@inproceedings{criminisi2008geos,
author = {Criminisi, Antonio and Sharp, Toby and Blake, Andrew},
title = {GeoS: Geodesic Image Segmentation},
series = {Lecture Notes in Computer Science},
booktitle = {Proc. European Conference on Computer Vision (ECCV)},
year = {2008},
month = {January},
abstract = {This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data. The segmentation problem is cast as approximate energy minimization in a conditional random field. A new, parallel filtering operator built upon efficient geodesic distance computation is used to propose a set of spatially smooth, contrast-sensitive segmentation hypotheses. An economical search algorithm finds the solution with minimum energy within a sensible and highly restricted subset of all possible labellings. Advantages include: i) computational efficiency with high segmentation accuracy; ii) the ability to estimate an approximation to the posterior over segmentations; iii) the ability to handle generally complex energy models. Comparison with max-flowindicates upto60 times greater computational efficiency as well as greater memory efficiency. GeoS is validated quantitatively and qualitatively by thorough comparative experiments on existing and novel ground-truth data. Numerous results on interactive and automatic segmentation of photographs, video and volumetric medical image data are presented.},
publisher = {Springer},
url = {http://approjects.co.za/?big=en-us/research/publication/geos-geodesic-image-segmentation/},
pages = {99-112},
volume = {5302},
isbn = {978-3-540-88681-5},
edition = {Proc. European Conference on Computer Vision (ECCV)},
}