papers

Publications (8)

cs.CV2019

DeGraF-Flow: Extending DeGraF Features for accurate and efficient sparse-to-dense optical flow estimation

Felix Stephenson, Toby Breckon, Ioannis Katramados

Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature d…

cs.CL2016

SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder

Noura Al Moubayed, Toby Breckon, Peter Matthews +1

In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages. Our approach requires minimum features engineering and a…

q-bio.QM2019

Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification

Nik Khadijah Nik Aznan, Amir Atapour-Abarghouei, Stephen Bonner +3

Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals i…

cs.RO2020

Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss

William Prew, Toby Breckon, Magnus Bordewich +1

In this paper, we introduce two methods of improving real-time object grasping performance from monocular colour images in an end-to-end CNN architecture. The first is the addition…

cs.CV2022

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

Bing Wang, Zhengdi Yu, Bo Yang +5

We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds. Unlike occupancy fields…

cs.CV2021

Towards Automatic Threat Detection: A Survey of Advances of Deep Learning within X-ray Security Imaging

Samet Akcay, Toby Breckon

X-ray security screening is widely used to maintain aviation/transport security, and its significance poses a particular interest in automated screening systems. This paper aims to…

cs.CV2019

Style Augmentation: Data Augmentation via Style Randomization

Philip T. Jackson, Amir Atapour-Abarghouei, Stephen Bonner +2

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both class…

cs.CV2018

Watermark Retrieval from 3D Printed Objects via Convolutional Neural Networks

Xin Zhang, Qian Wang, Toby Breckon +1

We present a method for reading digital data embedded in planar 3D printed surfaces. The data are organised in binary arrays and embedded as surface textures in a way inspired by Q…