1 August 1991 Feature extractor giving distortion invariant hierarchical feature space
Author Affiliations +
Proceedings Volume 1469, Applications of Artificial Neural Networks II; (1991); doi: 10.1117/12.45021
Event: Orlando '91, 1991, Orlando, FL, United States
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.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jouko Lampinen, "Feature extractor giving distortion invariant hierarchical feature space", Proc. SPIE 1469, Applications of Artificial Neural Networks II, (1 August 1991); doi: 10.1117/12.45021; https://doi.org/10.1117/12.45021
PROCEEDINGS
11 PAGES


SHARE
KEYWORDS
Distortion

Feature extraction

Artificial neural networks

Image filtering

Image resolution

Neural networks

Tolerancing

Back to Top