One of the most fundamental features of digital image and the basic steps in image processing, analysis, pattern recognition and computer vision is the Edge of an image where the preciseness and reliability of its results will affect directly on the comprehension machine system made objective world. Several Edge detectors have been developed in the past decades, although no single Edge detectors have been developed satisfactorily enough for all application. In this paper, a new Edge detection technique was proposed based on the BP neural network. Here, the Edge patterns of a quad-pixel in binary images were classified into 16 possible types of visual patterns. In the following, after training the pre-defined Edge patterns, the BP neural network was applied to correspond any type of Edges with their related visual patterns. Compared with traditional Edge detection techniques, the results demonstrate that the new proposed technique, improved the computations mass and mathematical complexity, turns out better.

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.

Edge detection plays a significant role in image processing and performance of high-level tasks such as image segmentation and object recognition depends on its efficiency. It is clear that accurate Edge map generation is more difficult when images are corrupted with noise. Moreover, most of Edge detection methods have parameters which must be set manually. Here we propose a new color Edge detector based on a statistical test, which is robust to noise. Also, the parameters of this method will be set automatically based on image content. To show the effectiveness of the proposed method, four state-of-the-art Edge detectors are implemented and the results are compared. Experimental results on five of the most well-known Edge detection benchmarks show that the proposed method is robust to noise. The performance of our method for lower levels of noise is very comparable to the existing approaches, whose performances highly depend on their parameter tuning stage. However, for higher levels of noise, the observed results significantly highlight the superiority of the proposed method over the existing Edge detection methods, both quantitatively and qualitatively.