Infrared image segmentation via intelligent genetic algorithm based on maximum entropy

This paper presents a fast and effective segmentation method for infrared image, based on fuzzy filtering, the criteria of maximum entropy and intelligent genetic algorithm. A fuzzy filter is applied to depress the Gaussian(-like) noise. Then we use the theory of maximum entropy to select the optimum threshold. A new intelligent genetic algorithm (IGA). which applies an intelligent crossover (IC) based on orthogonal arrays (OAS). is proposed to solve this optimal problem. Experiment results show that the proposed method can depress the Gaussian(-like) noise effectively, segment the infrared image properly, and is faster than the conventional genetic algorithm and exhaustive search, also is easier to implement on hardware.