Neural Abstraction Pyramid: A hierarchical image understanding architecture
Authors: Sven Behnke and Raul Rojas
In Proceedings of International Joint Conference on Neural Networks (IJCNN'98)
-- Anchorage, AL, vol. 2, pp. 820-825, 1998.
A hierarchical neural architecture for image interpretation is proposed
that is based on image pyramids and cellular neural networks and is inspired
by the principles of information processing found in the visual cortex.
Algorithms for this architecture are defined in terms of local interactions
of processing elements and utilize horizontal as well as vertical feedback
loops. The goal is to transform a given image into a sequence of representations
with increasing level of abstraction and decreasing level of detail.
A first application, the binarization of handwriting, has been implemented
and shown to improve the acceptance rate of an automatic ZIP-code recognition
system without decreasing its reliability.
Full paper: ijcnn98.pdf
to selected image interpretation publications