請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72738
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 蔡志宏(Zsehong Tsai) | |
dc.contributor.author | Je-Yuan Chang | en |
dc.contributor.author | 張哲源 | zh_TW |
dc.date.accessioned | 2021-06-17T07:04:54Z | - |
dc.date.available | 2021-01-20 | |
dc.date.copyright | 2021-01-20 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2021-01-11 | |
dc.identifier.citation | [1] D. Krishnan and R. Fergus, “Fast Image deconvolution using hyper-Laplacian priors,” Advances in Neural Information Processing Systems, pp.1033-1041, 2009. [2] Y. Yan, W. Ren, Y. Guo, R. Wang, and X. Cao, “Image deblurring via extreme channels prior,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4003-4011, 2017. [3] J. Pan, Z. Hu, Z. Su, and M. H. Yang, “Deblurring text images via L0-regularized intensity and gradient prior,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901-2908, 2014 [4] C.T. Shen, W.L. Hwang and S.C. Pei, “Spatially-varying out-of-focus image deblurring with L1-2 optimization and a guided blur map,” IEEE International Conference on Acoustics, Speech and Signal Processing, pp.1067-1072, 2012. [5] D. Krishnan, T. Tay, and R. Fergus, “Blind deconvolution using a normalized sparsity measure,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 233-240, 2011. [6] J. Pan, Z. Hu, H. Pfister, and M. H. Yang, “Blind image deblurring using dark channel prior,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1628-1636, 2016. [7] J. Pan, R. Liu, Z. Su and X. Gu. “Kernel estimation from salient structure for robust motion deblurring,” Signal Processing: Image Communication, vol.28, pp. 1156-1170, 2013. [8] O. Whyte, J. Sivic, A. Zisserman, and J. Ponce, “Non-uniform deblurring for shaken images,” International Journal of Computer Vision, vol. 98, pp. 168-186, 2012. [9] L. Xu, S. Zheng, J. Jia, “Unnatural L0 sparse representation for naturalimage deblurring,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1107-1114, 2013. [10] M. Jin, S. Roth, P. Favaro, “Normalized blind deconvolution,” Proceedings of the European Conference on Computer Vision (ECCV), pp. 668-684, 2018. [11] C. C. Hsu, J. J. Ding, and Y. C. Lee, “Structural constraint and fast L0-L2 deconvolution for image deblurring,” Computer Vision, Graphics, and Image Processing, pp. 1-8, Aug. 2017. [12] J. Dong, J. Pan, Z. Su, and M. H. Yang, “Blind image deblurring with outlier handling,” Proceedings of the IEEE International Conference on Computer Vision, pp. 2478-2486, 2017. [13] F. Wen, R. Ying, Y. Liu, P. Liu, and T. K. Truong, “A simple local minimal intensity prior and an improved algorithm for blind image deblurring,” IEEE Transactions on Circuits and Systems for Video Technology, 2020 [14] J. Pan, J. Dong, Y. W. Tai, Z. Su, and M. H. Yang, “Learning discriminative data fitting functions for blind image deblurring,” Proceedings of the IEEE International Conference on Computer Vision, pp. 1068-1076, 2017. [15] D. J. C. MacKay, Information Theory, Inference, and Learning Algorithms, 1st ed., Cambridge University Press, pp. 34, 2003. [16] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd ed., Pearson Prentice Hall, pp. 128-138, 2008. [17] N. Wiener, “Extrapolation, interpolation, and smoothing of stationary time series: with engineering applications,” MIT Press, vol. 8, 1964. [18] W. H. Richardson, “Bayesian-based iterative method of image restoration,” Journal of the Optical Society of America, vol. 62, no. 1, pp.745-754, 1974. [19] L.B. Lucy, “An iterative technique for the rectification of observed distributions,” The Astronomical Journal, vol. 79, pp. 745-754, 1974. [20] D. A. Fish, A. M. Brinicombe, E. R. Pike and J. G. Walker, “Blind deconvolution by means of the Richardson–Lucy algorithm,” Journal of the Optical Society of America A., vol. 12, no. 1, pp. 58-65, 1995. [21] Y. Wang, J. Yang, W.Yin, and Y. Zhang, “A new alternating minimization algorithm for total variation image reconstruction,” Society for Industrial and Applied Mathematics Journal on Imaging Sciences, vol. 1, pp. 248-272, 2008. [22] S. Cho, and S. Lee, “Fast motion deblurring,” ACM SIGGRAPH Asia, pp. 1-8, 2009. [23] A. Levin, Y. Weiss, F. Durand, and W. T. Freeman, “Efficient marginal likelihood optimization in blind deconvolution,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 2657-2664, 2011. [24] R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman, “Removing camera shake from a single photograph,” ACM SIGGRAPH, pp. 787-794, 2006. [25] A. Beck, and M. Teboulle, “A fast iterative shrinkage-thresholding algorithm for linear inverse problems,” SIAM Journal on Imaging Sciences, vol. 2, no. 1, pp. 183-202, 2009. [26] A. Levin, R. Fergus, F. Durand, and W. T. Freeman, “Image and depth from a conventional camera with a coded aperture,” ACM Transactions on Graphics (TOG), vol. 26, no. 3, article 70, 2007 [27] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Conference on Computer Vision and Pattern Recognition, pp 1956–1963, 2009 [28] L. Xu, Q. Yan, Y. Xia, and J. Jia, “Structure extraction from texture via relative total variation,” ACM transactions on graphics (TOG), vol. 31, no. 6, pp. 1-10, 2012. [29] J. J. Ding, W. S. Lai, H. H. Chang, C.W. Chang, and C. C. Chang, “Edge adaptive hybrid norm prior method for blurred image reconstruction,” IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), pp. 276-279, 2014. [30] H. C. Ko, J. Y. Chang, and J. J. Ding, “Deep priors inside an unrolled and adaptive deconvolution model,” Proceedings of the Asian Conference on Computer Vision, 2020. [31] L. Xu and J. Jia, “Two-phase kernel estimation for robust motion deblurring,” European Conference on Computer Vision, pp. 157-170, 2010 [32] G. Xu, G. Zheng, X. Xie and K. Fan, “Kernel optimization based on salient region detection for image deblurring,” International Conference on Wireless, Mobile and Multi-Media, 2015. [33] Q. Shan, J. Jia, and A. Agarwala, “High-quality motion deblurring from a single image,” ACM Transaction on Graphics, vol. 27, no. 3, article 73, 2008. [34] C. Tomasi, and R. Manduchi, “Bilateral filtering for gray and color images,” IEEE International Conference on Computer Vision, pp. 839-846, 1998. [35] P. R. Tadikamalla, “A look at the Burr and related distributions,” International Statistical Review, vol. 48, no. 3, pp. 337–344, 1980. [36] L. Sun and J. Hays. “Super-resolution from internet-scale scene matching,” IEEE Conference on Computational Photography, pp. 1-12, 2012. [37] A. Levin, Y. Weiss, F. Durand, and W.T. Freeman, “Understanding and evaluating blind deconvolution algorithms,” IEEE Conference on Computer Vision and Pattern Recognition, pp.1964-1971, 2009. [38] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Processing, vol. 13, pp. 600-612, Apr. 2004. [39] K. Zhang, W. Zuo, S. Gu, and L. Zhang, “Learning deep CNN denoiser prior for image restoration,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 3929-3938, 2017. [40] J. Zhang, J. Pan, W. S. Lai, R. W. Lau, and M. H. Yang, “Learning fully convolutional networks for iterative non-blind deconvolution,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 3817-3825, 2017. [41] S. A. Bigdeli, M. Zwicker, P. Favaro, and M. Jin, “Deep mean-shift priors for image restoration,” Advances in Neural Information Processing Systems, pp. 763-772, 2017 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72738 | - |
dc.description.abstract | 影像解模糊採用先驗模型以解決不適定性問題。使用先驗模型解模糊的方法以加權因數來控制先驗正則化(regularization)的強度,而這加權因數通常被設為一常數。在這我們提出一個做法:將加權因數依各個影像像素的區域統計分佈而去調整加權因數的大小。這種依像素的區域統計分佈而去調整加權因數的方法可使影像解模糊的效果更好。我們提出了區域高斯分佈模型,可將解模糊目標函數的加權因數最佳化。我們共提出五種區域高斯分佈模型: 1. 超拉普拉斯(hyper-Laplacian)模型, 2. 分區調整模型, 3. Alpha-beta模型, 4. 查找表模型, 5. 布氏(Burr)直方圖模型。將區域高斯分佈模型與其他影像解模糊方法比較,區域高斯分佈模型可在結構相似性指標得較高的分數,在視覺效果上也有較佳的表現。 影像梯度直方圖在影像處理研究上有很多應用,但是來自戶外大自然的影像梯度直方圖很難用一個統計分佈去完全描述。我們提出用K-L散度來當量測統計分佈與梯度直方圖是否匹配的匹配指數。我們發現布氏(Burr)統計分佈比其他統計分佈更適合用於描述影像梯度直方圖。我們將布氏統計分佈應用於我們的布氏直方圖區域高斯分佈模型。在影像解模糊時,我們不必儲存整個參考梯度直方圖,而只需儲存三個布氏分佈參數就可取得參考梯度直方圖。有了參考梯度直方圖和模糊影像的梯度,我們就能用“梯度匹配”的方法去產生原始影像的估計梯度。有了原始影像的估計梯度,我們就能產生依各個影像像素的區域統計分佈而去調整的加權因數。這是我們如何將布氏統計分佈應用於影像梯度分佈的匹配。其他影像處理研究應該也可應用布氏(Burr)統計分佈與影像梯度分佈的良好匹配性。 | zh_TW |
dc.description.abstract | Image de-blurring utilizes the norm prior to solve the ill-posed problem. Most of the norm prior based image de-blurring methods use weighting factors to control the strength of the regularization. We present an idea is to make these weighting factors adaptive to pixel-wise local statistical distribution. By using these adaptive weighting factors, we can achieve better performance in image de-blurring. We propose a series of Local Gaussian Distribution Models (LGDM), that can be used to optimize the weighting factors in the objective function of image de-blurring. Five LGDMs are introduced here: hyper-Laplacian LGDM, region adaptive LGDM, alpha-beta LGDM, lookup table based LGDM, and Burr Histogram LGDM. We compare our methods with other state-of-the-art image de-blurring approaches. Our approach shows better in performance. The image gradient histogram has a lot of applications in image processing research. However, the image gradient histogram from natural scene is a curve too complex to be fully described by a statistical distribution. We propose to use the K-L divergence [15] (Kullback-Leibler divergence) as the matching index to measure the match between the statistical distribution and the gradient histogram. We find the Burr distribution outperforms other distributions by a great margin. This good matching feature of the Burr distribution is applied to our Burr histogram LGDM. Instead of storing whole reference gradient histogram for image de-blurring, we can use three optimized Burr distribution parameters to represent the reference histogram. With the reference histogram and the gradient of blurred image, we can use the Histogram Matching method [16] to produce an estimated gradient latent image. This demonstrates one area to apply the Burr distribution for gradient distribution approximation. There should be other image processing research which can utilize the good matching feature of the Burr distribution. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T07:04:54Z (GMT). No. of bitstreams: 1 U0001-0801202111014300.pdf: 4182141 bytes, checksum: e8e678e2ff1304b98b48976e969a68f9 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 誌謝 i 中文摘要 ii ABSTRACT iii CONTENTS v LIST OF FIGURES vii LIST OF TABLES ix Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Primary Contribution 2 Chapter 2 Review of Image De-blurring Methods 4 2.1 Wiener Filter [17] 4 2.2 Richardson-Lucy Method [18][19][20] 6 2.3 Hyper-Laplacian Prior [1] 7 2.4 L0-regularized Intensity and Gradient Prior [3] 8 2.5 L1-L2 Normalized Gradient Prior [5] 11 2.6 Dark Channel Prior [6] 13 2.7 Dual-L0 Kernel Estimation and L0-L2 Gradient Priors [11] 16 Chapter 3 Proposed De-blurring Models 18 3.1 Hyper-Laplacian LGDM 20 3.2 Region Adaptive LGDM 21 3.3 Alpha-beta LGDM 22 3.4 Lookup Table Based LGDM 23 3.5 Ringing Suppression 25 3.5.1 Experiment on Ringing Suppression 26 3.6 Symbol Table 27 Chapter 4 Proposed De-blurring Models with Burr Distribution 29 4.1 Use Burr Distribution to Represent Histogram 29 4.2 Burr Distribution 31 4.3 Optimize Burr Parameters to Match Histogram 34 4.4 Burr Histogram LGDM 35 Chapter 5 Experiments 38 5.1 Experiment Results 38 Chapter 6 Conclusion 62 REFERENCE 64 | |
dc.language.iso | en | |
dc.title | 應用於影像解模糊的區域高斯分佈模型 | zh_TW |
dc.title | Local Gaussian Distribution Models for Image De-blurring | en |
dc.type | Thesis | |
dc.date.schoolyear | 109-1 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 丁建均(Jian-Jiun Ding) | |
dc.contributor.oralexamcommittee | 黃振康(Chen-Kang Huang),郭景明(Jing-Ming Guo) | |
dc.subject.keyword | 區域高斯模型,影像解模糊,先驗模型,布氏(Burr)統計分佈,影像梯度直方圖,K-L散度, | zh_TW |
dc.subject.keyword | Local Gaussian Models,Image De-Blurring,Norm Priors,Burr Distribution,Image Gradient Histogram, | en |
dc.relation.page | 68 | |
dc.identifier.doi | 10.6342/NTU202100031 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2021-01-12 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-0801202111014300.pdf 目前未授權公開取用 | 4.08 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。