Recognition by linear combinations of models
Ullman, S.
Basri, R.
Dept. of Brain & Cognitive Sci., MIT, Cambridge, MA;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Oct 1991
Volume: 13,
Issue: 10
On page(s): 992-1006
ISSN: 0162-8828
References Cited: 26
CODEN: ITPIDJ
INSPEC Accession Number: 4084150
Digital Object Identifier: 10.1109/34.99234
Current Version Published: 2002-08-06
Abstract
An approach to visual object recognition in which a 3D object is
represented by the linear combination of 2D images of the object is
proposed. It is shown that for objects with sharp edges as well as with
smooth bounding contours, the set of possible images of a given object
is embedded in a linear space spanned by a small number of views. For
objects with sharp edges, the linear combination representation is
exact. For objects with smooth boundaries, it is an approximation that
often holds over a wide range of viewing angles. Rigid transformations
(with or without scaling) can be distinguished from more general linear
transformations of the object by testing certain constraints placed on
the coefficients of the linear combinations. Three alternative methods
of determining the transformation that matches a model to a given image
are proposed
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
