Resolution enhancement via probabilistic deconvolution of multiple degraded images

Authors:
F. Šroubek;J. Flusser
Affiliations:
Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod vodárenskou ví 4, 182 08, Prague 8, Czech Republic;Institute of Information Theory and Automation, Academy of Sciences of the Czech Republic, Pod vodárenskou ví 4, 182 08, Prague 8, Czech Republic
Venue:
Pattern Recognition Letters - Special issue: Pattern recognition in remote sensing (PRRS 2004)
Year:
2006

Citing 11
Cited 3

Recursive Model-Based Image Restoration

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Deterministic edge-preserving regularization in computed imaging

IEEE Transactions on Image Processing
Total variation blind deconvolution

IEEE Transactions on Image Processing
Perfect blind restoration of images blurred by multiple filters: theory and efficient algorithms

IEEE Transactions on Image Processing
Blind identification of multichannel FIR blurs and perfect image restoration

IEEE Transactions on Image Processing
Efficient generalized cross-validation with applications to parametric image restoration and resolution enhancement

IEEE Transactions on Image Processing
On eigenstructure-based direct multichannel blind image restoration

IEEE Transactions on Image Processing
Multichannel blind iterative image restoration

IEEE Transactions on Image Processing
Multichannel blind image deconvolution using the Bussgang algorithm: spatial and multiresolution approaches

IEEE Transactions on Image Processing
Multichannel blind deconvolution of spatially misaligned images

IEEE Transactions on Image Processing
Blur identification by the method of generalized cross-validation

IEEE Transactions on Image Processing

Panchromatic sharpening of remote sensing images using a multiscale Kalman filter

Pattern Recognition
Accurate image registration for MAP image super-resolution

Image Communication
Single image super-resolution based on space structure learning

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a maximum a posteriori solution to the problem of obtaining a high-resolution image from a set of degraded low-resolution images of the same scene. The proposed algorithm has the advantage that no prior knowledge of blurring functions is required and it can handle unknown misregistrations between the input images. An efficient implementation scheme of alternating minimizations is presented together with experiments that demonstrate the performance of the algorithm.