DocumentCode :
2521790
Title :
A system for extracting and representing feature information driven by the application context
Author :
Falcidieno, Bianca ; Giannini, Franca
Author_Institution :
Istituto per la Matematica Applicata, CNR, Genova, Italy
fYear :
1990
fDate :
13-18 May 1990
Firstpage :
1672
Abstract :
The system described works in two steps. The first step starts from a boundary model of an object and identifies the generic shape features by considering only geometric and topological aspects. These features are divided into two general classes, protrusions and depressions, extracted as solid volumes, and arranged in a multilevel structure. This representation, called shape-feature object graph (SFOG), is capable of representing the recursive decomposition of an object in its main shape and the set of its form features (possibly compound). The SFOG is a hierarchical and relational boundary model represented by a graph in which the root component nodes correspond to the boundary representation of the main shape, while the other nodes correspond to the boundary representations of features; arcs between nodes define parent-child relations between components. In the second step, the identified features are classified according to the functional meaning in the application context. Thus, the hierarchical representation is reorganized by gluing and/or grouping sets of shape features which are functionally related in the context considered
Keywords :
graph theory; pattern recognition; picture processing; boundary model; boundary representation; features extraction; features representation; generic shape features; geometric aspects; pattern recognition; picture processing; recursive decomposition; shape-feature object graph; topological aspects; Assembly systems; CADCAM; Computer aided manufacturing; Data mining; Feature extraction; Geometry; Robotic assembly; Shape; Solid modeling; Virtual manufacturing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation, 1990. Proceedings., 1990 IEEE International Conference on
Conference_Location :
Cincinnati, OH
Print_ISBN :
0-8186-9061-5
Type :
conf
DOI :
10.1109/ROBOT.1990.126250
Filename :
126250
Link To Document :
بازگشت