This article is cited in 1 paper

MATHEMATICAL MODELING AND NUMERICAL SIMULATION

Symmetries of differential equations in computer vision applications

D. A. Vrazhnov^a, A. V. Shapovalov^bc, V. V. Nikolaev<sup>b

a</sup> Tomsklabs LLC, Akademicheskiy av,. 8/8, 634055, Tomsk, Russia
^b Tomsk State University, Lenin av., 36, 634050, Tomsk, Russia
^c Tomsk Polytechnic University, Lenin av., 30, 634050, Tomsk, Russia

Abstract: In our work we present generalization of well-known approach for construction of invariant feature vectors of images in computer vision applications. Basic feature of the suggested algorithm is replacement of commonly used Gaussian filter by convolution of image function with Green’s function of evolution operator, which inherits symmetries of this operator. The use of general filtration allows to obtain additional characteristics of invariant feature vectors.

Keywords: computer vision, pattern recognition, filtering, symmetries of differential equations, Green Function.

UDC: 004.931; 004.932

Received: 25.03.2010

DOI: 10.20537/2076-7633-2010-2-4-369-376