ABSTRACT
Edge-based segmentation is a type of segmentation that is based on the information about the edges in an image. It gives the information about the object boundaries using some edge-detecting operators. These operators fi nd the discontinuities in gray level, color, texture, etc. Edge-detection methods simplify the analysis of the image by reducing the data to be processed. Edge strength is calculated by taking the gradient value of the image when there is a sharp change in the pixel values. Edges may present in many directions and so the important requirements for a good edge detecting operator are that they should be capable of being tuned to act at any desired scale. So the edge detectors are such that they should consider all the edge directions to detect all the edges properly. The most common problem in edge detection is the presence of noise in the image where an edge due to noise will also be detected and these false edges will be misinterpreted as the edges of an image.
