Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
411015 | Neurocomputing | 2006 | 5 Pages |
Abstract
In this paper we present two novel image restoration algorithms based on a modified Hopfield neural network and variational partial differential equations (PDE). The first algorithm is based on a harmonic model and the other is based on a total variation model. Both algorithms can restore the degraded images and preserve the edges. The experimental results show that our algorithms are better than other known neural network-based restoration algorithms, especially when images mainly consist of edges, such as letters.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Ya-Dong Wu, Qing-Xin Zhu, Shi-Xin Sun, Hong-Ying Zhang,