Sept. 17, 2003 to Sept. 19, 2003
Luca Lombardi , Universitá di Pavia
Alfredo Petrosino , National Research Council
In this paper we present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, lenghth, simmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. The recognition procedure is formulated as a training procedure made by Recursive Neural Networks followed by a testing procedure over unknown tree structured patterns.
Luca Lombardi, Alfredo Petrosino, "Shape Recognition by Distributed Recursive Learning of Multiscale Trees", ICIAP, 2003, Image Analysis and Processing, International Conference on, Image Analysis and Processing, International Conference on 2003, pp. 26, doi:10.1109/ICIAP.2003.1234020