Mutual information-based 3D surface matching with applications to face recognition and brain mapping

Yalin Wang, Ming Chang Chiang, Paul M. Thompson

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

33 Citations (Scopus)

Abstract

Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surface-based registration is useful for tracking brain change, and for creating statistical shape models of anatomy. Based on surface correspondences, metrics can also be designed to measure differences in facial geometry and expressions. To avoid the need for a large set of manually-defined landmarks to constrain these surface correspondences, we developed an algorithm to automate the matching of surface features. It extends the mutual information method to automatically match general 3D surfaces (including surfaces with a branching topology). We use diffeomorphic flows to optimally align the Riemann surface structures of two surfaces. First, we use holomorphic 1-forms to induce consistent conformal grids on both surfaces. High genus surfaces are mapped to a set of rectangles in the Euclidean plane, and closed genus-zero surfaces are mapped to the sphere. Next, we compute stable geometric features (mean curvature and conformai factor) and pull them back as scalar fields onto the 2D parameter domains. Mutual information is used as a cost functional to drive a fluid flow in the parameter domain that optimally aligns these surface features. A diffeomorphic surface-to-surface mapping is then recovered that matches surfaces in 3D. Lastly, we present a spectral method that ensures that the grids induced on the target surface remain conformal when pulled through the correspondence field. Using the chain rule, we express the gradient of the mutual information between surfaces in the conformal basis of the source surface. This finite-dimensional linear space generates all conformal reparameterizations of the surface. Illustrative experiments apply the method to face recognition and to the registration of brain structures, such as the hippocampus in 3D MRI scans, a key step in understanding brain shape alterations in Alzheimer's disease and schizophrenia.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Pages527-534
Number of pages8
VolumeI
DOIs
StatePublished - 2005
Externally publishedYes
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: Oct 17 2005Oct 20 2005

Other

OtherProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
CountryChina
CityBeijing
Period10/17/0510/20/05

Fingerprint

Brain mapping
Face recognition
Brain

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Wang, Y., Chiang, M. C., & Thompson, P. M. (2005). Mutual information-based 3D surface matching with applications to face recognition and brain mapping. In Proceedings of the IEEE International Conference on Computer Vision (Vol. I, pp. 527-534). [1541299] https://doi.org/10.1109/ICCV.2005.165

Mutual information-based 3D surface matching with applications to face recognition and brain mapping. / Wang, Yalin; Chiang, Ming Chang; Thompson, Paul M.

Proceedings of the IEEE International Conference on Computer Vision. Vol. I 2005. p. 527-534 1541299.

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

Wang, Y, Chiang, MC & Thompson, PM 2005, Mutual information-based 3D surface matching with applications to face recognition and brain mapping. in Proceedings of the IEEE International Conference on Computer Vision. vol. I, 1541299, pp. 527-534, Proceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, 10/17/05. https://doi.org/10.1109/ICCV.2005.165
Wang Y, Chiang MC, Thompson PM. Mutual information-based 3D surface matching with applications to face recognition and brain mapping. In Proceedings of the IEEE International Conference on Computer Vision. Vol. I. 2005. p. 527-534. 1541299 https://doi.org/10.1109/ICCV.2005.165
Wang, Yalin ; Chiang, Ming Chang ; Thompson, Paul M. / Mutual information-based 3D surface matching with applications to face recognition and brain mapping. Proceedings of the IEEE International Conference on Computer Vision. Vol. I 2005. pp. 527-534
@inproceedings{11fbddb8c7ec47ff844a01b8e2b4d1b1,
title = "Mutual information-based 3D surface matching with applications to face recognition and brain mapping",
abstract = "Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surface-based registration is useful for tracking brain change, and for creating statistical shape models of anatomy. Based on surface correspondences, metrics can also be designed to measure differences in facial geometry and expressions. To avoid the need for a large set of manually-defined landmarks to constrain these surface correspondences, we developed an algorithm to automate the matching of surface features. It extends the mutual information method to automatically match general 3D surfaces (including surfaces with a branching topology). We use diffeomorphic flows to optimally align the Riemann surface structures of two surfaces. First, we use holomorphic 1-forms to induce consistent conformal grids on both surfaces. High genus surfaces are mapped to a set of rectangles in the Euclidean plane, and closed genus-zero surfaces are mapped to the sphere. Next, we compute stable geometric features (mean curvature and conformai factor) and pull them back as scalar fields onto the 2D parameter domains. Mutual information is used as a cost functional to drive a fluid flow in the parameter domain that optimally aligns these surface features. A diffeomorphic surface-to-surface mapping is then recovered that matches surfaces in 3D. Lastly, we present a spectral method that ensures that the grids induced on the target surface remain conformal when pulled through the correspondence field. Using the chain rule, we express the gradient of the mutual information between surfaces in the conformal basis of the source surface. This finite-dimensional linear space generates all conformal reparameterizations of the surface. Illustrative experiments apply the method to face recognition and to the registration of brain structures, such as the hippocampus in 3D MRI scans, a key step in understanding brain shape alterations in Alzheimer's disease and schizophrenia.",
author = "Yalin Wang and Chiang, {Ming Chang} and Thompson, {Paul M.}",
year = "2005",
doi = "10.1109/ICCV.2005.165",
language = "English (US)",
isbn = "076952334X",
volume = "I",
pages = "527--534",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",

}

TY - GEN

T1 - Mutual information-based 3D surface matching with applications to face recognition and brain mapping

AU - Wang, Yalin

AU - Chiang, Ming Chang

AU - Thompson, Paul M.

PY - 2005

Y1 - 2005

N2 - Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surface-based registration is useful for tracking brain change, and for creating statistical shape models of anatomy. Based on surface correspondences, metrics can also be designed to measure differences in facial geometry and expressions. To avoid the need for a large set of manually-defined landmarks to constrain these surface correspondences, we developed an algorithm to automate the matching of surface features. It extends the mutual information method to automatically match general 3D surfaces (including surfaces with a branching topology). We use diffeomorphic flows to optimally align the Riemann surface structures of two surfaces. First, we use holomorphic 1-forms to induce consistent conformal grids on both surfaces. High genus surfaces are mapped to a set of rectangles in the Euclidean plane, and closed genus-zero surfaces are mapped to the sphere. Next, we compute stable geometric features (mean curvature and conformai factor) and pull them back as scalar fields onto the 2D parameter domains. Mutual information is used as a cost functional to drive a fluid flow in the parameter domain that optimally aligns these surface features. A diffeomorphic surface-to-surface mapping is then recovered that matches surfaces in 3D. Lastly, we present a spectral method that ensures that the grids induced on the target surface remain conformal when pulled through the correspondence field. Using the chain rule, we express the gradient of the mutual information between surfaces in the conformal basis of the source surface. This finite-dimensional linear space generates all conformal reparameterizations of the surface. Illustrative experiments apply the method to face recognition and to the registration of brain structures, such as the hippocampus in 3D MRI scans, a key step in understanding brain shape alterations in Alzheimer's disease and schizophrenia.

AB - Face recognition and many medical imaging applications require the computation of dense correspondence vector fields that match one surface with another. In brain imaging, surface-based registration is useful for tracking brain change, and for creating statistical shape models of anatomy. Based on surface correspondences, metrics can also be designed to measure differences in facial geometry and expressions. To avoid the need for a large set of manually-defined landmarks to constrain these surface correspondences, we developed an algorithm to automate the matching of surface features. It extends the mutual information method to automatically match general 3D surfaces (including surfaces with a branching topology). We use diffeomorphic flows to optimally align the Riemann surface structures of two surfaces. First, we use holomorphic 1-forms to induce consistent conformal grids on both surfaces. High genus surfaces are mapped to a set of rectangles in the Euclidean plane, and closed genus-zero surfaces are mapped to the sphere. Next, we compute stable geometric features (mean curvature and conformai factor) and pull them back as scalar fields onto the 2D parameter domains. Mutual information is used as a cost functional to drive a fluid flow in the parameter domain that optimally aligns these surface features. A diffeomorphic surface-to-surface mapping is then recovered that matches surfaces in 3D. Lastly, we present a spectral method that ensures that the grids induced on the target surface remain conformal when pulled through the correspondence field. Using the chain rule, we express the gradient of the mutual information between surfaces in the conformal basis of the source surface. This finite-dimensional linear space generates all conformal reparameterizations of the surface. Illustrative experiments apply the method to face recognition and to the registration of brain structures, such as the hippocampus in 3D MRI scans, a key step in understanding brain shape alterations in Alzheimer's disease and schizophrenia.

UR - http://www.scopus.com/inward/record.url?scp=33745934273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745934273&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2005.165

DO - 10.1109/ICCV.2005.165

M3 - Conference contribution

AN - SCOPUS:33745934273

SN - 076952334X

SN - 9780769523347

VL - I

SP - 527

EP - 534

BT - Proceedings of the IEEE International Conference on Computer Vision

ER -