Independent component analysis and nongaussianity for blind image deconvolution and deblurring

Blind deconvolution or deblurring is a challenging problem in many signal processing applications as signals and images often suffer from blurring or point spreading with unknown blurring kernels or point-spread functions as well as noise corruption. Most existing methods require certain knowledge about both the signal and the kernel and their performance depends on the amount of prior information regarding the both. Independent component analysis (ICA) has emerged as a useful method for recovering signals from their mixtures. However, ICA usually requires a number of different input signals to uncover the mixing mechanism. In this paper a blind deconvolution and deblurring method is proposed based on the nongaussianity measure of ICA as well as a genetic algorithm. The method is simple and does not require prior knowledge regarding either the image or the blurring process, but is able to estimate or approximate the blurring kernel from a single blurred image. Various blurring functions are described and discussed. The proposed method has been tested on images degraded by different blurring kernels and the results are compared to those of existing methods such as Wiener filter, regularization filter, and the Richardson-Lucy method. Experimental results show that the proposed method outperform these methods.