Edge Detection of Noisy Images Using the Intelligent Techniques

In this paper an approach is presented for edge detection of noisy images that have been degraded by impulsive noise. It uses Fuzzy Inference System (FIS) and Ant Colony Optimization (ACO). Starting with, using the FIS with 12 simple rules is to identify the noisy pixels in order to perform the filtering operation only for the noisy pixels. Probable edge pixels in 4 main directions for filtered image are detected using fuzzy rules and then ACO is applied by assigning a higher pheromone value for the probable edge pixels rather than other pixels so that the ant’s movement toward edge pixels gets faster. Another factor is the influence of the heuristic information in the movement of any ant that is considered to be proportional to local change in intensity of each pixel in order to the possibility of movement of ants increased toward pixels that have more change in their local intensity. Finally, by using an intelligent thresholding technique which is provided by training a neural network, the edges from the final pheromone matrix are extracted. Experimental results are provided in order to demonstrate the superior performance of the proposed approach.