Image segmentation method based on genetic algorithm and maximum entropy threshold segmentation algorithm

The invention relates to an image segmentation method based on a genetic algorithm and a maximum entropy threshold segmentation algorithm, which comprises the following steps: calculating a gray scale histogram of the image; coding the gray scale of the image, thereby generating M initial populations; calculating the adaptability of each individual in the populations by means of the maximum entropy threshold segmentation algorithm; performing genetic operation on the populations for obtaining new populations, wherein the genetic operation comprises selection operation, crossover operation and mutation operation; determining the approximating level of an optimum solution in the secondary populations, and if the approximating level is smaller than an acceptance probability, ending the determining and acquiring a segmentation threshold, and otherwise returning and continuing iteration; and processing the image to be segmented according to a segmentation threshold. According to the image segmentation method, a relatively good segmentation threshold can be converged in a short time.