Title :
Edge-preserving neural network model for image restoration
Author :
Bao, Paul ; Wang, Dianhui
Author_Institution :
Dept. of Comput. Sci., Hong Kong Polytech. Univ., Hong Kong
Abstract :
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
Keywords :
edge detection; image coding; image restoration; multilayer perceptrons; SPIHT; artificial neural network; edge-preserving regularization; image compression; image restoration; multilayer perceptron model; neural network model; objective quality; subband coding; subjective quality; Artificial neural networks; Degradation; Discrete wavelet transforms; Image coding; Image reconstruction; Image restoration; Least squares approximation; Neural networks; Nonlinear equations; Partitioning algorithms;
Conference_Titel :
Signal Processing and Its Applications, 1999. ISSPA '99. Proceedings of the Fifth International Symposium on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
1-86435-451-8
DOI :
10.1109/ISSPA.1999.818134
