Neural Abstraction Pyramid: A hierarchical image understanding architecture
In Proceedings of International Joint Conference on Neural Networks (IJCNN'99)
-- Washington, DC, paper number #491, 1999.
The recently introduced Neural Abstraction Pyramid is a hierarchical
neural architecture for image interpretation that is inspired by the principles
of information processing
found in the visual cortex. In this paper we present an unsupervised
learning algorithm for it's connectivity based on Hebbian weight updates
and competition. The algorithm
yields a sequence of feature detectors that produce increasingly abstract
representations of the image content. These representations are distributed,
sparse, and facilitate the
interpretation of the image.
We apply the algorithm to a dataset of handwritten digits, starting
from local contrast detectors. The emerging feature detectors correspond
to step edges, lines, strokes, curves,
and digit shapes. They can be used to reliably classify the digits.
Full paper: ijcnn99.pdf
to selected image interpretation publications