Other Research Areas

Blind Image Restoration

Blind Image Restoration

The goal of image restoration is to reconstruct the original (ideal) scene from a degraded observation. The recovery process is critical to many image processing applications. Ideally, image restoration aims to undo the image degradation process during image acquisition and processing. If degradation is severe, it may not be possible to completely recover the original scene, but partial recovery may be plausible.

Typical forms of  degradation during image acquisition involve blurring and noise. The blurring may be from, for example, sensor motion or out-of-focus cameras. In such a situation, the blurring function (called a point-spread function) must be known prior to image restoration. When this blurring function is unknown, the image restoration problem is called blind image restoration.

Blind image restoration is the process of simultaneously estimating both the original image and point-spread function using partial information about the image processing and possibly even the original image. The various approaches that have been proposed depend upon the particular degradation and image models.

Our research focuses on the development and analysis of the non-negativity and support-constraints recursive inverse filtering (NAS-RIF) algorithm. The approach applies to images of finite known support (e.g., images you would commonly find on websites such as amazon). In this technique an adaptive finite impulse response (FIR) filter is used to adaptively de-blur a degraded image. Adaptation of the filter is based on an error function that measures the distance of the recovery estimate (i.e., output of the adaptive filter) from the known image information (i.e., it’s support). Convergence of the algorithm to the optimal solution is guaranteed due to the convexity of the cost function used for adaptation. Noise amplification is observed and early termination prevents excessive artifacts from resulting.

Many extensions of this work exist.

Related Publications

D. Kundur; D. Hatzinakos

On the use of Lyapunov Criteria to Analyze the Convergence of Blind Deconvolution Algorithms Journal Article

IEEE Transactions on Signal Processing, 26 (10), pp. 2918-2925, 1998.

BibTeX | Links:

D. Kundur; D. Hatzinakos

Semi-Blind Image Restoration Based on Telltale Watermarking Inproceedings

Proc. Asilomar Conference on Signals, Systems and, Computers, pp. 933-937, Pacific Grove, California, 1998.

BibTeX | Links:

D. Kundur; D. Hatzinakos

A Novel Blind Deconvolution Scheme for Image Restoration using Recursive Filtering Journal Article

IEEE Transactions on Signal Processing, 46 (2), pp. 375-390, 1998.

BibTeX | Links:

D. Kundur; D. Hatzinakos

Blind Image Deconvolution Revisited Journal Article

IEEE Signal Processing Magazine, 13 (6), pp. 61-63, 1996.

BibTeX | Links:

D. Kundur; D. Hatzinakos

On the Global Asymptotic Stability of the NAS-RIF Algorithm for Blind Image Restoration Inproceedings

Proc. IEEE International Conference on Image Processing (ICIP), pp. 73-76, Lausanne, Switzerland, 1996.

BibTeX | Links:

D. Kundur; D. Hatzinakos

Blind Image Deconvolution Journal Article

IEEE Signal Processing Magazine, 13 (3), pp. 43-64, 1996.

BibTeX | Links:

D. Kundur; D. Hatzinakos

Blind Image Restoration via Recursive Filtering using Deterministic Constraints Inproceedings

Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2283-2286, Atlanta, Georgia, 1996.

BibTeX | Links:

D. Kundur; D. Hatzinakos

A Novel Recursive Filtering Method for Blind Image Restoration Inproceedings

Proc. IASTED International Conference on Signal and Image Processing (SIP), pp. 428-431, Las Vegas, Nevada, 1995.

BibTeX | Links: