Perceptually Motivated Shape Evolution with Shape-Preserving Property

Authors:
Sergej Lewin;Xiaoyi Jiang;Achim Clausing
Affiliations:
Department of Mathematics and Computer Science, University of Münster, Münster, Germany D-48149;Department of Mathematics and Computer Science, University of Münster, Münster, Germany D-48149;Department of Mathematics and Computer Science, University of Münster, Münster, Germany D-48149
Venue:
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Year:
2008

Citing 8
Cited 0

Parts of Visual Form: Computational Aspects

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shapes, shocks, and deformations I: the components of two-dimensional shape and the reaction-diffusion space

International Journal of Computer Vision
Convexity rule for shape decomposition based on discrete contour evolution

Computer Vision and Image Understanding
Geometric partial differential equations and image analysis

Geometric partial differential equations and image analysis
Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization

Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization
Numerical Geometry of Images: Theory, Algorithms, and Applications

Numerical Geometry of Images: Theory, Algorithms, and Applications
Shape evolution driven by a perceptually motivated measure

ISVC'07 Proceedings of the 3rd international conference on Advances in visual computing - Volume Part II
An approach to perceptual shape matching

VISUAL'05 Proceedings of the 8th international conference on Visual Information and Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we introduce a novel concept of shape evolution. It is perceptually motivated and takes the local shape symmetry into account. In particular, during the new shape evolution the shape parts in accordance with the human perception are removed step by step and the coarse parts remain geometrically unchanged during removing the fine parts. This shape-preserving property cannot be achieved by the popular Gaussian smoothing (evolution based on geometric heat flow) and related variants. Experimental results demonstrate the behavior and power of this new shape evolution scheme.