Model-Based Matching by Linear Combinations of Prototypes
Name
AIM-1583.pdf
Size
1.91 MB
Format
Adobe PDF
Checksum (MD5)
97fc462e5b71c6bb41bdb2d20cddbb12
Name
AIM-1583.ps
Size
12.4 MB
Format
PostScript
Checksum (MD5)
6ca01a4f4b27087408aeaaab42fbfb15
Author(s)
Jones, Michael J.
Poggio, Tomaso
Date Issued
December 1, 1996
Series/Report no.
AIM-1583
CBCL-139
Abstract
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.
Subjects
AI
MIT
Artificial Intelligence
Computer Vision
Image Correspondence
Deformable Templates
Object Recognition
Persistent DSpace Link
