Edge-preserving neural network model for image restoration

This paper presents a combined approach for image restoration with edge-preserving regularization, subband coding, and artificial neural network. The multilayer perceptron model is employed to implement the restoration of images. The main merit of the neural network model is its massive parallelism with strong robustness for transmission noise and parameter or structure perturbation. The experiment has shown that the proposed approach outperforms SPIHT on both objective and subjective quality.