2026-09-19T08:18:54Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/456372022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Trevor J. Darrell. Lee, John Jaesung Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2009-06-25T20:37:01Z 2009-06-25T20:37:01Z 2008 2008 http://hdl.handle.net/1721.1/45637 367590769 Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Includes bibliographical references (p. 91-93). Algorithms for recognition and retrieval tasks generally call for both speed and accuracy. When scaling up to very large applications, however, we encounter additional significant requirements: adaptability and scalability. In many real-world systems, large numbers of images are constantly added to the database, requiring the algorithm to quickly tune itself to recent trends so it can serve queries more effectively. Moreover, the systems need to be able to meet the demands of simultaneous queries from many users. In this thesis, I describe two new algorithms intended to meet these requirements and give an extensive experimental evaluation for both. The first algorithm constructs an adaptive vocabulary forest, which is an efficient image-database model that grows and shrinks as needed while adapting its structure to tune itself to recent trends. The second algorithm is a method for efficiently performing classification tasks by comparing query images to only a fixed number of training examples, regardless of the size of the image database. These two methods can be combined to create a fast, adaptable, and scalable vision system suitable for large-scale applications. I also introduce LIBPMK, a fast implementation of common computer vision processing pipelines such as that of the pyramid match kernel. This implementation was used to build several successful interactive applications as well as batch experiments for research settings. This implementation, in addition to the two new algorithms introduced by this thesis, are a step toward meeting the speed, adaptability, and scalability requirements of practical large-scale vision systems. by John Jaesung Lee. M.Eng. 93 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. Efficient object recognition and image retrieval for large-scale applications Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="bff577d9-1eb8-4a47-a4bb-d7b700e0ad64"> <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>Efficient object recognition and image retrieval for large-scale applications</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2008</PublicationDate> <Authors> <Author> <DisplayName>Lee, John Jaesung</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>Algorithms for recognition and retrieval tasks generally call for both speed and accuracy. When scaling up to very large applications, however, we encounter additional significant requirements: adaptability and scalability. In many real-world systems, large numbers of images are constantly added to the database, requiring the algorithm to quickly tune itself to recent trends so it can serve queries more effectively. Moreover, the systems need to be able to meet the demands of simultaneous queries from many users. In this thesis, I describe two new algorithms intended to meet these requirements and give an extensive experimental evaluation for both. The first algorithm constructs an adaptive vocabulary forest, which is an efficient image-database model that grows and shrinks as needed while adapting its structure to tune itself to recent trends. The second algorithm is a method for efficiently performing classification tasks by comparing query images to only a fixed number of training examples, regardless of the size of the image database. These two methods can be combined to create a fast, adaptable, and scalable vision system suitable for large-scale applications. I also introduce LIBPMK, a fast implementation of common computer vision processing pipelines such as that of the pyramid match kernel. This implementation was used to build several successful interactive applications as well as batch experiments for research settings. This implementation, in addition to the two new algorithms introduced by this thesis, are a step toward meeting the speed, adaptability, and scalability requirements of practical large-scale vision systems.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>