A method for optimal complex rank-order morphological filters with hybrid genetic algorithm is presented in this paper. It combined simulated annealing genetic algorithm (SAGA) with adaptive genetic algorithm (AGA) to achieve optimal filtering parameters in a global searching. Experimental results show that this method is practical, easy to extend, and improves the performances of the complex rank-order morphological filters. By means of adaptive optimizing training the percentile and the structuring elements, morphological filters possess the shape and structural system characteristics of image targets. Complex rank-order morphological filters formed in this way become intelligent and can provide good filtering results and robust adaptability to image targets with clutter background.