Outputs (15)

Understanding insider threat: A framework for characterising attacks (2014)
Presentation / Conference
Nurse, J., Buckley, O., Legg, P., Goldsmith, M., Creese, S., Wright, G., & Whitty, M. (2014, May). Understanding insider threat: A framework for characterising attacks. Paper presented at Workshop on Research for Insider Threat (Security and Privacy Workshops at IEEE Symposium on Security and Privacy)

The threat that insiders pose to businesses, institu- tions and governmental organisations continues to be of serious concern. Recent industry surveys and academic literature provide unequivocal evidence to support the significance of this threat and... Read More about Understanding insider threat: A framework for characterising attacks.

Visualising state space representations of LSTM networks
Presentation / Conference
Smith, E. M., Smith, J., Legg, P., & Francis, S. Visualising state space representations of LSTM networks. Presented at Workshop on Visualization for AI Explainability, Berlin, Germany

Long Short-Term Memory (LSTM) networks have proven to be one of the most effective models for making predictions on sequence-based tasks. These models work by capturing, remembering, and forgetting information relevant to their future predictions. Th... Read More about Visualising state space representations of LSTM networks.

Non-rigid elastic registration of retinal images using local window mutual information
Presentation / Conference
Legg, P., Rosin, P., Marshall, D., & Morgan, J. Non-rigid elastic registration of retinal images using local window mutual information

In this paper we consider the problem of non-rigid retinal image registration between colour fundus photographs and Scanning Laser Ophthalmoscope (SLO) images. Registration would allow for cross-comparison between modalities, giving both appearence a... Read More about Non-rigid elastic registration of retinal images using local window mutual information.

Incorporating neighbourhood feature derivatives with Mutual Information to improve accuracy of multi-modal image registration
Presentation / Conference
Legg, P., Rosin, P., Marshall, D., & Morgan, J. Incorporating neighbourhood feature derivatives with Mutual Information to improve accuracy of multi-modal image registration

In this paper we present an improved method for performing image registration of different modalities. Russakoff [1] proposed the method of Regional Mutual Information (RMI) which allows neighbourhood information to be considered in the Mutual Inform... Read More about Incorporating neighbourhood feature derivatives with Mutual Information to improve accuracy of multi-modal image registration.

Improving accuracy and efficiency of registration by mutual information using Sturges’ Histogram Rule
Presentation / Conference
Legg, P., Rosin, P., Marshall, D., & Morgan, J. Improving accuracy and efficiency of registration by mutual information using Sturges’ Histogram Rule

Mutual Information is a common technique for image registration in the medical domain, in particular where images of different modalities are to be registered. In this paper, we wish to demonstrate the benefits of applying a common method known in st... Read More about Improving accuracy and efficiency of registration by mutual information using Sturges’ Histogram Rule.