Guaranteeing convergence of iterative skewed voting algorithms for image segmentation

Doru C. Balcan, Gowri Srinivasa, Matthew Fickus, Jelena Kovacevic

Research output: Contribution to journalLetter

Abstract

In this paper we provide rigorous proof for the convergence of an iterative voting-based image segmentation algorithm called Active Masks. Active Masks (AM) was proposed to solve the challenging task of delineating punctate patterns of cells from fluorescence microscope images. Each iteration of AM consists of a linear convolution composed with a nonlinear thresholding; what makes this process special in our case is the presence of additive terms whose role is to "skew" the voting when prior information is available. In real-world implementation, the AM algorithm always converges to a fixed point. We study the behavior of AM rigorously and present a proof of this convergence. The key idea is to formulate AM as a generalized (parallel) majority cellular automaton, adapting proof techniques from discrete dynamical systems.

Original languageEnglish (US)
Pages (from-to)300-308
Number of pages9
JournalApplied and Computational Harmonic Analysis
Volume33
Issue number2
DOIs
StatePublished - Jan 1 2012

Fingerprint

Voting
Image segmentation
Image Segmentation
Mask
Masks
Discrete Dynamical Systems
Cellular automata
Prior Information
Thresholding
Convolution
Microscope
Cellular Automata
Fluorescence
Skew
Dynamical systems
Microscopes
Fixed point
Converge
Iteration
Cell

Keywords

  • Active Masks
  • Cellular automata
  • Convergence
  • Segmentation

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

Guaranteeing convergence of iterative skewed voting algorithms for image segmentation. / Balcan, Doru C.; Srinivasa, Gowri; Fickus, Matthew; Kovacevic, Jelena.

In: Applied and Computational Harmonic Analysis, Vol. 33, No. 2, 01.01.2012, p. 300-308.

Research output: Contribution to journalLetter

Balcan, Doru C. ; Srinivasa, Gowri ; Fickus, Matthew ; Kovacevic, Jelena. / Guaranteeing convergence of iterative skewed voting algorithms for image segmentation. In: Applied and Computational Harmonic Analysis. 2012 ; Vol. 33, No. 2. pp. 300-308.
@article{49ac6b93b14d4f47ac4aadd0fc6caceb,
title = "Guaranteeing convergence of iterative skewed voting algorithms for image segmentation",
abstract = "In this paper we provide rigorous proof for the convergence of an iterative voting-based image segmentation algorithm called Active Masks. Active Masks (AM) was proposed to solve the challenging task of delineating punctate patterns of cells from fluorescence microscope images. Each iteration of AM consists of a linear convolution composed with a nonlinear thresholding; what makes this process special in our case is the presence of additive terms whose role is to {"}skew{"} the voting when prior information is available. In real-world implementation, the AM algorithm always converges to a fixed point. We study the behavior of AM rigorously and present a proof of this convergence. The key idea is to formulate AM as a generalized (parallel) majority cellular automaton, adapting proof techniques from discrete dynamical systems.",
keywords = "Active Masks, Cellular automata, Convergence, Segmentation",
author = "Balcan, {Doru C.} and Gowri Srinivasa and Matthew Fickus and Jelena Kovacevic",
year = "2012",
month = "1",
day = "1",
doi = "10.1016/j.acha.2012.03.008",
language = "English (US)",
volume = "33",
pages = "300--308",
journal = "Applied and Computational Harmonic Analysis",
issn = "1063-5203",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Guaranteeing convergence of iterative skewed voting algorithms for image segmentation

AU - Balcan, Doru C.

AU - Srinivasa, Gowri

AU - Fickus, Matthew

AU - Kovacevic, Jelena

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In this paper we provide rigorous proof for the convergence of an iterative voting-based image segmentation algorithm called Active Masks. Active Masks (AM) was proposed to solve the challenging task of delineating punctate patterns of cells from fluorescence microscope images. Each iteration of AM consists of a linear convolution composed with a nonlinear thresholding; what makes this process special in our case is the presence of additive terms whose role is to "skew" the voting when prior information is available. In real-world implementation, the AM algorithm always converges to a fixed point. We study the behavior of AM rigorously and present a proof of this convergence. The key idea is to formulate AM as a generalized (parallel) majority cellular automaton, adapting proof techniques from discrete dynamical systems.

AB - In this paper we provide rigorous proof for the convergence of an iterative voting-based image segmentation algorithm called Active Masks. Active Masks (AM) was proposed to solve the challenging task of delineating punctate patterns of cells from fluorescence microscope images. Each iteration of AM consists of a linear convolution composed with a nonlinear thresholding; what makes this process special in our case is the presence of additive terms whose role is to "skew" the voting when prior information is available. In real-world implementation, the AM algorithm always converges to a fixed point. We study the behavior of AM rigorously and present a proof of this convergence. The key idea is to formulate AM as a generalized (parallel) majority cellular automaton, adapting proof techniques from discrete dynamical systems.

KW - Active Masks

KW - Cellular automata

KW - Convergence

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84865619425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865619425&partnerID=8YFLogxK

U2 - 10.1016/j.acha.2012.03.008

DO - 10.1016/j.acha.2012.03.008

M3 - Letter

VL - 33

SP - 300

EP - 308

JO - Applied and Computational Harmonic Analysis

JF - Applied and Computational Harmonic Analysis

SN - 1063-5203

IS - 2

ER -