A parallel image restoration algorithm based on Harmonic model using neural networks

Abstract

In our previous work [1, 2J, an image restoration algorithm based on modified Hopfield neural network and harmonic model was proposed. But the computational complexity of the algorithm is high. In this paper, a parallel image restoration algorithm based on the Harmonic model using modified Hopfield neural network (MHNN) is de veloped. The proposed algorithm makes fu ll use of the parallel computation performance of neural network and effectively reduces the computational complexity from O(n x L) to O(n). Numerous experimental results de monstrate that the proposed restoration algorithm outperforms the traditional restoration algorithm in terms of computational complexity.