GA-Based Affine PPM Using Matrix Polar Decomposition

Point pattern matching (PPM) is an important problem in pattern recognition, digital video processing and computer vision. In this paper, novel and fast procedure based on Genetic Algorithm, for afine PPM is described. Most matching techniques solved the PPM problem by determining the correspondence between points localized spatially within two sets, then to get the proper transformation parameters, solved a set of equations. In this paper, we use this fact that correspondence and transformation matrices are two unitary polar factors of Grammian matrices. We estimate one of this factors by the Genetic Algorithm's population and evaluate this estimation by computing another factor using fitness function. This approach is easily implemented one and because of using the genetic algorithm, don't converge into local minima. Simulation results on randomly generated points patterns and real point patterns, show that the algorithm is very efective.