2026-09-19T13:45:30Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/531582022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Sai Ravela.
Yang, Christopher Minzer
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2010-03-25T15:08:26Z
2010-03-25T15:08:26Z
2009
2009
http://hdl.handle.net/1721.1/53158
505629587
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2009.
Includes bibliographical references (p. 55-57).
We present a new approach to deformation invariant image matching. Our approach retains the broad range of linear and nonlinear deformations that viscous alignment methods can model, but introduces a selectivity that is necessary for recognition. Our method models viscous kernels with an over-complete filter basis. The basis is parameterized with a single scalar parameter, the spectral radius r, which selects deformations ranging in complexity from tranlations to "turbulence." The spectral radius is used for cascaded alignment starting from low deformation frequencies and finishing with high deformation frequencies. Cascaded alignment makes deformation invariant matching for recognition feasible and efficient. Because spectral radii map directly to deformation complexity, their contributions are selectively weighed to calculate the template-target similarity. In this way, our model can distinguish deformations by their relevance to recognition, without losing the flexibility of viscous alignment for handling nonlinear deformations. Our approach is applied to recognize flexible bodies of animals, and results indicate that the method is very promising.
by Christopher Minzer Yang.
M.Eng.
57 p.
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Spectral control of viscous alignment for deformation invariant image matching
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="cc68d201-2b0f-4a64-ac95-1348357ccba2">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Spectral control of viscous alignment for deformation invariant image matching</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2009</PublicationDate>
<Authors>
<Author>
<DisplayName>Yang, Christopher Minzer</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>We present a new approach to deformation invariant image matching. Our approach retains the broad range of linear and nonlinear deformations that viscous alignment methods can model, but introduces a selectivity that is necessary for recognition. Our method models viscous kernels with an over-complete filter basis. The basis is parameterized with a single scalar parameter, the spectral radius r, which selects deformations ranging in complexity from tranlations to "turbulence." The spectral radius is used for cascaded alignment starting from low deformation frequencies and finishing with high deformation frequencies. Cascaded alignment makes deformation invariant matching for recognition feasible and efficient. Because spectral radii map directly to deformation complexity, their contributions are selectively weighed to calculate the template-target similarity. In this way, our model can distinguish deformations by their relevance to recognition, without losing the flexibility of viscous alignment for handling nonlinear deformations. Our approach is applied to recognize flexible bodies of animals, and results indicate that the method is very promising.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>