Share Email Print

Proceedings Paper

A contour-based approach for invariant shape description
Author(s): Evgeny Gladilin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This work presents an approach for contour-based shape description, which addresses a large number of cognitive problems related to classification and recognition of 2D single closed contours. Exploiting basic observations about the shape invariant properties, we construct a normalization procedure that establishes the ground for generalized similarity matching between arbitrarily translated, rotated and scaled 2D shapes. A novel descriptor for global and detailed shape analysis is proposed. Cognitive experiments show that the proposed method suits for the recognition of typical silhouettes of conservative anatomical structures, e.g. outlines of vertebra or inner organs. Common issues for optimal data pre-processing and shape representation are discussed.

Paper Details

Date Published: 12 May 2004
PDF: 10 pages
Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); doi: 10.1117/12.533280
Show Author Affiliations
Evgeny Gladilin, Zuse Institute Berlin (Germany)

Published in SPIE Proceedings Vol. 5370:
Medical Imaging 2004: Image Processing
J. Michael Fitzpatrick; Milan Sonka, Editor(s)

© SPIE. Terms of Use
Back to Top