Good continuations in digital image level lines

We propose a probabilistic algorithm able to detect the curves that are unexpectedly smooth in a set of digital curves. The only parameter is a false alarm rate, influencing the detection only by its logarithm. We experiment the good continuation criterion on image level lines. One of the conclusion is that, accordingly to Gestalt theory, one can detect edges in a way that is widely independent of contrast. We also use the same kind of method to detect corners and junctions.