The quotient image: class-based re-rendering and recognition withvarying illuminations
Shashua, A.
Riklin-Raviv, T.
Dept. of Comput. Sci., Hebrew Univ., Jerusalem ;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Feb 2001
Volume: 23,
Issue: 2
On page(s): 129-139
ISSN: 0162-8828
References Cited: 27
CODEN: ITPIDJ
INSPEC Accession Number: 6927554
Digital Object Identifier: 10.1109/34.908964
Current Version Published: 2002-08-07
Abstract
The paper addresses the problem of “class-based”
image-based recognition and rendering with varying illumination. The
rendering problem is defined as follows: Given a single input image of
an object and a sample of images with varying illumination conditions of
other objects of the same general class, re-render the input image to
simulate new illumination conditions. The class-based recognition
problem is similarly defined: Given a single image of an object in a
database of images of other objects, some of them multiply sampled under
varying illumination, identify (match) any novel image of that object
under varying illumination with the single image of that object in the
database. We focus on Lambertian surface classes and, in particular, the
class of human faces. The key result in our approach is based on a
definition of an illumination invariant signature image which enables an
analytic generation of the image space with varying illumination. We
show that a small database of objects-in our experiments as few as two
objects-is sufficient for generating the image space with varying
illumination of any new object of the class from a single input image of
that object. In many cases, the recognition results outperform by far
conventional methods and the re-rendering is of remarkable quality
considering the size of the database of example images and the mild
preprocess required for making the algorithm work
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
