Edge Detection of Smooth Metallic Surface Using Special Random Sampling Method

Edges are image attributes which are useful for image analysis and classification in a wide range of applications. The numerous applications and the subjective approaches to edge definition and characterization have promoted the development of a large number of edge operators which may perform well in given applications but poorly in smooth metallic surface where specular reflection components are very strong but diffuse reflection components are often too weak. In order to detect edge on smooth metallic surfaces, a set of real images are taken under various lighting conditions and Special Random Sampling Method is introduced to process reflection components. The experimental results show that a large number of edge operators can be effectively applied to realistic images of smooth metallic surfaces after processing reflection components by Special Random Sampling Method.