Generalised threshold selection for edge detection

Abstract This paper derives a generalised technique for selecting thresholds of edge strength maps from theoretical considerations of the known noise statistics of the image. A technique is described for estimating the mean and variance of the noise of an image using a pair of images. The threshold selection technique can be applied to any single digital edge operator and has been extended for use with combinations of edge operators. Two examples of thresholded edge maps using the techniques developed here are shown.