Share Email Print
cover

Proceedings Paper

The recognition of graphical patterns invariant to geometrical transformation of the models
Author(s): Ioan Ileană; Corina Rotar; Maria Muntean; Emilian Ceuca
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In case that a pattern recognition system is used for images recognition (in robot vision, handwritten recognition etc.), the system must have the capacity to identify an object indifferently of its size or position in the image. The problem of the invariance of recognition can be approached in some fundamental modes. One may apply the similarity criterion used in associative recall. The original pattern is replaced by a mathematical transform that assures some invariance (e.g. the value of two-dimensional Fourier transformation is translation invariant, the value of Mellin transformation is scale invariant). In a different approach the original pattern is represented through a set of features, each of them being coded indifferently of the position, orientation or position of the pattern. Generally speaking, it is easy to obtain invariance in relation with one transformation group, but is difficult to obtain simultaneous invariance at rotation, translation and scale. In this paper we analyze some methods to achieve invariant recognition of images, particularly for digit images. A great number of experiments are due and the conclusions are underplayed in the paper.

Paper Details

Date Published: 4 December 2010
PDF: 6 pages
Proc. SPIE 7821, Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies V, 782123 (4 December 2010); doi: 10.1117/12.882282
Show Author Affiliations
Ioan Ileană, 1 Decembrie 1918 Univ. of Alba Iulia (Romania)
Corina Rotar, 1 Decembrie 1918 Univ. of Alba Iulia (Romania)
Maria Muntean, 1 Decembrie 1918 Univ. of Alba Iulia (Romania)
Emilian Ceuca, 1 Decembrie 1918 Univ. of Alba Iulia (Romania)


Published in SPIE Proceedings Vol. 7821:
Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies V

© SPIE. Terms of Use
Back to Top