DocumentCode :
3316864
Title :
COSMOS-a representation scheme for free-form surfaces
Author :
Dorai, Chitra ; Jain, Anil K.
Author_Institution :
Dept. of Comput. Sci., Michigan State Univ., East Lansing, MI, USA
fYear :
1995
fDate :
20-23 Jun 1995
Firstpage :
1024
Lastpage :
1029
Abstract :
We address the problem of representing and recognizing arbitrarily curved 3D rigid objects when: the objects may vary in shape and complexity, and no restrictive assumptions are made about the types of surfaces on the object. We propose a new and general surface representation scheme for recognizing objects with free form (sculpted) surfaces from range data. In this scheme, an object is described concisely in terms of maximal surface patches of constant shape index. These maximal patches are mapped onto the unit sphere via their orientations, and aggregated via shape spectral functions. Properties such as surface area, curvedness and connectivity that capture local and global information are also built into the representation. The scheme yields not only a meaningful and rich surface description useful for the recoverability of the object, but also a set of powerful indexing primitives for object matching. We demonstrate the generality and the effectiveness of our scheme using real range images of complex objects. We also present results on the categorization of object views based on a novel shape spectral matching technique
Keywords :
computational geometry; image representation; object recognition; COSMOS; arbitrarily curved 3D rigid object recognition; connectivity; constant shape index; curvedness; free form sculpted surfaces; free form surfaces; free-form surfaces; general surface representation scheme; global information; image representation; maximal surface patches; object matching; powerful indexing primitives; real range images; representation scheme; rich surface description; shape spectral functions; shape spectral matching technique; surface area; unit sphere; Aggregates; Computer science; Convergence; Face recognition; Indexing; Noise level; Object detection; Shape measurement; Surface fitting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 1995. Proceedings., Fifth International Conference on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-8186-7042-8
Type :
conf
DOI :
10.1109/ICCV.1995.466822
Filename :
466822
Link To Document :
بازگشت