rejection Ratio) than single recognition systems using each fingerprints or voice, but zero FAR (False Acceptance Ratio), which is the most important factor in the recognition system. Moreover, there is almost no difference in the recognition time(average 1.5 seconds) comparing with other existing single biometric recognition systems; therefore, it is proved that the multi-biometric recognition system implemented is more efficient security system than single recognition systems based on various experiments.