Computationally efficient multiframe Wiener filtering algorithms that account for both intraframe (spatial) and interframe (temporal) correlations are proposed for restoring image sequences that are degraded by both blur and noise. One is a general computationally efficient multiframe filter, the cross-correlated multiframe (CCMF) Wiener filter, which directly utilizes the power and cross power spectra of only N*N matrices, where N is the number of frames used in the restoration. In certain special cases the CCMF lends itself to a closed-form solution that does not involve any matrix inversion. A special case is the motion-compensated multiframe (MCMF) filter, where each frame is assumed to be a globally shifted version of the previous frame. In this case, the interframe correlations can be implicitly accounted for using the estimated motion information. Thus the MCMF filter requires neither explicit estimation of cross correlations among the frames nor matrix inversion. Performance and robustness results are given. >

Efficient multiframe Wiener restoration of blurred and noisy image sequences

A method for performing multiframe Wiener restoration of noisy and blurred image sequences that provides either a cross-correlated multiframe Wiener restoration or a motion-compensated multiframe Wiener restoration. The cross-correlated multiframe restoration uses interframe correlations explicitly through the estimated cross-power spectra of the frames, and is computationally efficient in its calculation of the Wiener estimate by using either a closed form solution or using a small-size matrix inversion. The motion-compensated multiframe Wiener restoration is used when the interframe motion is a global shift which is either known a priori, or estimated using a motion estimation algorithm. The motion-compensated multiframe Wiener filter has a closed-form solution and does not require any matrix inversion.

Method for multiframe Wiener restoration of noisy and blurred image sequences

An algorithm is described for reconstructing images from colour sensor samples, which need not be aligned nor conform to a rectangular sampling geometry. The algorithm has applications in de-mosaicing digital camera color filter array (CFA) data, and processing other imaging modalities such as scanned images and captured video. A unique scale invariant WSS prior model is described for the uncorrupted surface spectral reflectance functions and used to form linear least mean squared error (LLMSE) optimal reconstructions with constrained support operators. Some important results are established concerning the existence and tractability of the solutions based on this prior.

Generalized Wiener reconstruction of images from colour sensor data using a scale invariant prior

In this correspondence, a constrained least-squares multichannel image restoration approach is proposed, in which no prior knowledge of the noise variance at each channel or the degree of smoothness of the original image is required. The regularization functional for each channel is determined by incorporating both within-channel and cross-channel information. It is shown that the proposed smoothing functional has a global minimizer.

Simultaneous multichannel image restoration and estimation of the regularization parameters

The validity of a multichannel deconvolution technique where both within and between channel relations are used was demonstrated using stochastic and deterministic deconvolution filters. In either case, prior knowledge about the original image and the noise is required. A generalized regularized multichannel image deconvolution approach is proposed in which no prior knowledge of the variance of the noise at each channel or a bound on the high-frequency energy of the image are assumed. This information instead is estimated iteratively, resulting also in the estimation of the regularization parameters, based on the partially deconvolved image at each iteration step. The multichannel smoothing functional to be minimized is formulated to have a global minimizer with the proper choice of the multichannel regularization functionals. With this algorithm, the regularization functional for each channel is determined by incorporating not only within-channel information but also cross-channel information. The proposed multichannel smoothing functional is shown to be convex, and therefore, has a global minimizer. The algorithm not only does not depend on initial conditions but is also shown to be much more computationally efficient than existing algorithms. The validity and efficiency of the approach is demonstrated by applying it to color image restoration, the wavelet-based image deconvolution, and the reconstruction of the higher resolution image.

Generalized multichannel image deconvolution approach and its applications

The sensitivity to the spectral estimate of the original image of linear minimum mean-square error (LMMSE) color image restoration methods is determined. It is concluded that (i) sensitivity of the full-correlation Wiener restoration to the spectral estimate is higher than that of the independent-channel Wiener restoration, and the full-correlation restoration is extremely sensitive to windowing, (ii) among independent-channel restorations, the ones based on autoregressive spectral estimates are the least sensitive, and (iii) full-correlation Wiener restoration may be outperformed by the independent-channel restoration depending on the prototype image used in spectral estimation. >

D. Tran

Papers

Sensitivity of color LMMSE restoration of images to the spectral estimate