Share Email Print

Proceedings Paper

n-D shape/texture optimal synthetic description and modeling by GEOGINE
Author(s): Rodolfo A. Fiorini; Gianfranco F. Dacquino
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

GEOGINE© (GEOmetrical enGINE), a state-of-the-art OMG (Ontological Model Generator) based on n-D Tensor Invariants for multidimensional shape/texture optimal synthetic description and learning, is presented. Usually elementary geometric shape robust characterization, subjected to geometric transformation, on a rigorous mathematical level is a key problem in many computer applications in different interest areas. The past four decades have seen solutions almost based on the use of n-Dimensional Moment and Fourier descriptor invariants. The present paper introduces a new approach for automatic model generation based on n -Dimensional Tensor Invariants as formal dictionary. An ontological model is the kernel used for specifying ontologies so that how close an ontology can be from the real world depends on the possibilities offered by the ontological model. By this approach even chromatic information content can be easily and reliably decoupled from target geometric information and computed into robus colour shape parameter attributes. Main GEOGINE© operational advantages over previous approaches are: 1) Automated Model Generation, 2) Invariant Minimal Complete Set for computational efficiency, 3) Arbitrary Model Precision for robust object description.

Paper Details

Date Published: 8 December 2004
PDF: 12 pages
Proc. SPIE 5613, Military Remote Sensing, (8 December 2004); doi: 10.1117/12.578546
Show Author Affiliations
Rodolfo A. Fiorini, Politecnico di Milano (Italy)
Gianfranco F. Dacquino, Politecnico di Milano (Italy)

Published in SPIE Proceedings Vol. 5613:
Military Remote Sensing
Gary W. Kamerman; David V. Willetts, Editor(s)

© SPIE. Terms of Use
Back to Top