跳到主要內容

臺灣博碩士論文加值系統

(3.235.185.78) 您好!臺灣時間:2021/07/27 16:57
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:林昭成
研究生(外文):Chao-Cheng Lin
論文名稱:基於大階梯邊緣的影像區塊選擇法於影像去模糊之研究
論文名稱(外文):A New Patch Selection Method for Image Deblurring Based on Large Step Edge
指導教授:吳俊霖吳俊霖引用關係
指導教授(外文):Jiunn-Lin Wu
口試委員:范育成韓斌
口試委員(外文):Yu-Cheng FanPin Han
口試日期:2015-07-23
學位類別:碩士
校院名稱:國立中興大學
系所名稱:資訊科學與工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:中文
論文頁數:46
中文關鍵詞:動態模糊大階梯邊緣區塊選擇法反卷積
外文關鍵詞:Motion BlurLarge Step EdgePatch SelectDeconvolution
相關次數:
  • 被引用被引用:0
  • 點閱點閱:145
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
動態模糊(Motion blur)是現在數位攝影拍攝中常遇到的問題,通常發生於光線不足的情況相機與移動物體的相對運動所造成的。因此如何有效解決動態模糊的問題也成為主要的研究方向之一。
影像去模糊(Image deblurring)在近幾年來在電腦視覺與影像處理領域上一直是重要的發展議題之一。大部分影像去模糊演算法是使用整張影像去估計出點擴散函數(Point Spread Function),再利用點擴散函數進行反卷積(Deconvolution)運算所產生的結果,使用整張影像去估計點擴散函數常常會造成相當大量的計算時間以及複雜的運算,並且這種方法得出的去模糊影像不一定會有最佳的結果,影像中許多部份更可能會使得估計的點擴散函數產生估計誤差。
為了防止這個問題,這本篇論文中我們提出一個基於大階梯邊緣(Large Step Edge)的影像區塊選擇法選出對於估計點擴散函數有用的區塊,首先我們先找出影像中大階梯邊緣的區塊,並利用這些區塊當作後選區,從這些候選區中計算影像中的梯度值,找出具有強邊緣且包含大階梯邊緣的區塊來做為估計點擴散函數的區塊,從實驗結果顯示我們的方法在模糊影像的點擴散函數估計和還原後的結果都能有良好的結果,並且能夠節省去模糊的時間以及獲得一張還原清晰的去模糊影像。


Motion blur is common problem in the field of digital photographing, usually happened in situations of insufficient light and relative movement of target object. It’s a main research way that how to solve the motion blur problem effect.
Image deblurring is a main development issue in the field of computer vision and image processing for the recent year. The common way of deblurring algorithm is that using a whole image to estimate the point spread function. Then using it to process deconvolution operation to generate the result. However, using the whole image to estimate the point spread function will cost a huge computing time and complex computing, and the result of deblurring image this way may not be the best one. Lots of the part in the image may cause inaccuracy of the point spread function.
To prevent the problem, we propose an image sector selecting function based on large step edge to select useful sector for estimating the point spread function. First, we find out the large and medium step edge sector of the image, and we mark this sector as second selecting sector. The finding out the strong edge including sector of large step edge as sector of estimating the point spread function based on the gradient value of these waiting selecting sector of computing image. Our method on blurring image of the point spread function cause good result on estimating and restoring, and it reduces the time of deblurring and getting a clear restored deblurring image.


第一章 緒論 1
1.1 研究背景及目的 1
1.2 論文架構 4
第二章 文獻探討 5
2.1 基於影像梯度的模糊影像區塊選擇法 5
2.2 自動調整影像梯度的模糊影像區塊選擇法 7
2.3 結合二階微分與影像梯度的模糊影像區塊選擇法 9
第三章 研究方法 11
3.1 取得影像中之大階梯邊緣 12
3.2 影像梯度計算與區塊選擇法 14
3.3點擴散函數的估計 15
3.4反卷積(DECONVOLUTION)影像還原計算 16
第四章 實驗結果及討論 19
第五章 結論與未來展望 44
參考文獻 45


[1]R. C. Gonzalez and R. E. Woods, Digital Image Processing (2nd Edition), Prentice Hall, 2002.
[2]Y. W. Tai and P. Tan, “Richardson-Lucy deblurring for scenes under a projective motion path”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.33, No.8, pp. 1603-1618, 2011
[3]L. Xu and J. Jia, “Depth-aware motion deblurring”, in Proc. IEEE International Conference on Computational Photography , pp.1-8, 2012.
[4]H.Y. Lin, K.J. Li and C.H. Chang, “ Vehicle speed detection from a single motion blurred image”, Image and Vision Computing, Vol.26, pp. 1327–1337, 2008.
[5]O. Whyte, J. Sivic, A. Zisserman, J. Ponce, “Non-uniform Deblurring for Shaken Images”, International Journal of Computer Vision, Vol.98, pp. 168-186, 2012.
[6]S. Zhuo and T. Sim, “Defocus map estimation from a single image”, Pattern Recognition, Vol. 44, pp. 1852–1858, 2011.
[7]Q. Shan, J. Jia, and A. Agarwala, "High-quality motion deblurring from a single image", Image and Vision Computing. , Vol.27, No.3, 2008.
[8]R. Fergus and B. Singh, "Removing camera shake from a single photograph", Image and Vision Computing., Vol.25, No.3, pp.787-794, 2006.
[9]S. Cho and S. Lee, "Fast motion deblurring", Image and Vision Computing., Vol.28, No.5, 2009.
[10]Li Xu, Jiaya Jia., “Two-Phase Kernel Estimation for Robust Motion Deblurring”, in Proc. European Conference on Computer Vision (ECCV), 2010
[11]H.S. Chang and M.P. Hyung. “A Pair of Noisy/blurry Patches-based PSF Estimation and Channel-dependent Deblurring”, IEEE Trans. Consum. Electron. Vol.57, pp. 1791-1799, 2011
[12]H. Zhang and Y. Zhang, “Multi-Observation Blind Deconvolution with an Adaptive Sparse Prior”, IEEE Trans on PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Vol 36, NO. 8, 2014
[13]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.
[14]D. Krishnan and R. Fergus, "Fast image deconvolution using hyper-Laplacian priors", in Proc. NIPS, pp.1033-1041, 2009.
[15]C. Zhou, S. Lin, and S. Nayar, “Coded aperture pairs for depth from defocus and defocus deblurring,” Int. J. Comput. Vis., Vol. 93, No. 1, pp. 53–72, 2011.
[16]X. Zhu, F. Sroubek, and P. Milanfar, “Deconvolving PSFs for a better motion deblurring using multiple images,” in Proc. 12th ECCV, Berlin, Germany, 2012.
[17]H. Zhang, D. P. Wipf, and Y. Zhang, “Multi-image blind deblurring using a coupled adaptive sparse prior,” in Proc. IEEE CVPR, Portland, OR, USA, 2013.
[18]W. Hu, J. Xue, and N. Zheng, “PSF estimation via gradient domain correlation,” in Proc.IEEE Trans. Image Process., Vol. 21, No. 1, pp. 386–392, Jan. 2012.
[19]D. Krishnan and R. Fergus, "Fast image deconvolution using hyper-Laplacian priors", Proc. NIPS, pp.1033-1041, 2009.
[20]Y. Wang, J. Yang, W. Yin, and Y. Zhang, "A new alternating minimization algorithm for total variation image reconstruction", SIAM Journal on Imaging Sciences, Vol. 1, pp.248-272, 2008.
[21]A. Levin, Y. Weiss, F. Durand and W.T. Freeman, "Understanding Blind Deconvolution Algorithms", IEEE Trans. PAMI, Vol. 33, No. 12, 2011.
[22]L. Yuan, J. Sun, L. Quan, and H. Shum, "Image deblurring with blurred/noisy image pairs", ACM Trans. Graph., Vol.26, No.3, 2007.
[23]S. Zhuo, D. Guo, and T. Sim, "Robust flash deblurring", in Proc. Computer Vision and Pattern Recognition , pp.2440-2447, 2010.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top