In view of the slow search speed and high frequency of local optimum resulting from the application of some bionic algorithms to the image segmentation, an improved bacterial foraging algorithm has been proposed for this specific purpose. Firstly, in the traditional bacterial foraging algorithm, chemotaxis operators, fixed step size is to be replaced with dynamic step size, and migration operators, fixed migration probability is to be replaced with dynamic migration probability. Then, the gray histograms of the images are to be extracted for the image segmentation, followed by an image segmentation by adopting the improved bacterial foraging optimization algorithm. The experimental results show that the accuracy and the speed of the image segmentation based on the improved bacterial foraging optimization algorithm are superior to those that are based on other conventional bionic algorithms.