Vision System for Image Recognition Based on Three-Dimensional Vector Patterns

• Autorzy: Gridin, V. N. , Titov, M. I. , Truphanov, M. I. , Korostelev, S. I.
• Języki publikacji: EN

Abstrakty

EN

We introduce a vision system for object image recognition based on a three-dimensional vector pattern, which offers a possibility to solve a broad variety of problems connected with image recognition. We point out that the use of three-dimensional vector models as patterns enables substantial reduction in the memory costs and simplification of the learning process. In the paper we provide a description of the image recognition method implemented by the vision system, and propose the ways for its development.

Słowa kluczowe

EN

vision system; image recognition; three-dimensional vector patterns; 3D pattern

• Czasopismo: Machine Graphics and Vision
• Rocznik: 2009
• Tom: Vol. 18, No. 2
• Strony: 175-186
• Opis fizyczny: Bibliogr. 4 poz., il.

Twórcy

autor

Gridin, V. N.

autor

Titov, M. I.

autor

Truphanov, M. I.

autor

Korostelev, S. I.

• Kursk State Technical University Russia

Bibliografia

• [1] Laszlo M.: Computational geometry and computer graphics in C++. Prentice Hall, 1996.
• [2] Buss S.: 3D Computer Graphics: A Mathematical Introduction with OpenGL. Cambridge University Press, 2003.
• [3] Korostelev S., Panishev V.: The use of 3D patterns in the problem of recognition: All-Russian conference of problems in informatics, physics and chemistry. Moscow Peoples' Friendship University of Russia; 2005. - pp.106-108.
• [4] Pillonetto G., De Nicolao G., Chierici M., Cobelli C.: Fast algorithms for nonparametric population modeling of large data sets, Automatica (Journal of IFAC), v.45 n. l, 2009, - pp. 173-179.