Open-File Report 2004–1325
AbstractTraditional edge detection systems function by returning every edge in an input image. This can result in a large amount of clutter and make certain vectorization algorithms less accurate. Accuracy problems can then have a large impact on automated object recognition systems that depend on edge information. A new method of directed edge detection can be used to limit the number of edges returned based on a particular feature. This results in a cleaner image that is easier for vectorization. Vectorized edges from this process could then feed an object recognition system where the edge data would also contain information as to what type of feature it bordered. |
First posted 2004 Part or all of this report is presented in Portable Document Format (PDF); the latest version of Adobe Reader or similar software is required to view it. Download the latest version of Adobe Reader, free of charge. |
Maddox, B.G. and Rhew, B., 1999, A new method of edge detection for object recognition: U.S. Geological Survey Open-File Report 2004–1325, 17 p., available only online at http://pubs.usgs.gov/of/2004/1325/.