17 February 2006 Region-based perceptual grouping: a cooperative approach based on the Dempster-Shafer theory
Author Affiliations +
As segmentation step does not allow recovering semantic objects, perceptual grouping is often used to overcome segmentation's lacks. This refers to the ability of human visual system to impose structure and regularity over signal-based data. Gestalt psychologists have exhibited some properties which seem to be at work for perceptual grouping and some implementations have been proposed by computer vision. However, few of these works model the use of several properties in order to trigger a grouping, even if it can lead to an increase in robustness. We propose a cooperative approach for perceptual grouping by combining the influence of several Gestalt properties for each hypothesis. We make use of Dempster-Shafer formalism, as it can prevent conflicting hypotheses from jamming the grouping process.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nicolas Zlatoff, Nicolas Zlatoff, Bruno Tellez, Bruno Tellez, Atilla Baskurt, Atilla Baskurt, } "Region-based perceptual grouping: a cooperative approach based on the Dempster-Shafer theory", Proc. SPIE 6064, Image Processing: Algorithms and Systems, Neural Networks, and Machine Learning, 60640R (17 February 2006); doi: 10.1117/12.649766; https://doi.org/10.1117/12.649766


Constructing long edge segments for object recognition
Proceedings of SPIE (July 31 1992)
Image segmentation using Gaussian curvature
Proceedings of SPIE (October 02 1995)
Segmentation using atlas-guided deformable contours
Proceedings of SPIE (October 09 1994)
Local level set segmentation method combined with narrow band
Proceedings of SPIE (November 14 2007)

Back to Top