An unsupervised algorithm for detecting good continuation in dot patterns

José LEZAMA; Gregory RANDALL; Jean-Michel MOREL; Rafael GROMPONE VON GIOI

doi:10.5201/ipol.2017.176

An unsupervised algorithm for detecting good continuation in dot patterns

José LEZAMA, Gregory RANDALL, Jean-Michel MOREL, Rafael GROMPONE VON GIOI

Research output: Journal Publications › Journal Article (refereed) › peer-review

4 Citations (Scopus)

Abstract

In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of ‘good continuation’ of points in 2D point patterns. The algorithm is based on the ‘a contrario’ detection theory and on the assumption that ‘good continuation’ of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections.

Original language	English
Pages (from-to)	81-92
Number of pages	12
Journal	Image Processing On Line
Volume	7
Early online date	24 Apr 2017
DOIs	https://doi.org/10.5201/ipol.2017.176
Publication status	Published - 2017
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2017 IPOL & the authors CC–BY–NC–SA.

Keywords

Dots
Gestalt
Good continuation
Local symmetry
Non-accidentalness

Access to Document

10.5201/ipol.2017.176Licence: CC BY-NC-SA

Cite this

@article{fc6f505388c146d6aa12b7bf91a2eb8e,

title = "An unsupervised algorithm for detecting good continuation in dot patterns",

abstract = "In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of {\textquoteleft}good continuation{\textquoteright} of points in 2D point patterns. The algorithm is based on the {\textquoteleft}a contrario{\textquoteright} detection theory and on the assumption that {\textquoteleft}good continuation{\textquoteright} of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections.",

keywords = "Dots, Gestalt, Good continuation, Local symmetry, Non-accidentalness",

author = "Jos{\'e} LEZAMA and Gregory RANDALL and Jean-Michel MOREL and \{GROMPONE VON GIOI\}, Rafael",

note = "Publisher Copyright: {\textcopyright} 2017 IPOL \& the authors CC–BY–NC–SA.",

year = "2017",

doi = "10.5201/ipol.2017.176",

language = "English",

volume = "7",

pages = "81--92",

journal = "Image Processing On Line",

issn = "2105-1232",

publisher = "Image Processing on Line",

}

TY - JOUR

T1 - An unsupervised algorithm for detecting good continuation in dot patterns

AU - LEZAMA, José

AU - RANDALL, Gregory

AU - MOREL, Jean-Michel

AU - GROMPONE VON GIOI, Rafael

PY - 2017

Y1 - 2017

N2 - In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of ‘good continuation’ of points in 2D point patterns. The algorithm is based on the ‘a contrario’ detection theory and on the assumption that ‘good continuation’ of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections.

AB - In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of ‘good continuation’ of points in 2D point patterns. The algorithm is based on the ‘a contrario’ detection theory and on the assumption that ‘good continuation’ of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections.

KW - Dots

KW - Gestalt

KW - Good continuation

KW - Local symmetry

KW - Non-accidentalness

UR - https://www.scopus.com/pages/publications/85025603743

U2 - 10.5201/ipol.2017.176

DO - 10.5201/ipol.2017.176

M3 - Journal Article (refereed)

AN - SCOPUS:85025603743

SN - 2105-1232

VL - 7

SP - 81

EP - 92

JO - Image Processing On Line

JF - Image Processing On Line

ER -

An unsupervised algorithm for detecting good continuation in dot patterns

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this