A FLIR image segmentation algorithm based on genetic algorithm and fuzzy set theory was presented. The method defines different member function for the object and background of the image to transform the image into fuzzy domain with maximum fuzzy entropy. The procedure for finding combination of a, b and c is implemented by genetic algorithm, thresholding image into object and background by maximizing the fuzzy entropy. The experiment results show that our proposed method gives better performance and higher calculation speed than other general methods with good real-time by using genetic algorithm.