Morphological edge detection by successive segmentation for thermal images

A morphological edge detection technique using successive segmentation is presented. This method is based on the fact that an existing edge must lie within one or more threshold levels of a grayscale image. The detection of the desired edge is achieved by applying a perimeter function criterion so that the corresponding threshold level is included. The detection of fine edges can be controlled by the number of stages in the process of successive segmentation. It has been shown that our proposed technique performs favourably in terrain-type images when compared with many other well known edge detection algorithms.