Using morphological operations — Erosion based algorithm for edge detection

摘要: Edge detection remains a challenging task in many applications even with the abundance of commonly used methods such as Sobel, Robert, Prewitt, Canny, and Cellular Automata. In this paper, new method is proposed for edge using morphological operations utilizing erosion processes to identify edges an image. work we propose use operators disk shape detect thin from binary images generated Otsu's thresholding technique. Using several synthetic real variety applications, show that our algorithm provides robust terms accuracy computation time, making it suitable time processing. The results also capable producing one-pixel-width continuous well accurate positioning while preserving minute image details. We present comparison between Canny Automata methods.