Imperial College London
Portrait Picture

Dr Ben Glocker

Faculty of Engineering, Department of Computing

Professor in Machine Learning for Imaging
 
 
 
//

Contact

 

+44 (0)20 7594 8334b.glocker Website CV

 
 
//

Location

 

377Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Kanavati:2016:10.1016/j.patcog.2016.09.026,
author = {Kanavati, F and Tong, T and Misawa, K and Fujiwara, M and Mori, K and Rueckert, D and Glocker, B},
doi = {10.1016/j.patcog.2016.09.026},
journal = {Pattern Recognition},
pages = {561--569},
title = {Supervoxel Classification Forests for Estimating Pairwise Image Correspondences},
url = {http://dx.doi.org/10.1016/j.patcog.2016.09.026},
volume = {63},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - This article presents a general method for estimating pairwise image correspondences,which is a fundamental problem in image analysis. The method consistsof over-segmenting a pair of images into supervoxels. A forest classifier is thentrained on one of the images, the source, by using supervoxel indices as voxelwiseclass labels. Applying the forest on the other image, the target, yields asupervoxel labelling, which is then regularised using majority voting within theboundaries of the target’s supervoxels. This yields semi-dense correspondencesin a fully automatic, unsupervised, efficient and robust manner. The advantageof our approach is that no prior information or manual annotations arerequired, making it suitable as a general initialisation component for variousmedical imaging tasks that require coarse correspondences, such as atlas/patchbasedsegmentation, registration, and atlas construction. We demonstrate theeffectiveness of our approach in two different applications: a) initialisation oflongitudinal registration on spine CT data of 96 patients, and b) atlas-basedimage segmentation using 150 abdominal CT images. Comparison to state-ofthe-artmethods demonstrate the potential of supervoxel classification forestsfor estimating image correspondences.
AU  - Kanavati,F
AU  - Tong,T
AU  - Misawa,K
AU  - Fujiwara,M
AU  - Mori,K
AU  - Rueckert,D
AU  - Glocker,B
DO  - 10.1016/j.patcog.2016.09.026
EP  - 569
PY  - 2016///
SN  - 0031-3203
SP  - 561
TI  - Supervoxel Classification Forests for Estimating Pairwise Image Correspondences
T2  - Pattern Recognition
UR  - http://dx.doi.org/10.1016/j.patcog.2016.09.026
UR  - http://hdl.handle.net/10044/1/40518
VL  - 63
ER  -
Download