• Home
  1. Home
  2. Asynchronous perceptual grouping: from contours to relevant 2D structures
Scientific article
English

Asynchronous perceptual grouping: from contours to relevant 2D structures

Contributors

Jacot-Descombes, Alain; Pun, Thierry

Published in

Computer vision and image understanding, vol. 66, no. 1, p. 1-24

Publication date

1997

Abstract

This paper addresses the issue of bottom-up recovery of structured 2-D geometric primitives from real, complex images. A novel approach for perceptual grouping is presented, using asynchrony whose fundamental principle is to process some primitives before some others, because they carry more information. The main contribution of this work lies in the reduction of the complexity of the grouping process to a problem linear with respect to the number of image contours. Another advantageous characteristic of the proposed method is that only two parameters need to be specified. The asynchronous perceptual grouping processes a data flow of ordered contour primitives, with a rank in the flow determined according to a measure of saliency. It sequentially attempts to group each contour primitive coming in the data flow with other neighboring ones having arrived earlier. Acceptance or rejection of the current contour depends on the geometrical configuration of its neighborhood in the image; properties tested include proximity, colinearity, curvilinearity, and parallelism. The topology as well as the morphology of the relevant structures emerging throughout the whole image are captured in a rigid graph. Junction and surface characteristics are easily extractable, which can help to choose pertinent primitives for an indexing or a recognition system.

UNIGE affiliation entities

UNIGE research groups

Citation (ISO format)

JACOT-DESCOMBES, Alain, PUN, Thierry. Asynchronous perceptual grouping: from contours to relevant 2D structures. In: Computer vision and image understanding, 1997, vol. 66, n° 1, p. 1–24. doi: 10.1006/cviu.1996.0509

Main files (1)

Article (Published version)

Identifiers

Additional URL for this publication

http://www.sciencedirect.com/science/article/pii/S1077314296905093#

Journal ISSN

1077-3142
589views
1downloads

Technical informations

Creation

03/03/2015 16:36:13

First validation

03/03/2015 16:36:13

Update

14/03/2023 22:56:57

Status update

14/03/2023 22:56:57

Last indexation

30/10/2024 23:11:51
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated