A novel CNN template design method based on GIM

Authors:
Jianye Zhao;Hongling Meng;Daoheng Yu
Affiliations:
Department of Electronics, Peking University, Beijing, China;Department of Electronics, Peking University, Beijing, China;Department of Electronics, Peking University, Beijing, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Year:
2005

Citing 4
Cited 0

Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Markovian image models for image labeling and edge detection

Signal Processing
Image thinning using pulse coupled neural network

Pattern Recognition Letters
Optimal solutions for cellular neural networks by paralleled hardware annealing

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a kind of relation between CNN (cellular neural network) and GIM (Gibbs image model) is noted. Based on this relation, a new approach for CNN's template design is proposed, this approach is valid to many questions that could be processed with GIM, such as segmentation, edge detection and restoration. We also discuss the learning algorithm and hardware annealing jointed with the new approach. Simulations of some examples are shown in order to validate effectiveness of new approach.