Application of pso for solving problems of invariant comparison of two-dimensional closed curve

Abstract

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 deformations is described. 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. 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, for pattern recognition and object tracking systems.

Keywords

• распознавание образов
• машинное зрение
• инвариантность
• диффеоморфные преобразования
• биоинформатика
• метод pso