2-D object recognition by structured neural networks in a pyramidal architecture
Virginio Cantoni, Alfredo Petrosino · 2002
In the paper we propose an approach to the realization of models inspired to biological solutions for pattern recognition. The approach is based on a hierarchical modular structure capable to learn by examples and recognize objects in digital images. The adopted techniques are based on multiresolution image correlation and neural networks. Performance on two different data sets and experimental timings on a SIMD machine are also reported.