Abstract:
This chapter presents an e±cient technique for linking edge points in
order to generate a closed contour representation. The original intensity image,
as well as its corresponding edge map, are assumed to be given as input to the
algorithm (i.e., an edge map is previously computed by some of the classical edge
detector algorithms). The proposed technique consists of two stages. The ¯rst stage
computes an initial representation by connecting edge points according to a global
measure. It relies on the use of graph theory. Spurious edge points are removed
by a morphological ¯lter. The second stage ¯nally generates closed contours, linking
unconnected edges, by using a local cost function. Experimental results with di®erent
intensity images are presented.
