Biometric Recognition

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 6024 Experts worldwide ranked by ideXlab platform

Dimitris Hatzinakos - One of the best experts on this subject based on the ideXlab platform.

  • Transient Otoacoustic Emissions for Biometric Recognition
    2012 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2012
    Co-Authors: Foteini Agrafioti, Siyuan Wang, Dimitris Hatzinakos
    Abstract:

    This paper investigates the potential use of Transient Otoacoustic Emissions (TEOAE) for Biometric Recognition. Multiresolution decomposition of TEOAE is done by a modified Bivariate EmpiricalMode Decomposition (BEMD) combined with an auditory model. Matching scores are computed by combining ranked correlations across different levels. Recognition rate with recording from left ear is 96.30% and can be improved to 98.15% by utilizing a matching score fusion with information from right ear.

  • ICASSP - Transient Otoacoustic Emissions for Biometric Recognition
    2012 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2012
    Co-Authors: Foteini Agrafioti, Siyuan Wang, Dimitris Hatzinakos
    Abstract:

    This paper investigates the potential use of Transient Otoacoustic Emissions (TEOAE) for Biometric Recognition. Multiresolution decomposition of TEOAE is done by a modified Bivariate EmpiricalMode Decomposition (BEMD) combined with an auditory model. Matching scores are computed by combining ranked correlations across different levels. Recognition rate with recording from left ear is 96.30% and can be improved to 98.15% by utilizing a matching score fusion with information from right ear.

  • ecg in Biometric Recognition time dependency and application challenges
    2011
    Co-Authors: Dimitris Hatzinakos, Foteini Agrafioti
    Abstract:

    As Biometric Recognition becomes increasingly popular, the fear of circumvention, obfuscation and replay attacks is a rising concern. Traditional Biometric modalities such as the face, the fingerprint or the iris are vulnerable to such attacks, which defeats the purpose of Biometric Recognition, namely to employ physiological characteristics for secure identity Recognition. This thesis advocates the use the electrocardiogram (ECG) signal for human identity Recognition. The ECG is a vital signal of the human body, and as such, it naturally provides liveness detection, robustness to attacks, universality and permanence. In addition, ECG inherently satisfies uniqueness requirements, because the morphology of the signal is highly dependent on the particular anatomical and geometrical characteristics of the myocardium in the heart. However, the ECG is a continuous signal, and this presents a great challenge to Biometric Recognition. With this modality, instantaneous variability is expected even within recordings of the same individual due to a variety of factors, including recording noise, or physical and psychological activity. While the noise and heart rate variations due to physical exercise can be addressed with appropriate feature extraction, the effects of emotional activity on the ECG signal are more obscure. This thesis deals with this problem from an affective computing point of view. First, the psychological conditions that affect the ECG and endanger Biometric accuracy are identified. Experimental setups that are targeted to provoke active and passive arousal as well as positive and negative valence are presented. The empirical mode decomposition (EMD) is used as the basis for the detection of emotional patterns, after adapting the algorithm to the particular needs of the ECG signal. Instantaneous frequency and oscillation features are used for state classification in various clustering setups. The result of this analysis is the designation of psychological states which affect the ECG signal to an extent that Biometric matching may not be feasible. An updating methodology is proposed to address this problem, wherein the signal is monitored for instantaneous changes that require the design of a new template. Furthermore, this thesis presents the enhanced Autocorrelation- Linear Discriminant Analysis (AC/LDA) algorithm for feature extraction, which incorporates a signal quality assessment module based on the periodicity transform. Three deployment scenarios are considered namely a) small-scale Recognition systems, b) large-scale Recognition systems and c) Recognition in distributed systems. The enhanced AC/LDA algorithm is adapted to each setting, and the advantages and disadvantages of each scenario are discussed. Overall, this thesis attempts to provide the necessary algorithmic and practical framework for the real-life deployment of the ECG signal in Biometric Recognition.

  • BTAS - HeartID: Cardiac Biometric Recognition
    2010 Fourth IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS), 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population [1–12]. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.

  • HeartID: Cardiac Biometric Recognition
    IEEE 4th International Conference on Biometrics: Theory Applications and Systems BTAS 2010, 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.

Foteini Agrafioti - One of the best experts on this subject based on the ideXlab platform.

  • Transient Otoacoustic Emissions for Biometric Recognition
    2012 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2012
    Co-Authors: Foteini Agrafioti, Siyuan Wang, Dimitris Hatzinakos
    Abstract:

    This paper investigates the potential use of Transient Otoacoustic Emissions (TEOAE) for Biometric Recognition. Multiresolution decomposition of TEOAE is done by a modified Bivariate EmpiricalMode Decomposition (BEMD) combined with an auditory model. Matching scores are computed by combining ranked correlations across different levels. Recognition rate with recording from left ear is 96.30% and can be improved to 98.15% by utilizing a matching score fusion with information from right ear.

  • ICASSP - Transient Otoacoustic Emissions for Biometric Recognition
    2012 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2012
    Co-Authors: Foteini Agrafioti, Siyuan Wang, Dimitris Hatzinakos
    Abstract:

    This paper investigates the potential use of Transient Otoacoustic Emissions (TEOAE) for Biometric Recognition. Multiresolution decomposition of TEOAE is done by a modified Bivariate EmpiricalMode Decomposition (BEMD) combined with an auditory model. Matching scores are computed by combining ranked correlations across different levels. Recognition rate with recording from left ear is 96.30% and can be improved to 98.15% by utilizing a matching score fusion with information from right ear.

  • ecg in Biometric Recognition time dependency and application challenges
    2011
    Co-Authors: Dimitris Hatzinakos, Foteini Agrafioti
    Abstract:

    As Biometric Recognition becomes increasingly popular, the fear of circumvention, obfuscation and replay attacks is a rising concern. Traditional Biometric modalities such as the face, the fingerprint or the iris are vulnerable to such attacks, which defeats the purpose of Biometric Recognition, namely to employ physiological characteristics for secure identity Recognition. This thesis advocates the use the electrocardiogram (ECG) signal for human identity Recognition. The ECG is a vital signal of the human body, and as such, it naturally provides liveness detection, robustness to attacks, universality and permanence. In addition, ECG inherently satisfies uniqueness requirements, because the morphology of the signal is highly dependent on the particular anatomical and geometrical characteristics of the myocardium in the heart. However, the ECG is a continuous signal, and this presents a great challenge to Biometric Recognition. With this modality, instantaneous variability is expected even within recordings of the same individual due to a variety of factors, including recording noise, or physical and psychological activity. While the noise and heart rate variations due to physical exercise can be addressed with appropriate feature extraction, the effects of emotional activity on the ECG signal are more obscure. This thesis deals with this problem from an affective computing point of view. First, the psychological conditions that affect the ECG and endanger Biometric accuracy are identified. Experimental setups that are targeted to provoke active and passive arousal as well as positive and negative valence are presented. The empirical mode decomposition (EMD) is used as the basis for the detection of emotional patterns, after adapting the algorithm to the particular needs of the ECG signal. Instantaneous frequency and oscillation features are used for state classification in various clustering setups. The result of this analysis is the designation of psychological states which affect the ECG signal to an extent that Biometric matching may not be feasible. An updating methodology is proposed to address this problem, wherein the signal is monitored for instantaneous changes that require the design of a new template. Furthermore, this thesis presents the enhanced Autocorrelation- Linear Discriminant Analysis (AC/LDA) algorithm for feature extraction, which incorporates a signal quality assessment module based on the periodicity transform. Three deployment scenarios are considered namely a) small-scale Recognition systems, b) large-scale Recognition systems and c) Recognition in distributed systems. The enhanced AC/LDA algorithm is adapted to each setting, and the advantages and disadvantages of each scenario are discussed. Overall, this thesis attempts to provide the necessary algorithmic and practical framework for the real-life deployment of the ECG signal in Biometric Recognition.

  • BTAS - HeartID: Cardiac Biometric Recognition
    2010 Fourth IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS), 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population [1–12]. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.

  • HeartID: Cardiac Biometric Recognition
    IEEE 4th International Conference on Biometrics: Theory Applications and Systems BTAS 2010, 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.

Rafiqul Islam - One of the best experts on this subject based on the ideXlab platform.

  • Robust ear Biometric Recognition using neural network
    2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2017
    Co-Authors: Mozammel Chowdhury, Rafiqul Islam
    Abstract:

    Ear based Biometric Recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear Biometric Recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.

B.v.k. Vijaya Kumar - One of the best experts on this subject based on the ideXlab platform.

  • Segmentation-Free Biometric Recognition Using Correlation Filters
    Academic Press Library in Signal Processing, 2020
    Co-Authors: Andres Rodriguez, B.v.k. Vijaya Kumar
    Abstract:

    Abstract In most Biometric Recognition studies, test Biometric signatures (e.g., faces, irises, finger prints, etc.) are segmented from their background before they are compared to stored signatures. However, such segmentation is not easy to carry out in challenging imaging conditions. Here we show that correlation filters (CFs) can be used to avoid segmentation and achieve segmentation-free Biometric Recognition. CFs do not require the object of interest to first be localized or segmented. In this paper we review in detail the most popular CF design algorithms and discuss their different usages and advantages. We begin with still images and then explore their usage in image sequences or video and activity Recognition. As an example of the power of CFs, experimental result are presented in this paper is in the area of recognizing people in videos using their ocular (eye) regions where common iris Recognition techniques fails due to low resolution. We also discuss examples when CFs have been applied to recognize faces, to localize pedestrians, and to recognize pedestrian actions.

  • Identifying the best periocular region for Biometric Recognition
    Iris and Periocular Biometric Recognition, 2017
    Co-Authors: Jonathon M. Smereka, B.v.k. Vijaya Kumar
    Abstract:

    Periocular images contain iris as well as other near-by regions such as eyelids and eyebrows. It is useful to know which regions of ocular images are important for achieving good Recognition performance. This chapter will present observations from experiments with regard to the effect of changing the size or selection of the periocular region on Biometric Recognition performance. One can use a single definition of the periocular region to identify areas that contain significant discriminative textural information in an attempt to identify such regions. In this chapter, we investigate sub-region effects over varying cropping sizes to determine an appropriate periocular image representation.

  • ICIP (1) - Spatial frequency domain image processing for Biometric Recognition
    Proceedings. International Conference on Image Processing, 2002
    Co-Authors: B.v.k. Vijaya Kumar, M. Savvides, K. Venkataramani
    Abstract:

    Biometric Recognition refers to the process of matching an input Biometric to stored Biometric information. In particular, Biometric verification refers to matching the live Biometric input from an individual to the stored Biometric template about that individual. Examples of Biometrics include face images, fingerprint images, iris images, retinal scans, etc. Thus, image processing techniques prove useful in the Biometric Recognition. We discuss spatial frequency domain image processing methods useful for Biometric Recognition.

  • Spatial frequency domain image processing for Biometric Recognition
    Proceedings. International Conference on Image Processing, 2002
    Co-Authors: B.v.k. Vijaya Kumar, M. Savvides, K. Venkataramani
    Abstract:

    Biometric Recognition refers to the process of matching an input Biometric to stored Biometric information. In particular, Biometric verification refers to matching the live Biometric input from an individual to the stored Biometric template about that individual. Examples of Biometrics include face images, fingerprint images, iris images, retinal scans, etc. Thus, image processing techniques prove useful in the Biometric Recognition. We discuss spatial frequency domain image processing methods useful for Biometric Recognition.

S. Zahra Fatemian - One of the best experts on this subject based on the ideXlab platform.

  • BTAS - HeartID: Cardiac Biometric Recognition
    2010 Fourth IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS), 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population [1–12]. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.

  • HeartID: Cardiac Biometric Recognition
    IEEE 4th International Conference on Biometrics: Theory Applications and Systems BTAS 2010, 2010
    Co-Authors: S. Zahra Fatemian, Foteini Agrafioti, Dimitris Hatzinakos
    Abstract:

    This letter examines the applicability of cardiac signals for Biometric Recognition. Two physiological signals are considered, namely the Electrocardiogram (ECG) and the Phono-cardiogram (PCG) as it has been shown they bare adequate discriminative information in a population. Due to the idiosyncratic properties of ECG and PCG, individual algorithms are developed for feature extraction. Time dependency, a major challenge of cardiac Biometrics, is taken to consideration in the design of robust gallery templates. To that end, a wavelet based analysis is introduced to handle noise artifacts and heart rate variability. A bi-modal configuration is presented, to perform decision level fusion of the information. The Recognition performance, tested over 21 subjects, is very promising.