Oe. Vega et Yh. Yang, DEFAULT SHAPE-THEORY - WITH APPLICATION TO THE COMPUTATION OF THE DIRECTION OF THE LIGHT-SOURCE, CVGIP. Image understanding, 60(3), 1994, pp. 285-299
Citations number
17
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Software Graphycs Programming
Humans appear to have the ability to infer the three-dimensional shape
of an object from its outline or occluding contour. In computer visio
n, an occluding contour is an important clue in the shape recovery pro
cess. So far, only a small family of shapes, in particular, shapes gen
erated by generalized cylinders, and shapes of polyhedrons, has been i
nvestigated in computer vision. However, there are many instances wher
e these types of surfaces are not applicable, e.g., a solid with holes
or a solid with no planar surfaces. This paper proposes a new concept
called the default shape theory which includes the solid of revolutio
n as a special case. A default shape is a function whose domain is a c
losed contour and whose range is a vector representation of a three-di
mensional solid. The application of this new concept to recover the di
rection of the light source is demonstrated in this paper. Experimenta
l results show that the default-shape-based method has comparable perf
ormance as the Pentland light source determination algorithm. This pap
er also proves the relationship between one particular type of default
shape with the solid of revolution. Other possible definitions of def
ault shape are also discussed. (C) 1994 Academic Press, Inc.