Authenticating Edges Produced by Zero-Crossing Algorithms

Abslruct-It is shown that zero-crossing edge detection algorithms can produce edges which do not correspond to significant image intensity changes. Such edges are called phantom or spurious. A method for classifying zero crossings as corresponding to “authentic” or “phantom” edges is presented. The contrast of an authentic edge is shown to increase with decreasing filter scale (and hence higher resolution), and the contrast of phantom edges is shown to decrease with a decrease in the filter scale. Thus, a phantom edge is truly a phantom edge in that the closer one examines it the weaker it becomes. The results of applying the classification schemes described in this paper to synthetic and authentic signals in one and two dimensions are given. The significance of the phantom edges is examined with respect to their frequency and strength relative to the authentic edges, and it is seen that authentic edges are denser and stronger, on the average, than phantom edges. Index Terms-Edge authentication, edge detection, phantom edges, scale space.