2026-09-18T21:12:23Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/346392022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Frédo Durand.
Bae, Soonmin
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2006-11-07T16:43:32Z
2006-11-07T16:43:32Z
2005
2005
http://hdl.handle.net/1721.1/34639
70081070
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005.
Includes bibliographical references (p. 96-103).
We show that image statistics can be used to analyze and transfer simple notions of pictorial style of paintings and photographs. We characterize the frequency content of pictorial styles, such as multi-scale, spatial variations, and anisotropy properties, using a multi-scale and oriented decomposition, the steerable pyramid. We show that the average of the absolute steerable coefficients as a function of scale characterizes simple notions of "look" or style. We extend this approach to account for image non-stationarity, that is, we capture and transfer the spatial variations of multi-scale content. In addition, we measure the standard deviation of the steerable coefficients across orientation, which characterizes image anisotropy and permits analysis and transfer of oriented structures. We focus on the statistical features that can be transferred. Since we couple analysis and transfer, our statistical model and transfer tools are consistent with the visual effect of pictorial styles. For this reason, our technique leads to more intuitive manipulation and interpolation of pictorial styles. In addition, our statistical model can be used to classify and retrieve images by style.
by Soonmin Bae.
S.M.
103 p.
5799741 bytes
5805362 bytes
application/pdf
application/pdf
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.
Statistical analysis and transfer of coarse-grain pictorial style
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="9ad66968-ee53-420f-b4dd-92f37721df9e">
<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>Statistical analysis and transfer of coarse-grain pictorial style</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2005</PublicationDate>
<Authors>
<Author>
<DisplayName>Bae, Soonmin</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 show that image statistics can be used to analyze and transfer simple notions of pictorial style of paintings and photographs. We characterize the frequency content of pictorial styles, such as multi-scale, spatial variations, and anisotropy properties, using a multi-scale and oriented decomposition, the steerable pyramid. We show that the average of the absolute steerable coefficients as a function of scale characterizes simple notions of "look" or style. We extend this approach to account for image non-stationarity, that is, we capture and transfer the spatial variations of multi-scale content. In addition, we measure the standard deviation of the steerable coefficients across orientation, which characterizes image anisotropy and permits analysis and transfer of oriented structures. We focus on the statistical features that can be transferred. Since we couple analysis and transfer, our statistical model and transfer tools are consistent with the visual effect of pictorial styles. For this reason, our technique leads to more intuitive manipulation and interpolation of pictorial styles. In addition, our statistical model can be used to classify and retrieve images by style.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>