Invariance problem for hierarchical neural networks

Horst Bischof; Axel J. Pinz

doi:10.1117/12.130823

16 December 1992 Invariance problem for hierarchical neural networks

Horst Bischof, Axel J. Pinz

Proceedings Volume 1766, Neural and Stochastic Methods in Image and Signal Processing; (1992) https://doi.org/10.1117/12.130823
Event: San Diego '92, 1992, San Diego, CA, United States

Abstract

Hierarchically organized neural networks are well suited for visual information processing. These models offer a way to cope with the complexity of vision. We identify strong relationships between hierarchical neural networks and image pyramids. However, we also show that if one has the freedom to choose the input patterns, these neural networks are not intrinsically shift invariant. In order to circumvent this problem we propose a new neural network architecture called `Neural Networks in Image Pyramids.' We use hierarchical neural networks with local connectivity (image pyramids) as stem networks. These networks generate hypotheses about the expected image content. These hypotheses are checked by small neural network modules which are used selectively on parts of the image. We give an example demonstrating the solution of the shift variance problem. Finally, we outline directions of further research.

Citation Download Citation

Horst Bischof and Axel J. Pinz "Invariance problem for hierarchical neural networks", Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); https://doi.org/10.1117/12.130823

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