Stable Image Descriptions Using Gestalt Principles

Yi Zhe Song, Peter M Hall

Research output: Chapter in Book/Report/Conference proceedingChapter

  • 2 Citations

Abstract

This paper addresses the problem of grouping image primitives; its principal contribution is an explicit definition of the Gestalt principle of Pragnanz, which organizes primitives into descriptions of images that are both simple and stable. Our definition of Pragnanz assumes just two things: that a vector of free variables controls some general grouping algorithm, and a scalar function measures the information in a grouping. Stable descriptions exist where the gradient of the function is zero; and these can be ordered by information content (simplicity) to create a "grouping" or "Gestalt" scale description. We provide a simple measure for information in a grouping based on its structure alone, leaving our grouper free to exploit other Gestalt principles as we see fit. We demonstrate the value of our definition of Pragnanz on several real-world images.
LanguageEnglish
Title of host publicationAdvances in Visual Computing. ISVC 2008 Proceedings, Part I
EditorsG Bebis
Place of PublicationBerlin
PublisherSpringer
Pages318-327
Number of pages10
ISBN (Electronic)978-3-540-89639-5
ISBN (Print)978-3-540-89638-8
DOIs
StatusPublished - 2008
Event4th International Symposium on Visual Computing: ISVC 2008: Advances in Visual Computing - Las Vegas, USA United States
Duration: 1 Dec 20083 Dec 2008

Publication series

NameLecture Notes in Computer Science
PublisherSpringer-Verlag

Conference

Conference4th International Symposium on Visual Computing
Abbreviated titleISVC 2008
CountryUSA United States
CityLas Vegas
Period1/12/083/12/08

Cite this

Song, Y. Z., & Hall, P. M. (2008). Stable Image Descriptions Using Gestalt Principles. In G. Bebis (Ed.), Advances in Visual Computing. ISVC 2008 Proceedings, Part I (pp. 318-327). (Lecture Notes in Computer Science). Berlin: Springer. DOI: 10.1007/978-3-540-89639-5_31

Stable Image Descriptions Using Gestalt Principles. / Song, Yi Zhe; Hall, Peter M.

Advances in Visual Computing. ISVC 2008 Proceedings, Part I. ed. / G Bebis. Berlin : Springer, 2008. p. 318-327 (Lecture Notes in Computer Science).

Research output: Chapter in Book/Report/Conference proceedingChapter

Song, YZ & Hall, PM 2008, Stable Image Descriptions Using Gestalt Principles. in G Bebis (ed.), Advances in Visual Computing. ISVC 2008 Proceedings, Part I. Lecture Notes in Computer Science, Springer, Berlin, pp. 318-327, 4th International Symposium on Visual Computing, Las Vegas, USA United States, 1/12/08. DOI: 10.1007/978-3-540-89639-5_31
Song YZ, Hall PM. Stable Image Descriptions Using Gestalt Principles. In Bebis G, editor, Advances in Visual Computing. ISVC 2008 Proceedings, Part I. Berlin: Springer. 2008. p. 318-327. (Lecture Notes in Computer Science). Available from, DOI: 10.1007/978-3-540-89639-5_31
Song, Yi Zhe ; Hall, Peter M. / Stable Image Descriptions Using Gestalt Principles. Advances in Visual Computing. ISVC 2008 Proceedings, Part I. editor / G Bebis. Berlin : Springer, 2008. pp. 318-327 (Lecture Notes in Computer Science).
@inbook{43656db653d54d15a6dca879840a41dd,
title = "Stable Image Descriptions Using Gestalt Principles",
abstract = "This paper addresses the problem of grouping image primitives; its principal contribution is an explicit definition of the Gestalt principle of Pragnanz, which organizes primitives into descriptions of images that are both simple and stable. Our definition of Pragnanz assumes just two things: that a vector of free variables controls some general grouping algorithm, and a scalar function measures the information in a grouping. Stable descriptions exist where the gradient of the function is zero; and these can be ordered by information content (simplicity) to create a {"}grouping{"} or {"}Gestalt{"} scale description. We provide a simple measure for information in a grouping based on its structure alone, leaving our grouper free to exploit other Gestalt principles as we see fit. We demonstrate the value of our definition of Pragnanz on several real-world images.",
author = "Song, {Yi Zhe} and Hall, {Peter M}",
year = "2008",
doi = "10.1007/978-3-540-89639-5_31",
language = "English",
isbn = "978-3-540-89638-8",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "318--327",
editor = "G Bebis",
booktitle = "Advances in Visual Computing. ISVC 2008 Proceedings, Part I",

}

TY - CHAP

T1 - Stable Image Descriptions Using Gestalt Principles

AU - Song,Yi Zhe

AU - Hall,Peter M

PY - 2008

Y1 - 2008

N2 - This paper addresses the problem of grouping image primitives; its principal contribution is an explicit definition of the Gestalt principle of Pragnanz, which organizes primitives into descriptions of images that are both simple and stable. Our definition of Pragnanz assumes just two things: that a vector of free variables controls some general grouping algorithm, and a scalar function measures the information in a grouping. Stable descriptions exist where the gradient of the function is zero; and these can be ordered by information content (simplicity) to create a "grouping" or "Gestalt" scale description. We provide a simple measure for information in a grouping based on its structure alone, leaving our grouper free to exploit other Gestalt principles as we see fit. We demonstrate the value of our definition of Pragnanz on several real-world images.

AB - This paper addresses the problem of grouping image primitives; its principal contribution is an explicit definition of the Gestalt principle of Pragnanz, which organizes primitives into descriptions of images that are both simple and stable. Our definition of Pragnanz assumes just two things: that a vector of free variables controls some general grouping algorithm, and a scalar function measures the information in a grouping. Stable descriptions exist where the gradient of the function is zero; and these can be ordered by information content (simplicity) to create a "grouping" or "Gestalt" scale description. We provide a simple measure for information in a grouping based on its structure alone, leaving our grouper free to exploit other Gestalt principles as we see fit. We demonstrate the value of our definition of Pragnanz on several real-world images.

UR - http://dx.doi.org/10.1007/978-3-540-89639-5_31

U2 - 10.1007/978-3-540-89639-5_31

DO - 10.1007/978-3-540-89639-5_31

M3 - Chapter

SN - 978-3-540-89638-8

T3 - Lecture Notes in Computer Science

SP - 318

EP - 327

BT - Advances in Visual Computing. ISVC 2008 Proceedings, Part I

PB - Springer

CY - Berlin

ER -