Semi-Blind Image Restoration using a Local Neural Approach

I. Gallo, E. Binaghi, and M. Raspanti (Italy)


Image restoration, deconvolution, neural network


This work aims to define and experimentally evaluate an it erative strategy based on neural learning for semi-blind im age restoration in the presence of blur and noise. A salient aspect of our solution is the local estimation of the restored image based on gradient descent strategies. This method can be viewed as a neural strategy where the pixels of the restored image are the synapse’s weights that the neural network tries to modify during learning to minimize the output error measure; the learning strategy adopted is un supervised. The method was evaluated experimentally us ing a test pattern generated by a checkerboard function in Matlab. To investigate whether the strategy can be consid ered an alternative to conventional restoration procedures, the results were compared with those obtained by a well known neural restoration approach.

Important Links:

Go Back