Stable Image Descriptions Using Gestalt Principles

Yi Zhe Song, Peter M Hall

Research output: Chapter or section in a book/report/conference proceedingChapter or section

2 Citations (SciVal)


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.
Original languageEnglish
Title of host publicationAdvances in Visual Computing. ISVC 2008 Proceedings, Part I
EditorsG Bebis
Place of PublicationBerlin
Number of pages10
ISBN (Electronic)978-3-540-89639-5
ISBN (Print)978-3-540-89638-8
Publication 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


Conference4th International Symposium on Visual Computing
Abbreviated titleISVC 2008
Country/TerritoryUSA United States
CityLas Vegas


Dive into the research topics of 'Stable Image Descriptions Using Gestalt Principles'. Together they form a unique fingerprint.

Cite this