Share Email Print
cover

Proceedings Paper

Image segmentation with scatter-partitioning RBF networks: a feasibility study
Author(s): Andrea Baraldi
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Scatter-partitioning Radian Basis Function (RBF) networks increase their number of degrees of freedom with the complexity of an input-output mapping to be estimated on the basis of a supervised training data set. Among scatter-partitioning RBF networks found in the literature, a Gaussian RBF model, termed supervised growing neural gas (SGNG), is selected due to its superior expressive power. SGNG employs a one-stage error-driven learning strategy and is capable of generating and removing both hidden units and synaptic connections. A slightly modified SGNG version is tested as a function estimator when the training surfaces to be fitted is an image, i.e., a 2D signal whose size is finite. The relationship between the generation, by the learning system, of disjointed maps of hidden units and the presence, in the image, of pictorially homogenous subsets is investigated. Unfortunately, the examined SGNG version performs poorly both as function estimator and image segmenter. This may be due to a intrinsic inadequacy of the one-stage error-driven learning strategy to adjust structural parameters and output weights simultaneously but consistently. As a possible remedy, in the framework of RBF networks the combination of a two-stage error-driven learning strategy with synapse generation and removal criteria should be further investigated.

Paper Details

Date Published: 13 October 1998
PDF: 11 pages
Proc. SPIE 3455, Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation, (13 October 1998); doi: 10.1117/12.326710
Show Author Affiliations
Andrea Baraldi, International Computer Science Institute/Univ. of California-Berkeley (United States)


Published in SPIE Proceedings Vol. 3455:
Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation
Bruno Bosacchi; David B. Fogel; James C. Bezdek, Editor(s)

© SPIE. Terms of Use
Back to Top