Browse > Article
http://dx.doi.org/10.7471/ikeee.2017.21.1.46

Fast Patch-based De-blurring with Directional-oriented Kernel Estimation  

Min, Kyeongyuk (Dept. of Electronics Engineering, Hanyang University)
Chong, Jongwha (Dept. of Electronics Engineering, Hanyang University)
Publication Information
Journal of IKEEE / v.21, no.1, 2017 , pp. 46-65 More about this Journal
Abstract
This paper proposes a fast patch-based de-blurring algorithm including kernel estimation based on the angle between the edge and the blur direction. For de-blurring, image patches from the most informative edges in the blurry image are used to estimate a kernel with low computational cost. Moreover, the kernels of each patch are estimated based on the correlation between the edge direction and the blur direction. This makes the final kernel more reliable and creates an accurate latent image from the blurry image. The combination of directionally oriented kernel estimation and patch-based de-blurring is faster and more accurate than existing state-of-the art methods. Experimental results using various test images show that the proposed method achieves its objectives: speed and accuracy.
Keywords
de-blurring; edge direction; image restoration; kernel estimation; motion blur;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. S. Lee and J. Lin, "Fast K-means clustering using direction by center displacement and norms product (CDNP)," Pattern Recognition and Image Analysis, vol. 23, no. 2, pp. 199-206, Apr. 2013. DOI:10.1134/S1054661813020144   DOI
2 http://statinfer.wordpress.com/2011/12/12/efficient-matlab-ii-kmeans-clustering-algorithm/.
3 D. Krishnan, T. Tay and R. Fergus, "Blind deconvolution using a normalized sparsity measure," IEEE Conf. Computer Vision and Pattern Recognition, pp. 233-240, Jun. 2011. DOI: 10.1109/CVPR.2011.5995521   DOI
4 A. Beck and M. Teboulle, "A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems," SIAM Journal on Image Sciences, vol. 2, no. 1, pp. 183-202, Jan. 2009. DOI:10.1137/080716542   DOI
5 Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, "Image quality assessment: From error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, Apr. 2004. DOI: 10.1109/TIP.2003.819861   DOI
6 D. Demaine, D. Harmon, J. Iacono, D. Kane and M. Patrascu, "The geometry of binary search trees," Proceedings of the 20th Annual ACM-SIAM Symposium on Discrete Algorithms, pp.496-505, Jan. 2009.
7 D. Krishnan and R. Fergus, "Fast image deconvolution using hyper-laplacian priors," NIPS, pp.1033-1041, Dec. 2009.
8 http://en.wikipedia.org/wiki/Regularization(mathematics)
9 T. Andrew, "Computation Time Comparison Between Matlab and C++ Using Launch Windows," Aerospace Engineering, California Polytechnic State University, San Luis.
10 L. Zhong, S.H. Cho, D.N. Metaxas, S. Paris and J. Wang, "Handling Noise in Single Image Deblurring Using Directional Filter," " IEEE Conf. Computer Vision and Pattern Recognition, pp.612-619, 2013.
11 Levin, Y. Weiss, F. Durand and W. T. Freeman, "Understanding Blind Deconvolution Algorithms," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2354-2367, Dec. 2011. DOI: 10.1109/TPAMI.2011.148   DOI
12 R. Lokhande, K. V. Arya and P. Gupta, "Identification of parameters and restoration of motion blurred images," ACM Symposium on Applied Computing, pp. 301-305, 2006. DOI:10.1145/1141277.1141347   DOI
13 N. Joshi, R. Szeliski and D. Kriegman, "PSF estimation using sharp edge prediction," IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, Jun. 2008. DOI: 10.1109/CVPR.2008.4587834   DOI
14 A. Levin, "Blind Motion Deblurring Using Image Statistics," In Advances in Neural Information Processing Systems, Dec. 2006.
15 A. Levin, R. Fergus, F. Durand and W. Freeman, "Image and depth from a conventional camera with a coded aperture," ACM SIGGRAPH, vol. 26, no. 3, pp.70-79, Jul. 2007. DOI:10.1145/1276377.1276464   DOI
16 Q. Shian, J. Jia and A. Agarwala, "High-quality Motion Deblurring from a Single Image," ACM SIGGRAPH, vol. 27, no. 3, pp. 1-10, Jul. 2008.DOI:10.1145/1360612.1360672   DOI
17 A. Levin and Y. Weiss, "User assisted separation of reflections from a single image using a sparsity prior," PAMI, vol. 29, no. 9, pp.1647-1654, Sep. 2007. DOI: 10.1109/TPAMI.2007.1106   DOI
18 A. Levin, Y. Weiss, F. Durand and W.T.Freeman, "Understanding and evaluating blind deconvolution algorithms," IEEE Conf. Computer Vision and Pattern Recognition, pp.1964-1971, Jun. 2009. DOI: 10.1109/CVPR.2009.5206815   DOI
19 R. Fergus, B. Singh, A. Hertzmann, S. T. Toweis and W. T. Freeman, "Removing camera shake from a single photograph," ACM SIGGRAPH, vol. 25, no. 3, pp. 787-794, Jul. 2006. DOI:10.1145/1141911.1141956   DOI
20 L. Yuan, J. Sun, L. Quan and H. Y. Shum, "Image deblurring with blurred/noisy image pairs," ACM SIGGRAPH, vol. 26, no. 3, pp. 1-10, Jul. 2007.DOI:10.1145/1276377.1276379   DOI
21 H. H. Bae, C. Fowlkes and P. H. Chou, "Patch mosaic for fast motion deblurring," Asian Conference on Computer Vision, pp. 322-335, Nov. 2012.DOI:10.1007/978-3-642-37431-9_25   DOI
22 S. H. Cho, J. Wang and S. Y. Lee, "Handling Outliers in Non-blind Image Deconvolution," IEEE Conf. Computer Vision, pp. 1-8, 2011. DOI: 10.1109/ICCV.2011.6126280   DOI
23 S. H. Chon and S. Y. Lee, "Fast motion deblurring," ACM SIGGRAPH, vol. 28, no. 5, Dec. 2009.DOI:10.1145/1618452.1618491   DOI
24 L. Xu and J. Jia, "Two-phase kernel estimation for robust motion deblurring," ECCV, vol. 6311, pp. 157-170, 2010. DOI:10.1007/978-3-642-15549-9_12   DOI
25 G. Zeng, "Fast approximate k-means via cluster closures," IEEE Conf. Computer Vision and Pattern Recognition, pp. 3037-3044, 2012. DOI:10.1007/978-3-319-14998-1_17   DOI
26 J. Jia, "Single Image Motion Deblurring Using Transparency," IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, Jun. 2007.DOI: 10.1109/CVPR.2007.383029   DOI
27 T. S. Cho, "Motion blur removal from photographs," Ph.D. dissertation, CSAIL, MIT, Cambridge, MA, 2010.
28 X. Zhang, X. Feng, W. Wang and W. Xue, "Edge Strength Similarity for Image Quality Assessment," IEEE Signal Processing Letters, vol. 20, no. 4, pp. 319-322, Apr. 2013.DOI: 10.1109/LSP.2013.2244081   DOI
29 G. Mantena and X. Anguera, "Speed improvements to Information Retrieval-based dynamic time warping using hierarchical K-Means clustering," IEEE ICASSP, pp. 8515-8519, May. 2013. DOI: 10.1109/ICASSP.2013.6639327   DOI
30 A. K. Jain, "Data clustering: 50 years beyond K-means," Pattern Recognition Letters, vol. 31, no. 8, pp. 651-666, Jun. 2010. DOI:10.1016/j.patrec.2009.09.011   DOI