The problem of estimating the norm of the distance between the two closed smooth curves for pattern recognition is considered. Diffeomorphic transformation curves based on the model of large deformation with the transformation of the starting points of domain in required is formed on the basis of which depends on time-dependent vector field of velocity is considered. The action of the translation, rotation and scaling closed curve, the invariants of the action of these groups are considered. The position of curves is normalized by centering, bringing the principal axes of the image to the axes of the coordinate system and bringing the area of a closed curve corresponding to one. For estimating of the norm of the distance between two closed curves is formed the functional corresponding normalized distance between the two curves, and the equation of evolution diffeomorphic transformations. The equation of evolution allows to move objects along trajectories which correspond to diffeomorphic transformations. The diffeomorphisms do not change the topology along the geodesic trajectories. The problem of inexact comparing the minimized functional contains a term that estimates the exactness of shooting points in the required positions. In the equation of evolution is introduced the variance of conversion error. An algorithm for solving the equation of diffeomorphic transformation is proposed, built on the basis of PSO, which can significantly reduce the number of computing operations, compared with gradient methods for solving. The developed algorithms can be used in bioinformatics and biometrics systems, classification of images and objects, machine vision systems, neuroimaging, for pattern recognition and object tracking systems. Algorithm for estimating the norm of distance between the closed curves by diffeomorphic transformation can spread to spatial objects (curves, surfaces, manifolds).

invariance, rotation group, translation group, diffeomorphic transformation, PSO method

1. 1 Beg M.F. et al. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International journal of computer vision, 2005, vol. 61, no. 2, pp. 139–157

2. 2 Chukanov S.N. A rotation, translation, and scaling invariant Fourier transform of 3D image function. Optoelectronics, Instrumentation and Data Processing, 2008, vol. 44, no. 3, pp. 249–255.

3. 3 Baker A. Matrix groups: An introduction to Lie group theory. Springer Science & Business Media, 2012.

4. 4 Arnold V.I., Khesin B.A. Topological methods in hydrodynamics. Springer Science & Business Media, 1998.

5. 5 Holm D.D. et al. Geometric mechanics and symmetry: from finite to infinite dimensions. London, Oxford University Press, 2009.

6. 6 Miller M.I., Trouve A., Younes L. Geodesic shooting for computational anatomy. Journal of mathematical imaging and vision, 2006, vol. 24, no. 2, pp. 209–228

7. 7 Bruveris M., Holm D.D. Geometry of image registration: The diffeomorphism group and momentum maps. Geometry, Mechanics, and Dynamics. Springer New York, 2015, pp. 19–56

8. 8 Kennedy J. et al. Swarm intelligence. Morgan Kaufmann, 2001

9. 9 Yang X.S. Nature-inspired optimization algorithms. Elsevier, 2014

10. 10Karpenko A.P. Sovremennye algoritmy poiskovoj optimizacii [Modern algorithms of search engine optimization] Moscow, Izdatel'stvo MGTU im. N. E. Baumana, 2014.