Audio-visual biometrics using reliability-based late fusion and deep neural networks

Mohammad Rafiqul Alam

    Research output: ThesisDoctoral Thesis

    134 Downloads (Pure)

    Abstract

    Recently data acquisition for audio-visual biometric systems has been facilitated by the advancement of mobile phone technology. The captured data may be of poor quality due to various factors such as variation in environment, pose and illumination. Although a quality based fusion approach may be used to deal with this, measuring the quality at the signal level is difficult, particularly for the visual inputs. This thesis presents a reliability-based late fusion framework as a method of dealing with noisy Input signals. In addition, a novel three-step algorithm is proposed to train a multimodal deep neural network.
    Original languageEnglish
    QualificationDoctor of Philosophy
    Awarding Institution
    • The University of Western Australia
    Award date20 Sep 2016
    Publication statusUnpublished - 2016

    Fingerprint

    Biometrics
    Fusion reactions
    Mobile phones
    Data acquisition
    Lighting
    Deep neural networks

    Cite this

    @phdthesis{db5c87b8fdcc4733b1b1975a21acbdbf,
    title = "Audio-visual biometrics using reliability-based late fusion and deep neural networks",
    abstract = "Recently data acquisition for audio-visual biometric systems has been facilitated by the advancement of mobile phone technology. The captured data may be of poor quality due to various factors such as variation in environment, pose and illumination. Although a quality based fusion approach may be used to deal with this, measuring the quality at the signal level is difficult, particularly for the visual inputs. This thesis presents a reliability-based late fusion framework as a method of dealing with noisy Input signals. In addition, a novel three-step algorithm is proposed to train a multimodal deep neural network.",
    keywords = "Audio-visual biometrics, Reliability fusion, Deep Boltzmann machine, Entropy fusion, Joint DBM, Mobile biometrics, i-vectors, Linear regression",
    author = "Alam, {Mohammad Rafiqul}",
    year = "2016",
    language = "English",
    school = "The University of Western Australia",

    }

    Alam, MR 2016, 'Audio-visual biometrics using reliability-based late fusion and deep neural networks', Doctor of Philosophy, The University of Western Australia.

    Audio-visual biometrics using reliability-based late fusion and deep neural networks. / Alam, Mohammad Rafiqul.

    2016.

    Research output: ThesisDoctoral Thesis

    TY - THES

    T1 - Audio-visual biometrics using reliability-based late fusion and deep neural networks

    AU - Alam, Mohammad Rafiqul

    PY - 2016

    Y1 - 2016

    N2 - Recently data acquisition for audio-visual biometric systems has been facilitated by the advancement of mobile phone technology. The captured data may be of poor quality due to various factors such as variation in environment, pose and illumination. Although a quality based fusion approach may be used to deal with this, measuring the quality at the signal level is difficult, particularly for the visual inputs. This thesis presents a reliability-based late fusion framework as a method of dealing with noisy Input signals. In addition, a novel three-step algorithm is proposed to train a multimodal deep neural network.

    AB - Recently data acquisition for audio-visual biometric systems has been facilitated by the advancement of mobile phone technology. The captured data may be of poor quality due to various factors such as variation in environment, pose and illumination. Although a quality based fusion approach may be used to deal with this, measuring the quality at the signal level is difficult, particularly for the visual inputs. This thesis presents a reliability-based late fusion framework as a method of dealing with noisy Input signals. In addition, a novel three-step algorithm is proposed to train a multimodal deep neural network.

    KW - Audio-visual biometrics

    KW - Reliability fusion

    KW - Deep Boltzmann machine

    KW - Entropy fusion

    KW - Joint DBM

    KW - Mobile biometrics

    KW - i-vectors

    KW - Linear regression

    M3 - Doctoral Thesis

    ER -