Matching of diffusion tensor images using gabor features

Ragini Verma, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel method for feature-based matching of diffusion tensor images using the complete tensor information available at each voxel rather than limited scalar parameters such as the fractional anisotropy. In our method, we characterize each voxel by a rich rotationally invariant feature vector defined using gabor filters. In order to obtain these features, the gabor filters are evaluated at multiple scales and frequencies and are oriented along the dominant direction of the tensors in a neighborhood around the voxel under consideration. The feature is able to obtain a fine to coarse description of each voxel and fully accounts for the highly oriented nature of the tensor data. The proposed matching paradigm based on these Gabor features has been tested on simulated and real images and produces good correspondences.

Original languageEnglish (US)
Title of host publication2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
Pages396-399
Number of pages4
Volume1
StatePublished - 2004
Externally publishedYes
Event2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano - Arlington, VA, United States
Duration: Apr 15 2004Apr 18 2004

Other

Other2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano
CountryUnited States
CityArlington, VA
Period4/15/044/18/04

Fingerprint

Tensors
Gabor filters
Anisotropy

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Verma, R., & Davatzikos, C. (2004). Matching of diffusion tensor images using gabor features. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano (Vol. 1, pp. 396-399)

Matching of diffusion tensor images using gabor features. / Verma, Ragini; Davatzikos, Christos.

2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. p. 396-399.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Verma, R & Davatzikos, C 2004, Matching of diffusion tensor images using gabor features. in 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. vol. 1, pp. 396-399, 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano, Arlington, VA, United States, 4/15/04.
Verma R, Davatzikos C. Matching of diffusion tensor images using gabor features. In 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1. 2004. p. 396-399
Verma, Ragini ; Davatzikos, Christos. / Matching of diffusion tensor images using gabor features. 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. Vol. 1 2004. pp. 396-399
@inproceedings{2c56c1eb90524fa89f302113b5075157,
title = "Matching of diffusion tensor images using gabor features",
abstract = "This paper presents a novel method for feature-based matching of diffusion tensor images using the complete tensor information available at each voxel rather than limited scalar parameters such as the fractional anisotropy. In our method, we characterize each voxel by a rich rotationally invariant feature vector defined using gabor filters. In order to obtain these features, the gabor filters are evaluated at multiple scales and frequencies and are oriented along the dominant direction of the tensors in a neighborhood around the voxel under consideration. The feature is able to obtain a fine to coarse description of each voxel and fully accounts for the highly oriented nature of the tensor data. The proposed matching paradigm based on these Gabor features has been tested on simulated and real images and produces good correspondences.",
author = "Ragini Verma and Christos Davatzikos",
year = "2004",
language = "English (US)",
isbn = "0780383885",
volume = "1",
pages = "396--399",
booktitle = "2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano",

}

TY - GEN

T1 - Matching of diffusion tensor images using gabor features

AU - Verma, Ragini

AU - Davatzikos, Christos

PY - 2004

Y1 - 2004

N2 - This paper presents a novel method for feature-based matching of diffusion tensor images using the complete tensor information available at each voxel rather than limited scalar parameters such as the fractional anisotropy. In our method, we characterize each voxel by a rich rotationally invariant feature vector defined using gabor filters. In order to obtain these features, the gabor filters are evaluated at multiple scales and frequencies and are oriented along the dominant direction of the tensors in a neighborhood around the voxel under consideration. The feature is able to obtain a fine to coarse description of each voxel and fully accounts for the highly oriented nature of the tensor data. The proposed matching paradigm based on these Gabor features has been tested on simulated and real images and produces good correspondences.

AB - This paper presents a novel method for feature-based matching of diffusion tensor images using the complete tensor information available at each voxel rather than limited scalar parameters such as the fractional anisotropy. In our method, we characterize each voxel by a rich rotationally invariant feature vector defined using gabor filters. In order to obtain these features, the gabor filters are evaluated at multiple scales and frequencies and are oriented along the dominant direction of the tensors in a neighborhood around the voxel under consideration. The feature is able to obtain a fine to coarse description of each voxel and fully accounts for the highly oriented nature of the tensor data. The proposed matching paradigm based on these Gabor features has been tested on simulated and real images and produces good correspondences.

UR - http://www.scopus.com/inward/record.url?scp=17144380827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17144380827&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780383885

SN - 9780780383883

VL - 1

SP - 396

EP - 399

BT - 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano

ER -