Details of Grant 

EPSRC Reference:	GR/K93471/01
Title:	DEVELOPMENT OF GRAPH-BASED SEGMENTATION ALGORITHMS WITH THE IU E FRAMEWORK
Principal Investigator:	Spann, Dr M
Other Investigators:	Pycock, Mr D
Researcher Co-Investigators:
Project Partners:
Department:	Electronic, Electrical and Computer Eng
Organisation:	University of Birmingham
Scheme:	Standard Research (Pre-FEC)
Starts:	01 April 1997	Ends:	30 June 1999	Value (£):	41,743
EPSRC Research Topic Classifications:	Image & Vision Computing
EPSRC Industrial Sector Classifications:
Related Grants:
Panel History:
Summary on Grant Application Form
A need has been identified within the UK machine vision community for a software environment to support research and specifically the issue of software standardisation. Within that overall context, the Image Understanding Environment (IUE) framework is seen to be lacking in a number of technical areas. This proposal is intended to contribute additional functionality to the IUE in key areas of texture and motion analysis. The overall theme of the proposed research will be image segmentation which is defined as the abstraction, through the use of labelling, of the image into segments according to some criteria of homogeneity. Segmentation is a crucial part of almost all real-world machine vision applications because the image usually comprises more than one area of interest that has to be identified. The benefits of having a range of modern image segmentation techniques implemented within a standard software framework as well as having a set of tools with which to implement new techniques is that it allows algorithms to be rapidly compared to a large range of data and it allows applications that rely on having a segmented image to be rapidly developed. The proposed research will be aimed at the implementation of a class of image segmentation algorithms which apply optimisation techniques to graph data structures, these data structures being supported by the IUE 'core'. This class of techniques spans current state-of-the-art research into image segmentation. Both grey-level and texture segmentation algorithms will be implemented on 2D and 3D data as well as motion-based segmentation on image sequence data.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.bham.ac.uk