Please use this identifier to cite or link to this item:
DC FieldValueLanguage
dc.contributorJiunn-Lin Wuen_US
dc.contributor.authorTsai, Hsin-Cheen_US
dc.identifier.citation[1]W. H. Richardson, “Bayesian-based iterative method of image Restoration”, Journal of the Optical Society of America, Vol.62, No.1, pp.55–59, 1972. [2]R. Fergus, B. Singh, A. Hertzmann, S.T. Roweis, and W.T. Freeman, “Removing camera shake from a single photograph”, ACM Trans. Graph., Vol.25, No.3, 2006. [3]N. Joshi, R. Szeliski, and D.J. Kriegman, “PSF estimation using sharp edge prediction”, In Proc. CVPR, pp.1-8, 2008. [4]S. Cho, and S. Lee, “Fast motion deblurring”, ACM Trans. Graph., Vol.28, No.5, 2009. [5]L. Xu, and J. Jia, “Two-phase kernel estimation for robust motion deblurring”, In Proc. ECCV, pp.157-170, 2010. [6]L. Yuan, J. Sun, L. Quan, and H. Shum, “Image deblurring with blurred/noisy image pairs”, ACM Trans. Graph., Vol.26, No.3, 2007. [7]S. Zhuo, D. Guo, and T. Sim, “Robust flash deblurring”, In Proc. CVPR, pp.2440-2447, 2010. [8]A. Levin, R. Fergus, F. Durand, and W.T. Freeman, “Image and depth from a conventional camera with a coded aperture”, ACM Trans. Graph., Vol.26, No.3, 2007. [9]L. Yuan, J. Sun, L. Quan, and H. Shum, “Progressive inter-scale and intra-scale non-blind image deconvolution”, ACM Trans. Graph., Vol.27, No.3, 2008. [10]D. Krishnan, and R. Fergus, “Fast image deconvolution using hyper-Laplacian priors”, In Proc. NIPS, pp.1033-1041, 2009. [11]Q. Shan, J. Jia, and A. Agarwala, “High-quality motion deblurring from a single image”, ACM Trans. Graph., Vol.27, No.3, 2008. [12]Y. Wang, H. Feng, Z. Xu, Q. Li, and C. Dai, “An improved Richardson–Lucy algorithm based on local prior”, Optics and Laser Technology, Vol.42, No.5, pp.845–849, 2010. [13]T.S. Cho, N. Joshi, C.L. Zitnick, S.B. Kang, R. Szeliski, and W.T. Freeman, “A content-aware image prior”, In Proc. CVPR, pp.169-176, 2010. [14]J.H. Lee, and Y.S. Ho, “High-quality non-blind image deconvolution with adaptive regularization”, Journal of Visual Communication and Image Representation, Vol.22, No.7, pp.653–663, 2011. [15]Y. Wang, J. Yang, W. Yin, and Y. Zhang, “A new alternating minimization algorithm for total variation image reconstruction”, SIAM J. Imaging Sciences, Vol.1, No.3, pp.248-272, 2008. [16]R. Liu, and J. Jia, “Reducing boundary artifacts in image deconvolution”, In Proc. ICIP, pp.505-508, 2008. [17]A. Levin, Y. Weiss, F. Durand, and W.T. Freeman, “Understanding blind deconvolution algorithms”, IEEE Trans. Pattern Anal. Mach. Intell., Vol.33, No.12, pp.2354-2367, 2011. [18]Y. Tai, P. Tan, and M.S. Brown, “Richardson-Lucy deblurring for scenes under a projective motion path”, IEEE Trans. Pattern Anal. Mach. Intell., Vol.33, No.8, pp.1603-1618, 2011.en_US
dc.description.abstract  動態模糊(Motion blur)是拍攝數位影像時常見的缺陷之一,其為快門時間過長情況下,手持式相機因晃動或相對移動而導致影像模糊。模糊化過程可視為原始清晰影像和點擴散函數(Point Spread Function)進行卷積(Convolution)運算後所產生的結果,點擴散函數等同曝光時間中相機的晃動軌跡,假設其為位移不變的(Shift-Invariant),重建回清晰影像可以簡化為反卷積(Deconvolution)之問題。   然而,還原影像過程中常於邊緣附近產生漣波瑕疵(Ringing Artifacts),為了抑制瑕疵,導入影像先驗(Prior)資訊的正則化(Regularization)技巧被廣泛運用來約束求取最佳解,但當估計的點擴散函數具有誤差或尺寸過大,傳統的正則化方法在減少漣波的同時也會過度平滑化影像的細節。   本篇研究中考慮到需有效保留影像邊緣細節並抑制漣波生成,假設點擴散函數已知,我們提出基於適應性正則化的非盲目(Non-blind)反卷積法,想法在於根據影像區塊特性去調整正則化的權重係數大小。於步驟流程上,利用邊緣梯度的差異以計算出區塊參照地圖(Reference Map ),其可區分出輸入影像中的紋理及平坦區域,更可進一步指出紋理區域中的邊緣強弱資訊,於最佳化求解階段中,再依據上述區塊資訊給予適當的權重程度來約束還原回清晰影像。在實驗設計方面,則分別針對單張合成與真實模糊影像進行去模糊,結果顯示出我們所提之方法能重建回清晰銳利影像,也能有效抑制漣波瑕疵。zh_TW
dc.description.abstract  One of the most common defects in digital photography is motion blur caused by camera shake. Shift-invariant motion blur can be modeled as a convolution of the true latent image and a point spread function (PSF) with additive noise. The goal of image deconvolution is to reconstruct a latent image from a degraded image.   However, ringing is inevitable artifacts arising in the deconvolution stage. To suppress undesirable artifacts, regularization based methods have been proposed using natural image priors to overcome the ill-posedness of deconvolution problem. When the estimated PSF is erroneous to some extent or the PSF size is large, conventional regularization to reduce those ringing would lead to lose image details.   In this study, we focus on non-blind deconvolution by adaptive regularization which preserves image details, while suppressing ringing artifacts. The way is to control the regularization weight adaptively according to the image local characteristics. We adopt elaborated reference maps that indicate the edge strength so that textured and smooth regions can be distinguished. Then we impose an appropriate constraint on the optimization process. The experiments results on both synthesized and real images show that our method can restore latent image with much fewer ringing and favors the sharp edges.en_US
dc.description.tableofcontentsCHAPTER 1 Introduction 1 1.1. Background and Motivation 1 1.2. Organization of This Thesis 5 CHAPTER 2 Related Works 6 2.1. Richardson-Lucy Deconvolution 6 2.2. Image Pairs Deconvolution 7 2.3. Single Image Deconvolution 9 CHAPTER 3 The Proposed Method 14 3.1. Regularization Formulation 14 3.2. Reference Map Estimation 18 3.2.1. Image Pyramid Based Estimation 18 3.2.2. Discrete Wavelet Transform Based Estimation 21 3.3. Image Deconvolution With Adaptive Regularization 23 CHAPTER 4 Experimental Results 29 4.1. Parameters Setting 29 4.2. Synthetic Images 31 4.3. Real Blurred Images 36 CHAPTER 5 Conclusions 40 References 41zh_TW
dc.subjectNon-blind deconvolutionen_US
dc.subjectRinging artifactsen_US
dc.subjectLocal constrainten_US
dc.subjectAdaptive regularizationen_US
dc.titleAn Improved Adaptive Deconvolution Algorithm for Single Image Deblurringen_US
dc.typeThesis and Dissertationzh_TW
Appears in Collections:資訊科學與工程學系所


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.