Return to search

Model-Based Matching by Linear Combinations of Prototypes

We 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.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7183
Date01 December 1996
CreatorsJones, Michael J., Poggio, Tomaso
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format33 p., 13000011 bytes, 1999501 bytes, application/postscript, application/pdf
RelationAIM-1583, CBCL-139

Page generated in 0.0021 seconds