Restoring Multisource Degraded Image Based on the Wavelet-domain Projection Pursuit Network

The Wavelet-Domain Projection Pursuit Learning Network(WDPPLN) is proposed for resolving the difficult task to restore image, which is blurred by multisource degraded factors. The new approach combines the advantages of both the projection pursuit and the wavelet shrinkage technique. By separately processing wavelet coefficients and scale coefficients, the WDPPLN resolves the problem of restoring image very well, when little is known about the prior knowledge for multisource degraded factors. The WDPPLN estimates the degraded factor, which blurred image, by using Projection Pursuit Learning Network (PPLN). Also, it suppresses the noise with the soft-threshold of the wavelet shrinkage technique. The results are compared with that of the traditional methods and the PPLN method in visual effect and objective evaluation criterion (SNR). Experiment results show that it is an effective method for restoring multisource degraded image.