Asymmetric iterative blind deconvolution of multiframe images

Imaging through a stochastically varying distorting medium, such as a turbulent atmosphere, requires multiple short-exposure frames to ensure maximum resolution of object features. Restoration methods are used to extract the common underlying object from the speckle images, and blind deconvolution techniques are required as typically there is little prior information available about either the image or individual PSFs. A method is presented for multiframe restoration based on iterative blind deconvolution, which alternates between restoring the image and PSF estimates, A maximum-likelihood approach is employed via the Richardson-Lucy (RL) method which automatically ensures positivity and conservation of the total number of photons. The restoration is accelerated by applying a vector extrapolation technique that significantly reduces processing time while maintaining positivity. The distorted image sequence is treated as a 3D volume of data and processed to produce a 3D stack of PSFs and a single 2D image of the object. The problem of convergence to an undesirable solution, such as a delta function, is addressed by weighting the number of image or PSF iterations according to how quickly each is converging, this leads to the asymmetrical nature of the algorithm. Noise artifacts are suppressed by using a dampened RL algorithm to prevent over fitting of the corrupted data. Results are presented for real single frame and simulated multiframe speckle imaging.