Image Clustering Using a Growing Neural Gas with Forbidden Regions

Clustering is one of the most common applications of unsupervised learning, being present in many statistical data analysis processes performed by scientists and engineers. Because of their special features, some categories of Artificial Neural Networks have demonstrated to be specially efficient when it comes to clustering. The Growing Neural Gas (GNG) is a good example of these networks, not only because its capability for revealing the clusters underlying in a certain distribution with an optimized number of neurons, but to faithfully describe the topological relations among the different clusters of a dataset. However, because of their intrinsic nature, there will be some data distributions with regions where no data can be found. Aiming to perform a clustering process on these datasets, this paper presents the design of a Growing Neural Gas-inspired model that keeps its neuron prototypes out of a set of regions previously specified, namely Forbidden Region Growing Neural Gas (FRGNG). Experimental results illustrate how this model can represent an alternative, in terms of accuracy, to one of the most recent region avoiding clustering algorithms such as the Forbidden Region Self-Organizing Map (FRSOFM).