Abstract | ||
---|---|---|
A modified Hopfield network model for image restoration is presented. The proposed neural network does not require zero autoconnections, which is one of the major drawbacks of the Hopfield network. A new number-representation scheme for implementing the proposed network is given. The proposed network with sequential update is shown to converge. The sufficient conditions for convergence of n -simultaneous updates are also given. When the image-restoration problem does not satisfy the convergence conditions, a greedy algorithm which guarantees convergence (at the expense of the image quality) is used |
Year | DOI | Venue |
---|---|---|
1990 | 10.1109/ICASSP.1990.115873 | Albuquerque, NM |
Keywords | DocType | ISSN |
neural nets,picture processing,hopfield network,convergence conditions,greedy algorithm,image restoration,neural network model,nonzero autoconnection,number-representation scheme,parallel algorithms,sequential update,satisfiability,neural network,neural networks,degradation,image quality,convergence,artificial neural networks,greedy algorithms | Conference | 1520-6149 |
Citations | PageRank | References |
6 | 2.73 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Paik, J.K. | 1 | 6 | 2.73 |
Katsaggelos, A. | 2 | 80 | 10.60 |