A Reliability Matching Method Based on an Improved Genetic Algorithm

A reliability matching method based on an improved genetic algorithm was presented.The real-time image and the referenced image were decomposed to wavelets pyramid and edge-enhanced with the fourth order center B spline wavelets.The matching was done based on the improved genetic algorithm in coarse scale.The improved genetic algorithm can find the local extreme as the candidate matching points to ensure the true matching point was included.The real-time image was corrected with rotation.The binary edge images were obtained based on the local gray feature around the candidate matching points.The correlation matching was implemented again and the maximal peak value was chosen as the true matching point.Then the precise matching point was obtained in fine scale.Experimental results show that the matching probability of the method is increased 9.5% than that of the method based on the wavelets binary edge extraction.