Research and Analysis on Gray Genetic Algorithm

Abstract

In view of the slow match speed of the image, the article proposes gray genetic algorithm (GGA), one kind of new fast image match method, combining the gray connection theory with genetic algorithm. This method, firstly, determines question's parameter space to obtain several of initial points required to be match through coding the parameter space and the string collection initialized. Then the reference sequence and the comparison sequence separately are to be constructed by means of the template chart and the histogram searching for current subgraph's information. Lastly, fitness function are established on these two sequences between pessimistic interrelatedness as reference Based on this, the string collection initialized evolves gradually optimizing region of the search space after many kinds of genetic algorithm's operation, such as the choice operation, the overlapping operation and the variation operation and so on. Finally, it infinitely approaches the optimum matching position. Because the GGA law has fully applied the small sample and genetic algorithm computation parallelism characterized in the gray connection theory, the timeliness of the image match have been distinctly enhanced with certain match precision.