A CONNECTIVITY SOLUTION FOR EXTRACTION OF THIN OBJECTS (MP-P4)

Author(s) : Marco Antonelli (Univ. of Genoa - Dept. of Biophysical and Electronic Engineering, Italy) Silvana Dellepiane (Univ. of Genoa - Dept. of Biophysical and Electronic Engineering, Italy) Gianni Vernazza (Univ. of Genoa - Dept. of Biophysical and Electronic Engineering, Italy) Lorena Novelli (Univ. of Genoa - Dept. of Biophysical and Electronic Engineering, Italy)

Abstract : Frequently image processing has to deal with thin structures that hold the information required. In natural images there are a wide variability of conditions and the borders of the objects are not always well defined. Progressive scan, an algorithm derived from fuzzy-connectedness theory is described here as a specific case of more general c–connectedness. Taking some analogies from the mechanical world it allows to track thin structures and, consequently, is suitable for river, motorways or vessel extraction. In the computation of fuzzy connectedness, a widely used approach is based on an adaptive growing mechanism that follows the best paths starting from a reference seed point. The new algorithm foresees to use three or more seed points in order to better drive that algorithm along the structure of interest. Results of the algorithm are the best path along the object and a connectivity map. The algorithm can deal with heterogeneous situations from medical to remote sensed images.

Menu