{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/42279"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/42279","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Epitome and its applications","abstract":"Due to the lack of explicit spatial consideration, the existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this thesis. Extended from the original simple graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, a new EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance based on patches and automatically cluster the spatial distribution of the similar patches. From the spatialized epitome, we present a principled (parameter-free) way of inferring the probability of a new input image under the learned model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome’s ability for discrimination on several tough vision tasks, e.g., misalignment/cross-pose face recognition, and vehicle detection with a few training samples. We also apply this model to image colorization which not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous methods.","abstract_html":"Due to the lack of explicit spatial consideration, the existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this thesis. Extended from the original simple graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, a new EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance based on patches and automatically cluster the spatial distribution of the similar patches. From the spatialized epitome, we present a principled (parameter-free) way of inferring the probability of a new input image under the learned model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome’s ability for discrimination on several tough vision tasks, e.g., misalignment/cross-pose face recognition, and vehicle detection with a few training samples. We also apply this model to image colorization which not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous methods.","abstract_has_math":false,"creators":["Chu, Xinqi"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Huang, Thomas S."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2013,"date_issued":"2013-02-03T19:30:08Z","date_published":"2013-02-03T19:30:08Z","updated_at":"2026-07-22T22:25:33Z","subjects":["colorization","probabilistic graphical models","image synthesis","recognition"],"languages":["en"],"rights":["Copyright 2012 Xinqi Chu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/42279","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huang, Thomas S."]},{"key":"dc:creator","label":"Author","values":["Chu, Xinqi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2013-02-03T19:30:08Z","2012-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["colorization","probabilistic graphical models","image synthesis","recognition"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2012 Xinqi Chu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/42279"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Due to the lack of explicit spatial consideration, the existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this thesis. Extended from the original simple graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, a new EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance based on patches and automatically cluster the spatial distribution of the similar patches. From the spatialized epitome, we present a principled (parameter-free) way of inferring the probability of a new input image under the learned model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome’s ability for discrimination on several tough vision tasks, e.g., misalignment/cross-pose face recognition, and vehicle detection with a few training samples. We also apply this model to image colorization which not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous methods.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-12-12T22:03:11Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 msthesis_Xinqi.pdf: 2881929 bytes, checksum: 7a24e11887f5cbd8617fe732b7c388e1 (MD5)","Made available in DSpace on 2013-02-03T19:30:08Z (GMT). No. of bitstreams: 2 Xinqi_Chu.pdf: 2881929 bytes, checksum: 7a24e11887f5cbd8617fe732b7c388e1 (MD5) license.txt: 4056 bytes, checksum: 7b987d5d20259b7fc16331313cb5e12b (MD5)"]},{"key":"dc:title","label":"Title","values":["Epitome and its applications"]}]}],"canonical_facts":{"dc:contributor":["Huang, Thomas S."],"dc:creator":["Chu, Xinqi"],"dc:date":["2013-02-03T19:30:08Z","2012-12"],"dc:description":["Due to the lack of explicit spatial consideration, the existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this thesis. Extended from the original simple graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, a new EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance based on patches and automatically cluster the spatial distribution of the similar patches. From the spatialized epitome, we present a principled (parameter-free) way of inferring the probability of a new input image under the learned model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome’s ability for discrimination on several tough vision tasks, e.g., misalignment/cross-pose face recognition, and vehicle detection with a few training samples. We also apply this model to image colorization which not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous methods.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2012-12-12T22:03:11Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 msthesis_Xinqi.pdf: 2881929 bytes, checksum: 7a24e11887f5cbd8617fe732b7c388e1 (MD5)","Made available in DSpace on 2013-02-03T19:30:08Z (GMT). No. of bitstreams: 2 Xinqi_Chu.pdf: 2881929 bytes, checksum: 7a24e11887f5cbd8617fe732b7c388e1 (MD5) license.txt: 4056 bytes, checksum: 7b987d5d20259b7fc16331313cb5e12b (MD5)"],"dc:identifier":["http://hdl.handle.net/2142/42279"],"dc:language":["en"],"dc:rights":["Copyright 2012 Xinqi Chu"],"dc:subject":["colorization","probabilistic graphical models","image synthesis","recognition"],"dc:title":["Epitome and its applications"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:33Z"}