Deformation invariant image matching by spectrally controlled diffeomorphic alignment
Name
Yang-2009-Deformation invariant image matching by spectrally controlled diffeomorphic alignment.pdf
Size
2.48 MB
Format
Adobe PDF
Checksum (MD5)
58d33823ffd7180566343c4eb8eede46
Author(s)
Yang, Christopher M.
Ravela, Sai
Date Issued
May 2010
Journal
Proceedings of the IEEE Conference on Computer Vision (ICCV), 2009
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Ravela, Srinivas and Christopher M. Yang. "Deformation Invariant Image Matching by Spectrally Controlled Diffeomorphic Alignment." Proceedings of the 2009 IEEE Conference on Computer Vision (ICCV): 1303-1310. © 2009 IEEE.
Version
Final published version
Abstract
We present a new approach to deformation invariant image matching. Our matcher (a) aligns templates to targets over a broad range of nonlinear deformations, (b) factors the total deformation into spectral categories, where low wavenumber deformations are smooth and global and high wavenumbers are turbulent and local, and (c) weighs the reduction in template-target misfit within each category to differentiate between relevant and irrelevant deformations. It accomplishes this by aligning images in a scale-cascaded fashion, with more complex, local deformations following simpler, more global ones. Each step of the cascade involves finding an iterative solution to a nonlinear optimization problem using a Gabor deformation basis. Cascaded alignment makes deformation invariant matching feasible and efficient. Our approach is applied to recognize the flexible bodies of salamanders from a large database; results indicate that the method is very promising.
MIT Department
Massachusetts Institute of Technology. Department of Earth, Atmospheric, and Planetary Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/ICCV.2009.5459315
