Dr Voiculescu works in the general area of geometric modelling, with particular interest in topics such as:
- Medical image analysis
- 3D printing
- Mathematics of curves and surfaces
- Finding roots of polynomials
- Constructive Solid Geometry (CSG)
- Molecular modelling
In recent years her research has focused on the analysis of CT scans. Members of the Spatial Reasoning research group have developed image segmentation software to partition CT scan images into regions with similar properties. These images are then analysed further so that particular features (such as bones, organs or blood vessels) can be identified within them and segmented out. Irina's research continues to deal with each of these two separate meanings of medical image segmentation.
Here is a 3D reconstruction of an abdominal CT scan. It features the rib cage, liver, kidneys, spleen, blood vessels and a renal tumour.
Irina is always happy to supervise MSc or DPhil projects in this general area.
One of the current goals is to enable the software to work with input from MRI scans. We have recently received a generous John Fell OUP Research Fund award to further our research in this area.
- Varduhi Yeghiazaryan, started October 2013, working on region growing methods for feature identification
- Stuart Golodetz,DPhil, "Zipping and unzipping: the use of image partition forests in the analysis of abdominal CT scans", 2006-2011
- Gwyn Skone, DPhil, "Stratagems for effective function evaluation in computational chemistry", 2005-2010
- Jian Chen, DPhil in collaboration with the Department of Structural Biology, "Improving icosahedral virus reconstruction from cryo-electron micrographs", 2002-2012
Dr Irina Voiculescu has been a Lecturer at the Oxford University Department of Computer Science since 1999. She obtained her PhD at the University of Bath, for research in Constructive Solid Geometry (CSG). She contributed to the development of the geometric modelling software svLis through the application of polynomial root finding methods.
As part of the Spatial Reasoning research group at Oxford she has been conducting research in the areas of molecular modelling (protein docking), medical imaging (CT scan analysis) and polynomial root finding (interval arithmetic). She is interested in other aspects of geometric modelling such as as applications of multivariate polynomial forms in geometry, Bernstein-form polynomials and generalized Newton-like methods.
Irina is actively involved in public engagement activities, such as the Oxford RobotGames, a programme where children of high school age design and build their own robot in half a day. Another on-going project of the Spatial Reasoning group has been to build a robot sheepdog which automatically herds either live or robotic animals. The Oxford robotic flock was shown in 2001 at the Royal Society Summer Science Exhibition.
She is a Fellow of the UK Geometric Modelling Society.
Path reducing watershed for the GPU
Varduhi Yeghiazaryan and Irina Voiculescu
IEEE Winter Conf. on Applications of Computer Vision. 2018.
Simpler Editing of Graph−Based Segmentation Hierarchies using Zipping Algorithms
Stuart Golodetz‚ Irina Voiculescu and Stephen Cameron
In Pattern Recognition. Vol. 70. Pages 44−59. October, 2017.
Interpolation of 3D slice volume data for 3D printing
Samuel Littley and Irina Voiculescu
In Proceedings of SPIE Medical Imaging. SPIE International Society for Optics and Photonics. February, 2017.