On the perceptual organization of texture and shading flows: from a geometrical model to coherence computation
Authors:
- 24 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919) , 1048
Abstract
Locally parallel dense patterns - sometimes called texture flows define a perceptually coherent structure which is important to image segmentation, edge classification, shading analysis, and shape interpretation. This paper develops the notion of texture flow from a geometrical point of view to argue that local measurements of such structures must incorporate two curvatures. We show how basic theoretical considerations lead to a unique model for the local behavior of the flow and allow for the specification of consistency constraints between nearby measurements. The computation of globally coherent structure via neighborhood relationships is demonstrated on synthetic and natural images, and is compared to orientation diffusion.Keywords
This publication has 17 references indexed in Scilit:
- Diffusion of General Data on Non-Flat Manifolds via Harmonic Maps Theory: The Direction Diffusion CaseInternational Journal of Computer Vision, 2000
- Orientation diffusionsIEEE Transactions on Image Processing, 1998
- Texture Laciness: The Texture Equivalent of Transparency?Perception, 1996
- A Bayesian framework for understanding texture segmentation in the primary visual cortexVision Research, 1995
- Direct Estimation and Error Analysis for Oriented PatternsComputer Vision and Image Understanding, 1993
- Visual perceptions of smoothly curved surfaces from double-projected contour patterns.Journal of Experimental Psychology: Human Perception and Performance, 1990
- Radial projection: an efficient update rule for relaxation labelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- Perceptual Organization and Visual Recognition1985
- Computation of locally parallel structureBiological Cybernetics, 1978
- Gestalt theory.1938