Implementation of some image thresholding algorithms on a connection machine-200

On serial computers, global segmentation methods are preferred to local methods due to their lower CPU time requirements. However, due to the increased availability of parallel machines, if local segmentation algorithms are efficiently parallelizable then they are also equally preferable. In this le...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters 1995, Vol.16 (7), p.759-768
Main Author: Venkateswarlu, N.B.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Complexity
Computer science
control theory
systems
Exact sciences and technology
Local algorithms
Parallel
Pattern recognition. Digital image processing. Computational geometry
Segmentation
Serial
Speed-up
Thresholding
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:On serial computers, global segmentation methods are preferred to local methods due to their lower CPU time requirements. However, due to the increased availability of parallel machines, if local segmentation algorithms are efficiently parallelizable then they are also equally preferable. In this letter, we have implemented some widely used image thresholding algorithms on a Connection Machine-200 to know their parallel complexity. Compared to global methods, local methods are observed to be efficiently parallelizable.
ISSN:0167-8655
1872-7344
DOI:10.1016/0167-8655(95)00020-H