Restoring partly occluded patterns: a neural network model

Authors:
Kunihiko Fukushima
Affiliations:
School of Media Science, Tokyo University of Technology 1404-1 Katakura, Hachioji, Tokyo 192-0982, Japan
Venue:
Neural Networks
Year:
2005

Citing 3
Cited 9

Restoring partly occluded patterns: a neural network model

Neural Networks
Intermediate-level visual representations and the construction of surface perception

Journal of Cognitive Neuroscience
Restoring partly occluded patterns: a neural network model with backward paths

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Restoring partly occluded patterns: a neural network model

Neural Networks
Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning

Neural Computation
Recent Advances in the Neocognitron

Neural Information Processing
Neural Network Capable of Amodal Completion

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
2010 Special Issue: Neural network model for completing occluded contours

Neural Networks
Research frontier: deep machine learning--a new frontier in artificial intelligence research

IEEE Computational Intelligence Magazine
Acquisition of nonlinear forward optics in generative models: Two-stage "downside-up" learning for occluded vision

Neural Networks
Artificial vision by multi-layered neural networks: Neocognitron and its advances

Neural Networks
Template matching of occluded object under low PSNR

Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a neural network model that has an ability to restore missing portions of partly occluded patterns. It is a multi-layered hierarchical neural network, in which visual information is processed by interaction of bottom-up and top-down signals. Memories of learned patterns are stored in the connections between cells. Occluded parts of a pattern are reconstructed mainly by top-down signals from higher stages of the network, while the unoccluded parts are reproduced mainly by signals from lower stages. The restoration progresses successfully, even if the occluded pattern is a deformed version of a learned pattern. The model tries to complete even an unlearned pattern by interpolating and extrapolating visible edges. Resemblance of local features to other learned patterns are also utilized for the restoration.