Search results for key=Sta1998 : 1 match found.

Ph.D. Theses

1998

@phdthesis{Sta1998,
	vgclass =	{thesis},
	vgproject =	{cbir,invariance},
	author =	{Sergei Startchik},
	title =	{Geometric and Illumination Invariant Object
	Representation: Application to Content-based Image Retrieval},
	type =	{{P}h.{D}. {D}issertation {N}o. 3009},
	school =	{University of Geneva},
	address =	{Switzerland},
	month =	{July},
	year =	{1998},
	url =	{http://cuiwww.unige.ch/\~startchi/PhD/},
	abstract =	{This work addresses several issues in the field of
	computer vision. In particular, attention is focussed on the problem of
	the representation of an object from its appearance in an image.
	Several advances are proposed for the representation of planar shapes,
	which are thus suitable for representing planar and faceted objects.
	The representation developed is employed for content-based retrieval
	from an image database. 

	The proposed projectively invariant description for groups of planar
	disjoint contours as a simultaneous polar reparametrization of multiple
	curves. Its origin is an invariant point and, for each ray orientation,
	the cross-ratio of the intersections with the closest curves gives the
	radius.  The sequence of cross-ratio values for all orientations forms
	a signature.  With respect to other methods, this representation is
	less reliant on individual curve properties, both for the construction
	of the reference frame and for the calculation of the signature. At the
	same time, this representation is local and integrates information from
	multiple curves, guaranteeing robustness to curve discontinuities and
	partial occlusions.  Chromatic information is introduced into the
	representation and offers two advantages. First, the representation
	provides a more complete description of the shape and thus becomes more
	discriminative. Secondly, the chromatic description is illumination
	invariant under a diagonal chromaticity model and one more acquisition
	variable is therefore removed. The proposed representation was
	originally developed for planar shapes, but an extension has been
	proposed and validated for trihedral corners. [truncated]},
}