Show simple item record

dc.contributor.authorJones, Michael J.en_US
dc.contributor.authorPoggio, Tomasoen_US
dc.date.accessioned2004-10-20T20:49:06Z
dc.date.available2004-10-20T20:49:06Z
dc.date.issued1996-12-01en_US
dc.identifier.otherAIM-1583en_US
dc.identifier.otherCBCL-139en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/7183
dc.description.abstractWe describe a method for modeling object classes (such as faces) using 2D example images and an algorithm for matching a model to a novel image. The object class models are "learned'' from example images that we call prototypes. In addition to the images, the pixelwise correspondences between a reference prototype and each of the other prototypes must also be provided. Thus a model consists of a linear combination of prototypical shapes and textures. A stochastic gradient descent algorithm is used to match a model to a novel image by minimizing the error between the model and the novel image. Example models are shown as well as example matches to novel images. The robustness of the matching algorithm is also evaluated. The technique can be used for a number of applications including the computation of correspondence between novel images of a certain known class, object recognition, image synthesis and image compression.en_US
dc.format.extent33 p.en_US
dc.format.extent13000011 bytes
dc.format.extent1999501 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesAIM-1583en_US
dc.relation.ispartofseriesCBCL-139en_US
dc.subjectAIen_US
dc.subjectMITen_US
dc.subjectArtificial Intelligenceen_US
dc.subjectComputer Visionen_US
dc.subjectImage Correspondenceen_US
dc.subjectDeformable Templatesen_US
dc.subjectObject Recognitionen_US
dc.titleModel-Based Matching by Linear Combinations of Prototypesen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record