250036 60 archive 960 http://eprints.ecs.soton.ac.uk/id/eprint/36 disk0/00/25/00/36 2001-10-29 2026-05-21 01:34:59 2011-03-01 10:13:45 article show 0 pub none 1997 IEEE Trans. on Pattern Analysis and Machine Intelligence FALSE 8f5a429e-c670-42a4-955d-9ff7bcbecf3d e18b223d-73f8-4d0b-971e-87475fc2a1e9 19 1 Gunn S.R. 306af9b3-a7fa-4381-baf9-5d6a6ec89868 0009-0003-8924-8263 FALSE Nixon M.S. 2b5b9804-5a81-462a-82e6-92ee5fa74e12 0000-0002-9174-5934 FALSE http://www.loc.gov/loc.terms/relators/AUT Gunn S.R. 306af9b3-a7fa-4381-baf9-5d6a6ec89868 0009-0003-8924-8263 FALSE http://www.loc.gov/loc.terms/relators/AUT Nixon M.S. 2b5b9804-5a81-462a-82e6-92ee5fa74e12 0000-0002-9174-5934 FALSE A conventional active contour formulation suffers difficulty in appropriate choice of an initial contour and values of parameters. Recent approaches have aimed to resolve these problems but can compromise other performance aspects. To relieve the problem in initialisation, we use a dual active contour, which is combined with a local shape model to improve the parameterisation. One contour expands from inside the target feature, the other contracts from the outside. The two contours are inter-linked to provide a balanced technique with an ability to reject weak local energy minima. published 63--68 eng Electronic & Software Systems Southampton Wireless Group ea7365ce-ddee-42be-8033-ec60f866414d info:eu-repo/semantics/article 1997 published 304 2001-10-29