Advanced Search
DSpace@MIT

Object recognition with latent Conditional Random Fields

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Michael Collins. en_US
dc.contributor.author Quattoni, Ariadna J en_US
dc.contributor.other Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US
dc.date.accessioned 2006-11-07T11:47:34Z
dc.date.available 2006-11-07T11:47:34Z
dc.date.copyright 2005 en_US
dc.date.issued 2005 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/34358
dc.description Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005. en_US
dc.description Includes bibliographical references (leaves 55-57). en_US
dc.description.abstract In this thesis we present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modelled as flexible constellations of parts conditioned on local observations. For each object class the probability of a given assignment of parts to local features is modelled by a Conditional Random Field (CRF). We propose an extension of the CRF framework that incorporates hidden variables and combines class conditional CRFs into a unified framework for part-based object recognition. The random field captures spatial coherence between region labels. The parameters of the CRF are estimated in a maximum likelihood framework and recognition proceeds by finding the most likely class under our model. The main advantage of the proposed CRF framework is that it allows us to relax the assumption of conditional independence of the observed data (i.e. local features) often used in generative approaches, an assumption that might be too restrictive for a considerable number of object classes. In the second part of this work we extend the detection model and develop a discriminative recognition system which both detects the presence of objects and finds their regions of support in an image. Our part based model allows joint object detection and region labelling; in contrast to previous methods ours can be trained with a combination of examples for which we have labelled support regions and examples for which we only know whether the object is present in the image. en_US
dc.description.abstract (cont.) We extend the detection model by incorporating a segmentation variable; the segmentation variable is assumed to be observed in the fully labelled data and hidden on the partially labelled one. Our latent variable model learns sets of part labels for each image site, which allows us to merge part-based detection with part-based region labelling (or segmentation). en_US
dc.description.statementofresponsibility by Ariadna Quattoni. en_US
dc.format.extent : en_US
dc.format.extent 2437001 bytes
dc.format.extent 2438351 bytes
dc.format.mimetype application/pdf
dc.format.mimetype application/pdf
dc.language.iso eng en_US
dc.publisher Massachusetts Institute of Technology en_US
dc.rights 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. en_US
dc.rights.uri http://dspace.mit.edu/handle/1721.1/7582
dc.subject Electrical Engineering and Computer Science. en_US
dc.title Object recognition with latent Conditional Random Fields en_US
dc.title.alternative Object recognition with latent CRFs en_US
dc.type Thesis en_US
dc.description.degree S.M. en_US
dc.contributor.department Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US
dc.identifier.oclc 70078709 en_US


Files in this item

Name Size Format Description
70078709.pdf 13.67Mb PDF Preview, non-printable (open to all)
70078709-MIT.pdf 13.66Mb PDF Full printable version (MIT only)

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage