Department of Electrical and Electronics Engineering

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1925

Browse

Filters

2019 - 20202

Settings

Author: search.filters.author.Ajmera, Pawan K.Subject: search.filters.subject.Convolutional neural networks (CNNs)

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Upgrading security and protection in ear biometrics
    (IET, 2019-02) Ajmera, Pawan K.
    Biometrics is being widely accepted for user authentication across the globe. Integration of biometrics in the daily life provokes the need to design secure authentication systems. This study proposes the use of outer ear images as a biometric modality. The comparable complexity between the human outer ear and face in terms of its uniqueness and permanence has increased interest in the use of ear as a biometric. However, similar to face recognition, it poses challenges of variation in illumination, contrast, rotation, scale and pose. Owing to the extensive work in the field of computer vision using convolutional neural networks (CNNs), its feasibility in the field of ear biometrics has been presented in this work. The proposed technique uses a CNN as a feature extractor and a support vector machine (SVM) for the classification task. The joint CNN-SVM framework is used for mapping ear images to random base-n codes. The codes are further hashed using the secure hash algorithm SHA-3 to generate secure ear templates. The feasibility of the proposed technique has been evaluated on annotated web ears dataset. This work demonstrates 12.52% average equal error rate without any image pre-processing, which shows that the proposed approach is promising in the field of secure ear biometrics.
  • No Thumbnail Available
    Item
    Audio classification using braided convolutional neural networks
    (IET, 2020-09) Ajmera, Pawan K.
    Convolutional neural networks (CNNs) work surprisingly well and have helped drastically enhance the state-of-the-art techniques in the domain of image classification. The unprecedented success motivated the application of CNNs to the domain of auditory data. Recent publications suggest hidden Markov models and deep neural networks for audio classification. This study aims to achieve audio classification by representing audio as spectrogram images and then use a CNN-based architecture for classification. This study presents an innovative strategy for a CNN-based neural architecture that learns a sparse representation imitating the receptive neurons in the primary auditory cortex in mammals. The feasibility of the proposed CNN-based neural architecture is assessed for audio classification tasks on standard benchmark datasets such as Google Speech Commands datasets (GSCv1 and GSCv2) and the UrbanSound8K dataset (US8K). The proposed CNN architecture, referred to as braided convolutional neural network, achieves 97.15, 95 and 91.9% average recognition accuracy on GSCv1, GSCv2 and US8 K datasets, respectively, outperforming other deep learning architectures.