Comparative analysis of common edge detection techniques in context of object extraction

Edges characterize boundaries and are therefore a problem of fundamental importance in image processing and particularly in automatic feature extraction. In this paper a comparative study of various edge detection techniques and band wise analysis of these algorithms in the context of object extraction with regard to remote sensing satellite images from the Indian Remote Sensing Satellite (IRS) sensors LISS-III, LISS-IV & Cartosat-I as well as Google Earth is presented. The comparison has been done between commonly used edge detection algorithms like Sobel, Canny, Prewitt, Roberts, Laplacian and Zero Crossing. Analysis results have shown that the Canny’s algorithm is best suitable for the object extraction in most contexts due to fact that it yields less number of false edges, while Sobel is also a good option with lesser time and space complexity. The band wise analyses of the algorithms have also been done to find the suitability of band for the extraction of various features and it has been observed that linear features like roads, railway lines etc. can be detected more efficiently using infra red wavelength range images.