GNG3D - A Software Tool for Mesh Optimization Based on Neural Networks

A new software tool-denoted as GNG3D for mesh optimization is presented. This tool has been implemented taking as a basis a new method which is based on neural networks and consists on two differentiated phases: an optimization phase and a reconstruction phase. The optimization phase is developed applying an optimization algorithm based on the Growing Neural Gas model, which constitutes an unsupervised incremental clustering algorithm. The primary goal of this phase is to obtain a simplified set of vertices representing the best approximation of the original 3D object. In the reconstruction phase we use the information provided by the optimization algorithm to reconstruct the faces obtaining in such a way the optimized mesh. Finally, we will report some experimental results and examples for some 3D models using the different options implemented in the GNG3D tool.