The quotient image: Class based recognition and synthesis undervarying illumination conditions
Riklin-Raviv, T.
Shashua, A.
Inst. of Comput. Sci., Hebrew Univ., Jerusalem ;
This paper appears in: Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.
Publication Date: 1999
Volume: 2,
On page(s): -571 Vol. 2
Meeting Date: 06/23/1999 - 06/25/1999
Location: Fort Collins, CO, USA
ISBN: 0-7695-0149-4
References Cited: 16
INSPEC Accession Number: 6338807
Digital Object Identifier: 10.1109/CVPR.1999.784968
Current Version Published: 2002-08-06
Abstract
The paper addresses the problem of “class-based”
recognition and image-synthesis with varying illumination. The
class-based synthesis and recognition tasks are 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, capture the equivalence relationship (by generation of new images
or by invariants) among all images of the object corresponding to new
illumination conditions. The key result in our approach is based on a
definition of an illumination invariant signature image, we call the
“quotient” image, which enables an analytic generation of
the image space with varying illumination from a single input image and
a very small sample of other objects of the class-in our experiments as
few as two objects. In many cases the recognition results outperform by
far conventional methods and the image-synthesis is of remarkable
quality considering the size of the database of example images and the
mild pre-process 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
