DOI: 10.36347/sjet

Pages: 78-90

In the field of image processing, edge detection is an important step for extracting relevant and meaningful information from digital images. The main goal of edge detection techniques is to obtain and detect thin edges of the objects present in the image, so that the result is more suitable for further processing and analysis such as boundary detection, image segmentation, motion detection/estimation, texture analysis, object identification, feature detection, implementing various transformations and so on. We tested six edge detection algorithms that use different methods for detecting edges and compared their results under a variety of situations to determine a generally preferable technique under different sets of conditions. This data could then be used to create a multi-edge-detector system, which analyses the scene and runs the edge detector best suited for the current set of data. For each of these edge detectors we considered two different ways of implementation, the one using intensity only and the other coupling to it, the colour information. We also considered one additional edge detector which takes a different philosophy to edge detection. Rather than trying to find the ideal edge detector to apply to traditional photographs, it would be more efficient to merely change the method of photography to one which is more conducive to edge detection.