Distance transform algorithm for bit-serial SIMD architectures

Jouko Viitanen, Jarmo Takala

Research output: Contribution to journalArticleScientificpeer-review

7 Citations (Scopus)

Abstract

A distance transform converts a binary image consisting of foreground (feature) and background (nonfeature) elements into a gray level image, where each element contains the distance from the corresponding element to the nearest foreground element. The calculation of exact Euclidean distance transform is a computationally intensive task and, therefore, approximations are often utilized. These algorithms are typically iterative or require several passes to complete the transform. In this paper, a novel parallel single-pass algorithm for the calculation of constrained distance transform is presented. The algorithm can be implemented by utilizing only bit-wise logical operations; thus, it is well suited for low-cost bit-serial SIMD architectures or conventional uniprocessors with a large word width, where the SIMD operation is emulated. Implementations on a parallel SIMD architecture and a sequential architecture are described. Comparisons are provided, showing results of the implementations of the presented algorithm, a sequential local algorithm utilizing integer approximated distances and an algorithm utilizing exact Euclidean distances.
Original languageEnglish
Pages (from-to)150-161
Number of pages12
JournalComputer Vision and Image Understanding
Volume74
Issue number2
DOIs
Publication statusPublished - 1999
MoE publication typeA1 Journal article-refereed

Fingerprint

Parallel architectures
Binary images
Costs

Cite this

Viitanen, Jouko ; Takala, Jarmo. / Distance transform algorithm for bit-serial SIMD architectures. In: Computer Vision and Image Understanding. 1999 ; Vol. 74, No. 2. pp. 150-161.
@article{788da9a0b1f8456fa4176ba12f58f472,
title = "Distance transform algorithm for bit-serial SIMD architectures",
abstract = "A distance transform converts a binary image consisting of foreground (feature) and background (nonfeature) elements into a gray level image, where each element contains the distance from the corresponding element to the nearest foreground element. The calculation of exact Euclidean distance transform is a computationally intensive task and, therefore, approximations are often utilized. These algorithms are typically iterative or require several passes to complete the transform. In this paper, a novel parallel single-pass algorithm for the calculation of constrained distance transform is presented. The algorithm can be implemented by utilizing only bit-wise logical operations; thus, it is well suited for low-cost bit-serial SIMD architectures or conventional uniprocessors with a large word width, where the SIMD operation is emulated. Implementations on a parallel SIMD architecture and a sequential architecture are described. Comparisons are provided, showing results of the implementations of the presented algorithm, a sequential local algorithm utilizing integer approximated distances and an algorithm utilizing exact Euclidean distances.",
author = "Jouko Viitanen and Jarmo Takala",
year = "1999",
doi = "10.1006/cviu.1999.0756",
language = "English",
volume = "74",
pages = "150--161",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press",
number = "2",

}

Distance transform algorithm for bit-serial SIMD architectures. / Viitanen, Jouko; Takala, Jarmo.

In: Computer Vision and Image Understanding, Vol. 74, No. 2, 1999, p. 150-161.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Distance transform algorithm for bit-serial SIMD architectures

AU - Viitanen, Jouko

AU - Takala, Jarmo

PY - 1999

Y1 - 1999

N2 - A distance transform converts a binary image consisting of foreground (feature) and background (nonfeature) elements into a gray level image, where each element contains the distance from the corresponding element to the nearest foreground element. The calculation of exact Euclidean distance transform is a computationally intensive task and, therefore, approximations are often utilized. These algorithms are typically iterative or require several passes to complete the transform. In this paper, a novel parallel single-pass algorithm for the calculation of constrained distance transform is presented. The algorithm can be implemented by utilizing only bit-wise logical operations; thus, it is well suited for low-cost bit-serial SIMD architectures or conventional uniprocessors with a large word width, where the SIMD operation is emulated. Implementations on a parallel SIMD architecture and a sequential architecture are described. Comparisons are provided, showing results of the implementations of the presented algorithm, a sequential local algorithm utilizing integer approximated distances and an algorithm utilizing exact Euclidean distances.

AB - A distance transform converts a binary image consisting of foreground (feature) and background (nonfeature) elements into a gray level image, where each element contains the distance from the corresponding element to the nearest foreground element. The calculation of exact Euclidean distance transform is a computationally intensive task and, therefore, approximations are often utilized. These algorithms are typically iterative or require several passes to complete the transform. In this paper, a novel parallel single-pass algorithm for the calculation of constrained distance transform is presented. The algorithm can be implemented by utilizing only bit-wise logical operations; thus, it is well suited for low-cost bit-serial SIMD architectures or conventional uniprocessors with a large word width, where the SIMD operation is emulated. Implementations on a parallel SIMD architecture and a sequential architecture are described. Comparisons are provided, showing results of the implementations of the presented algorithm, a sequential local algorithm utilizing integer approximated distances and an algorithm utilizing exact Euclidean distances.

U2 - 10.1006/cviu.1999.0756

DO - 10.1006/cviu.1999.0756

M3 - Article

VL - 74

SP - 150

EP - 161

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 2

ER -