An Edge Preserving Regularization Model for Image Restoration Based on Hopfield Neural Network
This paper designs an edge preserving regularization model for image restoration. First, we propose a generalized form of Digitized Total Variation (DTV), and then introduce it into restoration model as the regularization term. To minimize the proposed model, we map digital image onto network, and then develop energy descending schemes based on Hopfield neural network. Experiments show that our model can significantly better preserve the edges of image compared with the commonly used Laplacian regularization (with constant and adaptive coefficient). We also study the effects of neighborhood and gaussian parameter on the proposed model through experiments.
KeywordsRegularization Term Image Restoration Minimization Algorithm Image Denoising Hopfield Neural Network
Unable to display preview. Download preview PDF.
- 5.Ghennam, S., Benmahammed, K.: Adaptive Image Restoration Using Hopfield Neural Network. In: Proceedings of the 2001 IEEE Signal Processing Society Workshop, pp. 569–578 (2001)Google Scholar
- 6.Palmer, A.S., Razaz, M., Mandic, D.P.: Spatially Adaptive Image Restoration by Neural Network Filtering. In: Proceedings of VII Brazilian Symposium on Neural Networks, pp. 184–189 (2002)Google Scholar
- 12.Perry, S.W., Guan, L.: Perception-Based Adaptive Image Restoration. In: Proc. Int. Conf. Acoust., Speech, Signal Processing, pp. 2893–2896 (1998)Google Scholar