A modified image restoration algorithm for multiframe degraded images
Zexun Geng, Zhenlei Zhao, Xiang Rong Song · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2009
A modified multiframe image restoration algorithm of degraded images is described in this paper, which is based on the method developed by V. Katkovnik. The projection gradient algorithm based on anisotropic LPA-ICI filtering, being proposed by V. Katkovnik, could only restore images contaminated by Gaussian noisy, also it was too complicated and time consuming. By improving Katkovnik's cost function and applying constraints on image intensity value in iteration, we reached a new multiframe recursive iteration restoration scheme in frequency domain. This method is suitable for reconstruction of images degenerated by both Gaussian noise and Poissonian noise, as well by mixed noise. Experimental results demonstrated that this method works efficiently, and could well restore images blurred heavily by multi-noise.