Optimal Sparse Representations for Blind Deconvolution of Images
نویسندگان
چکیده
The relative Newton algorithm, previously proposed for quasi maximum likelihood blind source separation and blind deconvolution of one-dimensional signals is generalized for blind deconvolution of images. Smooth approximation of the absolute value is used in modelling the log probability density function, which is suitable for sparse sources. We propose a method of sparsification, which allows blind deconvolution of sources with arbitrary distribution, and show how to find optimal sparsifying transformations by training.
منابع مشابه
Optimal Dictionaries for Sparse Solutions of Multi-frame Blind Deconvolution
Abstract: Sparse representation of data has grown rapidly in signal processing. The benefits of sparse regularization are economy of representation of many different varieties of data, as well as control of difficult aspects of inverse problems, e.g., regularization of ill-conditioned inverse problems. Herein we represent atmospheric turbulence point-spread-functions by training optimal overcom...
متن کاملPSO-Optimized Blind Image Deconvolution for Improved Detectability in Poor Visual Conditions
Abstract: Image restoration is a critical step in many vision applications. Due to the poor quality of Passive Millimeter Wave (PMMW) images, especially in marine and underwater environment, developing strong algorithms for the restoration of these images is of primary importance. In addition, little information about image degradation process, which is referred to as Point Spread Function (PSF...
متن کاملFace Recognition in Thermal Images based on Sparse Classifier
Despite recent advances in face recognition systems, they suffer from serious problems because of the extensive types of changes in human face (changes like light, glasses, head tilt, different emotional modes). Each one of these factors can significantly reduce the face recognition accuracy. Several methods have been proposed by researchers to overcome these problems. Nonetheless, in recent ye...
متن کاملA novel framework method for non-blind deconvolution using subspace images priors
Non-blind deconvolution has been an active challenge in the research fields of computer vision and computational photography. However, most existing deblurring methods conduct direct deconvolution only on the degraded image and are sensitive to noise. To enhance the performance of non-blind deconvolution, we propose a novel framework method by exploiting different sparse priors of subspace imag...
متن کاملBayesian Blind Deconvolution with General Sparse Image Priors
We present a general method for blind image deconvolution using Bayesian inference with super-Gaussian sparse image priors. We consider a large family of priors suitable for modeling natural images, and develop the general procedure for estimating the unknown image and the blur. Our formulation includes a number of existing modeling and inference methods as special cases while providing additio...
متن کامل