Computer Architectures for Machine Perception, International Workshop on (2000)
Sept. 11, 2000 to Sept. 13, 2000
V. Cantoni , Dipt. di Inf. e Sistemistica, Pavia Univ., Italy
A. Petrosino , Dipt. di Inf. e Sistemistica, Pavia Univ., Italy
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.
object recognition; object recognition; structured neural networks; pyramidal architecture; pattern recognition; hierarchical modular structure; SIMD machine; image correlation
V. Cantoni and A. Petrosino, "2-D Object Recognition by Structured Neural Networks in a Pyramidal Architecture," Computer Architectures for Machine Perception, International Workshop on(CAMP), Padova, Italy, 2000, pp. 81.