The main problem in image processing is to find out the correct boundaries or edges of any object for clearly identifying it. To characterize the boundaries and edge detection is not an easy task in image processing and it become very difficult when image is noisy. Edges are significant local or sharp change of intensity in an image and it occur on the boundary between two different regions in an image. It means that if the edge of any object can be identified accurately and all of the object can be located then basic properties such as area shape can be measured. Edge detection of an image significantly reduces the amount of irrelevant data and filters out the useless information while preserving the main structural properties of any object.  It is very crucial to have a better understanding of edge detection algorithm. Many techniques of have been developed for edge detection. This paper tries to provide a comparison of different edge detection schemes that fall in three main categories of edge detectors: Gradient based edge detectors, Laplacian based edge detectors and Non-derivative based edge detectors. Pratts figure of merit is used to compare quantitatively results of edge maps for a synthetic image at various levels of noise. Results of real life image are analyzed qualitatively. Non-derivative based edge detector SUSAN gives the best results even in presence of noise.