Electronic Resource
Springer
Journal of mathematical imaging and vision
4 (1994), S. 69-80
ISSN:
1573-7683
Keywords:
hybrid algorithm
;
attribute maps
;
range images
;
intrinsic surface property
;
segmentation
;
edge points
Source:
Springer Online Journal Archives 1860-2000
Topics:
Mathematics
Notes:
Abstract This paper presents a hybrid algorithm that combines edge detection and region growing approaches to range image segmentation. Edges detected by this method possess good localization properties. This aids in steering the region growing process towards accurate border partitioning. In addition, the incorporation of the region growing process eliminates internal microedges and provides for missing border reconstruction because it is able to detect weak edges. It is believed that the edge and segmentation maps produced may prove to be valuable for CAD-based modeling purposes and may also help to provide a descriptive syntax at the object identification level.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF01250005
Permalink
|
Location |
Call Number |
Expected |
Availability |