Abstract:
In order to increase the speed of SAR image segmentation based on fuzzy Artificial Bee Colony algorithm, a method of SAR image in spatial threshold segmentation is proposed.In this method, gray morphology operations are employed to reduce the inherent image noise, and the searching range is reduced on the basis of the histogram feature of the denoised image. Simultaneously, a fuzzy function is introduced in order to refine the motion of bees, and fast search the optimal threshold. Experimental results show that the proposed method is not only robust to the speckle noise in SAR images, but also superior to the segmentation methods based on Genetic algorithm or Artificial Fish Swarm algorithm in terms of segmenting speed and quality.
