×

Kullback-Leibler divergence based composite prior modeling for Bayesian super-resolution. (English) Zbl 1356.94025

Summary: This paper proposes to adaptively combine the known total variation model and more recent Frobenius norm regularization for multi-frame image super-resolution (SR). In contrast to existing literature, in this paper both the composite prior modeling and posterior variational optimization are achieved in the Bayesian framework by utilizing the Kullback-Leibler divergence, and hyper-parameters related to the composite prior and noise statistics are all determined automatically, resulting in a spatially adaptive SR reconstruction method. Experimental results demonstrate that the new approach can generate a super-resolved image with higher signal-to-noise ratio and better visual perception, not only image details better preserved but also staircase effects better suppressed.

MSC:

94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
62F15 Bayesian inference

Software:

RecPF
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ng, M.K., Shen, H., Lam, E.Y., Zhang, L.: A total variation regularization based super-resolution reconstruction algorithm for digital video. EURASIP J. Adv. Signal Process. (74585), 1-16 (2007) · Zbl 1168.94345
[2] Cristani, M., Cheng, D.S., Murino, V., Pannullo, D.: Distilling information with super-resolution for video surveillance. In: Proceedings of the ACM 2nd international workshop on Video surveillance and sensor, networks, pp. 2-11 (2004) · Zbl 1337.62303
[3] Li, F., Jia, X., Fraser, D., Andrew, L.: Super resolution for remote sensing images based on a universal hidden Markov tree model. IEEE Trans. Geosci. Remote Sens. 48(3), 1270-1278 (2010) · doi:10.1109/TGRS.2009.2031636
[4] Yang, J., Wright, J., Huang, T., Ma, Y.: Image superresolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861-2873 (2010) · Zbl 1371.94429 · doi:10.1109/TIP.2010.2050625
[5] Robinson, MD; Chiu, SJ; Lo, JY; Toth, CA; Izatt, JA; Farsiu, S.; Milanfar, Peyman (ed.), Novel applications of super-resolution in medical imaging, 383-412 (2010), Boca Raton
[6] Kang, M., Chaudhuri, S. (ed.): Super-resolution image reconstruction. IEEE Signal Process. Mag. 20(3), 19-20 (2003) · Zbl 1371.94018
[7] Milanfar, P.: Super-Resolution Imaging. CRC Press, New York (2011)
[8] Katsaggelos, A.K., Molina, R., Mateos, J.: Super Resolution of Images and Video. Morgan and Claypool, San Rafael (2007)
[9] Hardie, R.C., Barnard, K.J., Armstrong, E.E.: Join MAP registration and high resolution image estimation using a sequence of undersampled images. IEEE Trans. Image Process. 6(12), 1621-1633 (1997) · doi:10.1109/83.650116
[10] He, H., Kondi, L.P.: MAP based resolution enhancement of video sequences using a Huber-Markov random field image prior model. Int. Conf. Image Process. 3, 933-936 (2003)
[11] Marquina, A., Osher, S.J.: Image super-resolution by TV-regularization and Bregman iteration. J. Sci. Comput. 37(3), 367-382 (2008) · Zbl 1203.94014 · doi:10.1007/s10915-008-9214-8
[12] Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Trans. Image Process. 13(10), 1327-1344 (2004) · Zbl 1062.14065 · doi:10.1109/TIP.2004.834669
[13] Zeng, W.L., Lu, X.B.: A robust variational approach to super-resolution with nonlocal TV regularisation term. The Imaging Science Journal (2012) accepted · Zbl 1372.94145
[14] Babacan, S.D., Molina, R., Katsaggelos, A.K.: Variational Bayesian super resolution. IEEE Trans. Image Process. 20(4), 984-999 (2011) · Zbl 1372.94014 · doi:10.1109/TIP.2010.2080278
[15] Lefkimmiatis, S., Bourquard, A., Unser, M.: Hessian-based norm regularization for image restoration with biomedical applications. IEEE Trans. Image Process. 21(3), 983-995 (2012) · Zbl 1372.94145 · doi:10.1109/TIP.2011.2168232
[16] Lysaker, M., Tai, X.-C.: Iterative image restoration combining total variation minimization and a second-order functional. Int. J. Comput. Vision. 66(1), 5-18 (2006) · Zbl 1286.94021 · doi:10.1007/s11263-005-3219-7
[17] Yang, J., Zhang, Y., Yin, W.: A fast alternating direction method for TVL1-L2 signal reconstruction from partial fourier data. IEEE J. Sel. Top. Signal Process. 4(2), 288-297 (2010) · doi:10.1109/JSTSP.2010.2042333
[18] Shao, W.-Z., Deng, H.-S., Wei, Z.-H.: Multi-Parseval frame-based nonconvex sparse image deconvolution. Opt. Eng. 51(6), 067008-067008-12 (2012) · doi:10.1117/1.OE.51.6.067008
[19] Li, F., Shen, C., Fan, J., Shen, C.: Image restoration combining a total variational filter and a fourth-order filter. J. Visual Commun. Image Represent 18(4), 322-330 (2007) · doi:10.1016/j.jvcir.2007.04.005
[20] Mignotte, M.: Fusion of regularization terms for image restoration. J. Electron. Imaging 19, 033004 (2010) · doi:10.1117/1.3466799
[21] Afonso, M.V., Bioucas-Dias, J.M., Figueiredo, M.A.T.: Fast image recovery using variable splitting and constrained optimization. IEEE Trans. Image Process. 19(9), 2345-2356 (2010) · Zbl 1371.94018 · doi:10.1109/TIP.2010.2047910
[22] Villena, S., Vega, M., Babacan, S.D., Molina, R., Katsaggelos, A.K.: Using the Kullback-Leibler divergence to combine image priors in super-resolution image reconstruction. IEEE 17th international conference on image processing, pp. 893-896 (2010)
[23] Oliveira, J., Figueiredo, M., Bioucas-Dias, J.: Adaptative total variation image deblurring: a majorization-minimization approach. Signal Process. 89(9), 1683-1693 (2009) · Zbl 1178.94029 · doi:10.1016/j.sigpro.2009.03.018
[24] Tipping, M.E., Bishop, C.M.: Bayesian Image Super-Resolution. Advances in Neural Information Processing Systems (15). MIT Press, Cambridge (2003)
[25] Kanemura, A., Maeda, S.-I., Ishii, S.: Superresolution with compound Markov random fields via the variational EM algorithm. Neural Netw. 22(7), 1025-1034 (2009) · Zbl 1337.62303 · doi:10.1016/j.neunet.2008.12.005
[26] Pickup, L.C., Capel, D.P., Roberts, S.J., Zisserman, A.: Bayesian methods for image super-resolution. Comput. J. 52(1), 101-113 (2009) · doi:10.1093/comjnl/bxm091
[27] Zomet, A., Rav-Acha, A., Peleg, S.: Robust super-resolution. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 645-650 (2001)
[28] Shao, W. Z., Deng, H. S., Wei, Z. H.: A posterior mean approach for MRF-based spatially adaptive multi-frame image super-resolution. Signal Image Video Process. (2013). doi:10.1007/s11760-013-0458-x
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.