Feature extractor giving distortion invariant hierarchical feature space

Jouko Lampinen

doi:10.1117/12.45021

1 August 1991 Feature extractor giving distortion invariant hierarchical feature space

Jouko Lampinen

Proceedings Volume 1469, Applications of Artificial Neural Networks II; (1991) https://doi.org/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.

Citation Download Citation

Jouko Lampinen "Feature extractor giving distortion invariant hierarchical feature space", Proc. SPIE 1469, Applications of Artificial Neural Networks II, (1 August 1991); https://doi.org/10.1117/12.45021

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available