Fast Linear Feature Detection Using Multiple Directional Non-Maximum Suppression

Linear feature detection is a very important issue in the areas of image analysis, computer vision, and pattern recognition. It has found applications in many diverse areas such as neurite outgrowth detection, compartment assay analysis, retinal vessel extraction, skin hair removal for malonoma detection, plant root analysis, and roads detection. We have developed a new algorithm for linear feature detection using multiple directional non-maximum suppression. The algorithm is very fast compared with methods in the literature. We also show a large number of application examples using our linear feature detection algorithm, and very good results have been obtained.

• Type: Conference
• Year: 2006
• Where: ICPR
• Authors: Changming Sun, Pascal Vallotton
• Keywords: Computer Vision, Feature Detection Algorithm, ICPR 2006, Linear Feature Detection, Neurite Outgrowth Detection