An Enhanced Edge Detection Algorithm for 2-D Images

In gray-level image processing, images of typical scenes contain large areas of gradual intensity change, called segments, bounded by narrow regions of very rapid intensity change, called edges. An edge detector is a procedure or rule that locates a series of points, arranged roughly in a line, where rapid intensity changes have occurred. Edge detection is a problem of fundamental importance in image analysis and is a terminology in image processing and computer vision, particularly in the areas of feature detection and feature extraction. Many different forms of edge detectors have been developed in image processing, including Sobel, Robert, LOG (laplacian of Gaussian), Prewitt, Canny, Mathematical Morphology and Multi-Structure Elements Mathematical Morphology. In this paper all the various edge detection algorithms are discussed and in addition to that, Top-hat and bottom-hat transformation are used for enhancing the image contrast and reduces noise as well.