Quad-pixel edge detection using neural network


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.