Share Email Print

Proceedings Paper

Feature extractor giving distortion invariant hierarchical feature space
Author(s): Jouko Lampinen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A block structured neural feature extraction system is proposed whose distortion tolerance is built up gradually by successive blocks in a pipeline architecture. The system consists of only feedforward neural networks, allowing efficient parallel implementation. The feature extraction is based on distortion-tolerant Gabor transformation and minimum distortion clustering by hierarchical self-organizing feature maps (SOFM). Due to unsupervised learning strategy, there is no need for preclassified training samples or other explicit selection for training patterns during the training. A subspace classifier implementation on top of the feature extractor is demonstrated. The current experiments indicate that the feature space has sufficient resolution power for a small number of classes with rather strong distortions. The amount of supervised training required is very small, due to many unsupervised stages refining the data to be suitable for classification.

Paper Details

Date Published: 1 August 1991
PDF: 11 pages
Proc. SPIE 1469, Applications of Artificial Neural Networks II, (1 August 1991); doi: 10.1117/12.45021
Show Author Affiliations
Jouko Lampinen, Lappeenranta Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 1469:
Applications of Artificial Neural Networks II
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?