DocumentCode :
428553
Title :
λ-connected segmentation and fitting
Author :
Chen, Li ; Adjei, Osei
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., District of Columbia Univ., Washington, DC, USA
Volume :
4
fYear :
2004
fDate :
10-13 Oct. 2004
Firstpage :
3500
Abstract :
This paper presents three new algorithms for λ-connected segmentation and fitting. It deals with a discrete system in which the elements are connected. The connectivity (known as the degree of connectedness) has the property of gradual variation. The first algorithm proposed is a direct segmentation method for quadtree represented images. The algorithm does not decode the original quadtree code to restore the compressed image before segmentation. The second algorithm, called the λ-band-connected search, is designed for noised image segmentation. It reserves a band width for the search agent to surpass, so that the search agent will not stop when it encounters a small noise. The third algorithm adds gradients and smoothes in λ-connected fitting.
Keywords :
graph theory; image segmentation; quadtrees; λ-connected segmentation; compressed image; direct segmentation method; discrete system; noised image segmentation; quadtree represented images; search agent; Algorithm design and analysis; Decoding; Extraterrestrial measurements; Graph theory; Image coding; Image reconstruction; Image segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man and Cybernetics, 2004 IEEE International Conference on
ISSN :
1062-922X
Print_ISBN :
0-7803-8566-7
Type :
conf
DOI :
10.1109/ICSMC.2004.1400884
Filename :
1400884
Link To Document :
بازگشت