16 December 1992 Invariance problem for hierarchical neural networks
Author Affiliations +
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.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Horst Bischof, Horst Bischof, Axel J. Pinz, Axel J. Pinz, } "Invariance problem for hierarchical neural networks", Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); doi: 10.1117/12.130823; https://doi.org/10.1117/12.130823
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT


Back to Top