×

An additive convolution model for fast restoration of nonuniform blurred images. (English) Zbl 1307.62158

Summary: Nonuniform blurring would be introduced during imaging by many inevitable factors, such as defocus, camera shake, or motion. Fast restoration of nonuniform blurred images, however, remains a challenging problem. The sparse blur matrix-based approach models nonuniform blurring as the multiplication of a high-dimensional sparse blur matrix and an image vector, and suffers from the high computational and memory complexity problems. To tackle these, we propose an additive convolution model (ACM) which models nonuniform blurring as the space variant weighted sum of the convolution images of a set of basis filters. We further propose a principal component analysis-based method to learn the basis filters and weight matrices. Finally, we incorporate ACM with the total variation-based restoration model, and adopt the generalized accelerated proximal gradient algorithm for the restoration of nonuniform blurred images. Numerical results show that the proposed method is effective for the restoration of nonuniform blurred images caused by defocus or camera shake, and is superior to the sparse matrix-based approach in terms of computational and memory complexity.

MSC:

62H25 Factor analysis and principal components; correspondence analysis
62H35 Image analysis in multivariate analysis
68U10 Computing methodologies for image processing
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1109/TIP.2010.2047910 · Zbl 1371.94018 · doi:10.1109/TIP.2010.2047910
[2] DOI: 10.1109/TIP.2010.2076294 · Zbl 1372.94004 · doi:10.1109/TIP.2010.2076294
[3] DOI: 10.1137/080716542 · Zbl 1175.94009 · doi:10.1137/080716542
[4] DOI: 10.1109/TIP.2009.2028250 · Zbl 1371.94049 · doi:10.1109/TIP.2009.2028250
[5] DOI: 10.1109/TIP.2007.909319 · Zbl 05516510 · doi:10.1109/TIP.2007.909319
[6] DOI: 10.1080/00207160.2012.700400 · Zbl 1278.68327 · doi:10.1080/00207160.2012.700400
[7] DOI: 10.1007/978-1-4612-1490-8 · doi:10.1007/978-1-4612-1490-8
[8] DOI: 10.1080/00207160.2012.757073 · Zbl 1278.68329 · doi:10.1080/00207160.2012.757073
[9] DOI: 10.1002/cpa.20042 · Zbl 1077.65055 · doi:10.1002/cpa.20042
[10] DOI: 10.1109/TPAMI.2005.43 · Zbl 05110876 · doi:10.1109/TPAMI.2005.43
[11] P. Favaro and S. Soatto,3-D Shape Estimation and Image Restoration: Exploiting Defocus and Motion Blur, Springer-Verlag, London, 2007. · Zbl 1138.68632
[12] DOI: 10.1023/A:1022366408068 · Zbl 1009.68644 · doi:10.1023/A:1022366408068
[13] DOI: 10.1109/TPAMI.2007.1175 · Zbl 05340782 · doi:10.1109/TPAMI.2007.1175
[14] Gunturk B.K., Image Restoration: Fundamentals and Advances (2012) · Zbl 1252.68033
[15] Horn R.A., Matrix Analysis (1986)
[16] Jolliffe I.T., Principal Component Analysis (2002) · Zbl 1011.62064
[17] Kim S., Proceedings of IEEE Conference on Computer Vision and Pattern Recognition pp 25– (2012)
[18] DOI: 10.1109/TIP.2011.2181522 · Zbl 1373.94211 · doi:10.1109/TIP.2011.2181522
[19] DOI: 10.1038/44565 · Zbl 1369.68285 · doi:10.1038/44565
[20] DOI: 10.1109/TPAMI.2011.148 · doi:10.1109/TPAMI.2011.148
[21] DOI: 10.1109/TIP.2010.2041400 · Zbl 1371.94297 · doi:10.1109/TIP.2010.2041400
[22] DOI: 10.1109/34.777369 · doi:10.1109/34.777369
[23] DOI: 10.1109/TPAMI.2004.102 · Zbl 05112666 · doi:10.1109/TPAMI.2004.102
[24] DOI: 10.1016/0167-2789(92)90242-F · Zbl 0780.49028 · doi:10.1016/0167-2789(92)90242-F
[25] DOI: 10.1145/1360612.1360672 · Zbl 05457902 · doi:10.1145/1360612.1360672
[26] DOI: 10.1137/090779437 · Zbl 1219.94012 · doi:10.1137/090779437
[27] DOI: 10.3390/s110908536 · doi:10.3390/s110908536
[28] DOI: 10.1109/TPAMI.2010.222 · doi:10.1109/TPAMI.2010.222
[29] DOI: 10.1080/00207160.2012.688821 · Zbl 1278.94013 · doi:10.1080/00207160.2012.688821
[30] DOI: 10.1109/TIP.2003.819861 · Zbl 05453404 · doi:10.1109/TIP.2003.819861
[31] DOI: 10.1137/080724265 · Zbl 1187.68665 · doi:10.1137/080724265
[32] DOI: 10.1007/s11263-011-0502-7 · Zbl 1254.68287 · doi:10.1007/s11263-011-0502-7
[33] DOI: 10.1109/TIP.2011.2131665 · Zbl 1372.94320 · doi:10.1109/TIP.2011.2131665
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.