2-D Maximum Entropy Method of Image Segmentation Based on Genetic Algorithm

2-D thresholds are coded，then the fitness function is established according to the criterion function of 2-D maximum entropy．Finally the image which is disturbed by serious noise is segmented effectively under the proper crossover rate and mutation rate．Segmentation examples show that the method proposed has greater resistance capability to noise than 1-D maximum entropy approach，and is faster than the common 2-D maximum entropy approach．