Processor-time optimal parallel algorithms for digitized images on mesh-connected processor arrays

Hussein Alnuweiri, V. K. Prasanna Kumar

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We present processor-time optimal parallel algorithms for several problems on n ×n digitized image arrays, on a mesh-connected array having p processors and a memory of size O(n 2) words. The number of processors p can vary over the range [1, n 3/2] while providing optimal speedup for these problems. The class of image problems considered here includes labeling the connected components of an image; computing the convex hull, the diameter, and a smallest enclosing box of each component; and computing all closest neighbors. Such problems arise in medium-level vision and require global operations on image pixels. To achieve optimal performance, several efficient data-movement and reduction techniques are developed for the proposed organization.

Original languageEnglish
Pages (from-to)698-733
Number of pages36
JournalAlgorithmica
Volume6
Issue number1-6
DOIs
Publication statusPublished - 1 Jun 1991
Externally publishedYes

Fingerprint

Parallel processing systems
Optimal Algorithm
Parallel algorithms
Parallel Algorithms
Labeling
Pixels
Mesh
Data storage equipment
Computing
Connected Components
Convex Hull
Speedup
Pixel
Vary
Range of data

Keywords

  • Digitized image problems
  • Mesh arrays
  • Parallel algorithms
  • Processor-time tradeoffs

ASJC Scopus subject areas

  • Applied Mathematics
  • Safety, Risk, Reliability and Quality
  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Processor-time optimal parallel algorithms for digitized images on mesh-connected processor arrays. / Alnuweiri, Hussein; Prasanna Kumar, V. K.

In: Algorithmica, Vol. 6, No. 1-6, 01.06.1991, p. 698-733.

Research output: Contribution to journalArticle

@article{2274dfcb2a6f4d7ca01194943490a29e,
title = "Processor-time optimal parallel algorithms for digitized images on mesh-connected processor arrays",
abstract = "We present processor-time optimal parallel algorithms for several problems on n ×n digitized image arrays, on a mesh-connected array having p processors and a memory of size O(n 2) words. The number of processors p can vary over the range [1, n 3/2] while providing optimal speedup for these problems. The class of image problems considered here includes labeling the connected components of an image; computing the convex hull, the diameter, and a smallest enclosing box of each component; and computing all closest neighbors. Such problems arise in medium-level vision and require global operations on image pixels. To achieve optimal performance, several efficient data-movement and reduction techniques are developed for the proposed organization.",
keywords = "Digitized image problems, Mesh arrays, Parallel algorithms, Processor-time tradeoffs",
author = "Hussein Alnuweiri and {Prasanna Kumar}, {V. K.}",
year = "1991",
month = "6",
day = "1",
doi = "10.1007/BF01759068",
language = "English",
volume = "6",
pages = "698--733",
journal = "Algorithmica",
issn = "0178-4617",
publisher = "Springer New York",
number = "1-6",

}

TY - JOUR

T1 - Processor-time optimal parallel algorithms for digitized images on mesh-connected processor arrays

AU - Alnuweiri, Hussein

AU - Prasanna Kumar, V. K.

PY - 1991/6/1

Y1 - 1991/6/1

N2 - We present processor-time optimal parallel algorithms for several problems on n ×n digitized image arrays, on a mesh-connected array having p processors and a memory of size O(n 2) words. The number of processors p can vary over the range [1, n 3/2] while providing optimal speedup for these problems. The class of image problems considered here includes labeling the connected components of an image; computing the convex hull, the diameter, and a smallest enclosing box of each component; and computing all closest neighbors. Such problems arise in medium-level vision and require global operations on image pixels. To achieve optimal performance, several efficient data-movement and reduction techniques are developed for the proposed organization.

AB - We present processor-time optimal parallel algorithms for several problems on n ×n digitized image arrays, on a mesh-connected array having p processors and a memory of size O(n 2) words. The number of processors p can vary over the range [1, n 3/2] while providing optimal speedup for these problems. The class of image problems considered here includes labeling the connected components of an image; computing the convex hull, the diameter, and a smallest enclosing box of each component; and computing all closest neighbors. Such problems arise in medium-level vision and require global operations on image pixels. To achieve optimal performance, several efficient data-movement and reduction techniques are developed for the proposed organization.

KW - Digitized image problems

KW - Mesh arrays

KW - Parallel algorithms

KW - Processor-time tradeoffs

UR - http://www.scopus.com/inward/record.url?scp=52449147462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52449147462&partnerID=8YFLogxK

U2 - 10.1007/BF01759068

DO - 10.1007/BF01759068

M3 - Article

VL - 6

SP - 698

EP - 733

JO - Algorithmica

JF - Algorithmica

SN - 0178-4617

IS - 1-6

ER -