Corner detection using vector potential

This paper describes how corner detection can be realised using a new feature representation that has recently been successfully exploited for edge and symmetry detection. The feature representation based on an magneto-static analogy. The idea is to compute a vector potential by appealing to an analogy in which the Canny edge-map is regarded as an elementary current density residing on the image plane. In our previous work we demonstrated that edges are the local maxima of the vector potential while points of symmetry correspond to the local minimum. In this paper we demonstrate that corners are located at the saddle points of the magnitude of the vector potential. These points corresponds to the intersections of saddle-ridge and saddle-valley structures, i.e. to junctions of the edge and symmetry lines. We describe a template-based method for locating the saddle-points. This involves performing a nonminimum suppression test in the direction of the vector potential and a nonmaximum suppression test in the orthogonal direction. Experimental results of both synthetic and real images are given.