2026-09-19T00:18:05Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/321002022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Tomaso Poggio. Martin, Ian Stefan Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2006-03-28T19:51:29Z 2006-03-28T19:51:29Z 2005 2005 http://hdl.handle.net/1721.1/32100 62277937 Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005. 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. 85-91). This thesis demonstrates methods useful in learning to understand images from only a few examples, but they are by no means limited to this application. Boosting techniques are popular because they learn effective classification functions and identify the most relevant features at the same time. However, in general, they overfit and perform poorly on data sets that contain many features, but few examples. A novel stochastic regularization technique is presented, based on enhancing data sets with corrupted copies of the examples to produce a more robust classifier. This regularization technique enables the gentle boosting algorithm to work well with only a few examples. It is tested on a variety of data sets from various domains, including object recognition and bioinformatics, with convincing results. In the second part of this work, a novel technique for extracting texture edges is introduced, based on the combination of a patch-based approach, and non-param8tric tests of distributions. This technique can reliably detect texture edges using only local information, making it a useful preprocessing step prior to segmentation. Combined with a parametric deformable model, this technique provides smooth boundaries and globally salient structures. by Ian Stefan Martin. M.Eng. 91 p. 2143504 bytes 2139513 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. Robust learning and segmentation for secure understanding Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="5d7d2162-bb5f-4bab-9c37-c679e2279bb1"> <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>Robust learning and segmentation for secure understanding</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2005</PublicationDate> <Authors> <Author> <DisplayName>Martin, Ian Stefan</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>This thesis demonstrates methods useful in learning to understand images from only a few examples, but they are by no means limited to this application. Boosting techniques are popular because they learn effective classification functions and identify the most relevant features at the same time. However, in general, they overfit and perform poorly on data sets that contain many features, but few examples. A novel stochastic regularization technique is presented, based on enhancing data sets with corrupted copies of the examples to produce a more robust classifier. This regularization technique enables the gentle boosting algorithm to work well with only a few examples. It is tested on a variety of data sets from various domains, including object recognition and bioinformatics, with convincing results. In the second part of this work, a novel technique for extracting texture edges is introduced, based on the combination of a patch-based approach, and non-param8tric tests of distributions. This technique can reliably detect texture edges using only local information, making it a useful preprocessing step prior to segmentation. Combined with a parametric deformable model, this technique provides smooth boundaries and globally salient structures.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>