SURE-Based Projections Onto Convex Sets for Image Restoration

• Autorzy: Deng C. , Tian W. , Wang S. , Hu S. , Rao W. , Li Y.

Warianty tytułu

PL

Zastosowanie estymatora SURE w metodzie POCS do odtwarzania obrazów

• Języki publikacji: EN

Abstrakty

EN

Projections onto convex sets (POCS) algorithms have been widely used for image restoration problem. However, the relaxation parameter of POCS is strongly data-dependent and difficult to tune. In this work we focus on optimally selecting such parameter in POCS algorithm for image restoration. A stein’s unbiased risk estimate (SURE) based POCS (SPOCS) for image restoration algorithm is proposed, in which SURE is used to determine an optimal value. Finally, the effectiveness of the optimality of the proposed parameter selection is tested by image restoration experiments.

PL

W artykule przedstawiono metodę optymalnego doboru parametru relaksacji dla algorytmu POCS, służącego do odtwarzania obrazów. W proponowanym rozwiązaniu (SPOCS) zastosowano estymator Stein’a (SURE), służący do wyznaczenia optymalnej wartości współczynnika lambda. Działania algorytmu zostało zbadane eksperymentalnie.

Słowa kluczowe

EN

image restoration; convex set; risk estimation

PL

odtwarzanie obrazów; estymator Stein'a; metoda POCS

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2013
• Tom: R. 89, nr 5
• Strony: 167--170
• Opis fizyczny: Bibliogr. 11 poz., rys., tab.

Twórcy

autor

Deng C.

• Nanchang Institute of Technology, Department of Information Engineering

autor

Tian W.

• Nanchang Institute of Technology, Department of Information Engineering

autor

Wang S.

• Nanchang Institute of Technology, Department of Information Engineering

autor

Hu S.

• Nanchang Institute of Technology, Department of Information Engineering

autor

Rao W.

• Nanchang Institute of Technology, Department of Information Engineering

autor

Li Y.

• Nanchang Institute of Technology, Department of Information Engineering

Bibliografia

• [1] Galatsanos N. P., Katsaggelos A. K., Methods for choosing the regularization parameter and estimating the noise variance in image restoration and their relation, IEEE Trans. Image Process., 1 (1992), No. 3, 322-336.
• [2] Yang S. Y., Liu B. Y., Image deblurring using weighted total variation regularisation for half-quadratic model, Electronics Letters, 47 (2011), No. 22, 133-134.
• [3] Bioucas-Dias J. M., Bayesian wavelet-based image deconvolution: A GEM algorithm exploiting a class of heavytailed priors, IEEE Trans. Image Process., 15 (2006), No. 4, 937-951.
• [4] Afonso M. V., Bioucas-Dias J. M., Figueiredo M. A., An augmented lagrangian approach to the constrained optimization formulation of image inverse problems, IEEE Trans. Image Process., 20 (2011), No. 3, 681-695.
• [5] Eren P. E., Sezan M. I., Tekalp A. M., Robust, object-based high-resolution image reconstruction from low-resolution video, IEEE Trans. Image Process., 6 (1997), No. 10, 1446-1451.
• [6] Jiang M., Zhang M., Review on POCS algorithms for image reconstruction, Computerized Tomography Theory and Applications, 12(2003), No. 1, 51–55.
• [7] Pana J. P., Fonseca L. M. G., Carvalho L. A. S., Projection onto convex sets through particle swarm optimization and its application for remote sensing image restoration, Pattern Recognition Letters, 31 (2010), No. 13, 1876-1886.
• [8] Qu G., Wang C., Jiang M., Necessary and sufficient convergence conditions for algebraic image reconstruction algorithms, IEEE Trans. Image Process., 18 (2009), No. 2, 435-440.
• [9] Luisier F., Blu T., Unser M., A new SURE approach to image denoising: Interscale orthonormal wavelet thresholding, IEEE Trans. Image Process., 16(2007), No. 3, 593-606.
• [10] Eldar Y. C., Generalized SURE for exponential families: Applications to regularization, IEEE Trans. Signal Process., 57(2009), No. 2, 471-481.
• [11] Donoho D. L., Johnstone I. M., Ideal spatial adaptation via wavelet shrinkage, Biometrika, 81(1994), No. 3, 425-355.