Browsing by Author "Bazrafkan, Shabab"
Now showing items 1-12 of 12
-
The application of deep learning on depth from multi-array camera
Javidnia, Hossein; Bazrafkan, Shabab; Corcoran, Peter (Institute of Electrical and Electronics Engineers, 2018-01-02)Consumer-level multi-array cameras are a key enabling technology for next generation smartphones imaging systems. The present paper aims to analyze the accuracy of the depth estimation while using different camera combinations ... -
Contributions to deep learning methodologies
Bazrafkan, Shabab (NUI Galway, 2018-10-26)In recent years the Deep Neural Networks (DNN) has been using widely in a big range of machine learning and data-mining purposes. This pattern recognition approach can handle highly nonlinear problems. In this work, ... -
Deep learning for consumer devices and services: Pushing the limits for machine learning, artificial intelligence, and computer vision
Lemley, Joseph; Bazrafkan, Shabab; Corcoran, Peter (Institute of Electrical and Electronics Engineers (IEEE), 2017-04)In the last few years, we have witnessed an exponential growth in research activity into the advanced training of convolutional neural networks (CNNs), a field that has become known as deep learning. This has been triggered ... -
Deep learning for consumer devices and services: Pushing the limits for machine learning, artificial intelligence, and computer vision (Errata for acknowledgments)
Lemley, Joseph; Bazrafkan, Shabab; Corcoran, Peter (IEEE, 2017-06-14)Presents corrections for acknowledgments in the paper: Lemley, J., Bazrafkan, S., & Corcoran, P. (2017). Deep Learning for Consumer Devices and Services: Pushing the limits for machine learning, artificial intelligence, ... -
Deep learning for facial expression recognition: A step closer to a smartphone that knows your moods
Bazrafkan, Shabab; Nedelcu, Tudor; Filipczuk, Pawel; Corcoran, Peter (Institute of Electrical and Electronics Engineers, 2017-01-08)By growing the capacity and processing power of the handheld devices nowadays, a wide range of capabilities can be implemented in these devices to make them more intelligent and user friendly. Determining the mood of the ... -
Deep learning for hand segmentation in complex backgrounds
Ungureanu, Adrian-Stefan; Bazrafkan, Shabab; Corcoran, Peter (Institute of Electrical and Electronics Engineers, 2018-01-02)This paper presents a Deep Learning segmentation approach for hand segmentation in gray level images with cluttered backgrounds where standard techniques cannot be used. Two networks were trained with a database of hand ... -
Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets
Varkarakis, Viktor; Bazrafkan, Shabab; Corcoran, Peter (Elsevier, 2019-08-01)A data augmentation methodology is presented and applied to generate a large dataset of off-axis iris regions and train a low-complexity deep neural network. Although of low complexity the resulting network achieves a high ... -
Latent space mapping for generation of object elements with corresponding data annotation
Bazrafkan, Shabab; Javidnia, Hossein; Corcoran, Peter (Elsevier, 2018-10-25)Deep neural generative models such as Variational Auto-Encoders (VAE) and Generative Adversarial Networks (GAN) give promising results in estimating the data distribution across a range of machine learning fields of ... -
Pushing the AI envelope: merging deep networks to accelerate edge artificial intelligence in consumer electronics devices and systems
Bazrafkan, Shabab; Corcoran, Peter (IEEE, 2018-02-08)Deep neural networks (DNNs) are widely used by both academic and industry researchers to solve many long-standing problems in machine learning. There has been such a growth of research in this field, and it has been applied ... -
Re-training StyleGAN-A first step towards building large, scalable synthetic facial datasets
Varkarakis, Viktor; Bazrafkan, Shabab; Corcoran, Peter (Institute of Electrical and Electronics Engineers (IEEE), 2020-08-31)StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper we recap the StyleGAN architecture and training methodology and ... -
Semiparallel deep neural network hybrid architecture: first application on depth from monocular camera
Bazrafkan, Shabab; Javidnia, Hossein; Lemley, Joseph; Corcoran, Peter (Society of Photo-optical Instrumentation Engineers (SPIE), 2018-08-07)Deep neural networks have been applied to a wide range of problems in recent years. Convolutional neural network is applied to the problem of determining the depth from a single camera image (monocular depth). Eight different ... -
Smart augmentation learning an optimal data augmentation strategy
Lemley, Joseph; Bazrafkan, Shabab; Corcoran, Peter (Institute of Electrical and Electronics Engineers (IEEE), 2017-04-24)A recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks. There are many techniques to address this, including ...