Title :
2-D object recognition by structured neural networks in a pyramidal architecture
Author :
Cantoni, Virginio ; Petrosino, Alfredo
Author_Institution :
Dipt. di Inf. e Sistemistica, Pavia Univ., Italy
Abstract :
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
Keywords :
computer architecture; neural nets; object recognition; SIMD machine; hierarchical modular structure; image correlation; object recognition; pattern recognition; pyramidal architecture; structured neural networks; Biological system modeling; Context modeling; Digital images; Hopfield neural networks; Image recognition; Intelligent networks; Neural networks; Neurons; Object recognition; Testing;
Conference_Titel :
Computer Architectures for Machine Perception, 2000. Proceedings. Fifth IEEE International Workshop on
Conference_Location :
Padova
Print_ISBN :
0-7695-0740-9
DOI :
10.1109/CAMP.2000.875961
