(3.230.154.160) 您好!臺灣時間:2021/05/07 23:13
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:::

: 
twitterline
研究生:陳冠任
研究生(外文):Kuan-Jen Chen
論文名稱:使用梯度學習法於單張影像去模糊之研究
論文名稱(外文):A Study of Single Image Deblurring Using Gradient-Based Learning
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:林惠勇韓斌
口試日期:2016-07-27
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:2016
畢業學年度:104
語文別:中文
論文頁數:43
中文關鍵詞:影像去模糊盲目影像反卷積邊緣補片影像金字塔
外文關鍵詞:Motion BlurBlind Image DeconvolutionEdge PatchImage Pyramid
相關次數:
  • 被引用被引用:0
  • 點閱點閱:122
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:11
  • 收藏至我的研究室書目清單書目收藏:0
動態模糊(Motion Blur)在現今的數位攝影中是一個常見的問題。在拍攝環境光源不足時,為了有較好的結果而增加曝光時間,因曝光時間較長在未有腳架輔助的狀況下,會因相機的晃動產生動態模糊的破壞。因此影像去模糊(Image Deblurring)在電腦視覺與影像處理領域上一直是個重要的發展議題。

假設模糊影像中的每一個像素點模糊破壞一致,則此模糊影像可以假設為清晰影像和拍攝時移動軌跡進行卷積(Convolution)運算的結果。而在曝光時間中相機的晃動軌跡即為點擴散函數(Point Spread Function)。在多數情況下我們不會有已知的點擴散函數,因此選用盲目的影像反卷積(Blind Image Deconvolution)的方法來還原動態模糊的影像,我們使用補片(Edge patch)增強的去動態模糊方法來進行影像去模糊,此方法可以估計出良好的點擴散函數(Point Spread Function)並還原良好的結果,但是仍會有漣波(Ringing)的破壞產生。因此本研究針對動態模糊的影像去模糊,提出了結合補片增強和雙邊濾波器的去模糊演算法。利用補片增強來還原模糊的邊緣,並使用雙邊濾波器(Bilateral Filter)來消除會影響點擴散函數估計的雜訊。最後採用影像金字塔(Image Pyramid)的架構來進行影像去模糊的程序。我們期望所提的方法可以估計出更精確的點擴散函數,且減少漣波的破壞產生,進而得到一張清晰的去模糊影像。


Motion blur is one of the common defects in digital photography. While there is not enough light, we need to use long shutter speed for the good image quality. Take a photo with long shutter speed and without camera tripod, it may result in a motion blur image.

To solve this problem, image deblurring is an active topic in computational photography and image processing fields. A blurred image can be modeled as unblurred image convolutes the movement of camera (or called the point spread function), if the kernel function of motion blur is assumed shift-invariant. Mostly, we do not have the point spread function. So we focus on the study of blind image deconvolution. We estimate point spread function accurately by using edge patch to enhance blurred image, but the deblurred image is still having some ringing artifact. In the study, we propose an efficient and adaptive image deconvolution method, it combines the edge patch enhancement and bilateral filter for the restoration of the burred images. We use edge patch to enhance image and bilateral filter to reduce ringing artifacts which is caused by noise and narrow edge. Finally, we apply image pyramid strategy to accelerate the process of image deblurring. We expect that the proposed method can not only achieve the result without ringing artifact, but also have a good image deconvolution result.


目錄
第一章、緒論 1
1.1研究背景及動機 1
1.2 論文架構 5
第二章、文獻探討 6
2.1 Richardson-Lucy演算法 6
2.2使用影像濾波器的反卷積演算法 7
2.3基於邊緣的補片增強方法 8
2.4使用補片前驗訊息(Patch Prior)去模糊演算法 9
第三章、研究方法 10
3.1邊緣補片(Edge Patch)的產生 11
3.2使用補片的影像增強 14
3.3點擴散函數的估計(PSF Estimation) 21
3.4適應性影像反卷積(Image Deconvolution)運算 24
第四章、實驗結果及討論 26
4.1使用人造影像測試資料 27
4.2使用自然影像測試資料 33
第五章、結論與未來展望 41
參考文獻 42




參考文獻
[1]R. C. Gonzalez and R. E. Woods, Digital Image Processing (2nd Edition), Prentice Hall, 2002.
[2]W. H. Richardson, “Bayesian-based iterative method of image restoration,” JOSA, Vol.62, No.1, pp. 55–59, 1972.
[3]A. Rav-Acha and S. Peleg, “Two motion-blurred images are better than one”, Pattern Recognition Letters, pp.311-317, 2005.
[4]L. Yuan, J. Sun, L. Quan, and H. Shum, “Image deblurring with blurred/noisy image pairs”, ACM Trans. Graph., Vol.26, No.3, 2007.
[5]S. Zhuo, D. Guo, and T. Sim, “Robust flash deblurring”, in Proc. CVPR, pp.2440-2447, 2010.
[6]H. Zhang, D. Wipf, and Y. Zhang, “Multi-Observation blind deconvolution with an adaptive sparse prior", IEEE Trans. PAMI, Vol. 36, No. 8, pp. 1628-1643, 2014.
[7]L. Xu, S. Zheng and J. Jia, “ Unnatural L0 sparse representation for natural image deblurring,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[8]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, pp.787-794, 2006.
[9]Q. Shan, J. Jia, and A. Agarwala, “High-quality motion deblurring from a single image”, ACM Trans. Graph. , Vol.27, No.3, 2008.
[10]S. Cho and S. Lee, “Fast motion deblurring”, ACM Trans. Graph., Vol.28, No.5, 2009.
[11]C. Wang, L. Sun, P. Cui, J. Zhang, and S. Yang, “Analyzing image deblurring through three paradigms,” IEEE Trans. Image Processing,vol. 21, no. 1, pp. 115–129, Jan. 2012.
[12]C. Wang, Y. Yue, F. Dong, Y. Tao, X. Ma, G. Clapworthy, H. Lin, and X. Ye, “Nonedge-Specific adaptive scheme for highly robust blind motion deblurring of natural images”, IEEE Trans. Image Processing, Vol. 22, pp. 884 – 897, 2013.
[13]L. Yuan, J. Sun, L. Quan, and H.-Y. Shum, “Progressive inter-scale and intra-scale non-blind image deconvolution,” in Proc. SIGGRAPH, Los Angeles, CA, 2008.
[14]G. Ankit, J. Neel, Z. Larry, C. Michael, and C. Brian, “Single image deblurring using motion density functions,” in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 171–184.
[15]J. Neel, K. S. Bing, C. L. Zitnick, and Z. Richard, “Image deblurring using inertial measurement sensors,” in Proc. ACM SIGGRAPH, Los Angeles, CA, 2010.
[16]A. Levin, Y. Weiss, F. Durand and W.T. Freeman, “Understanding blind deconvolution algorithms”, IEEE Trans. PAMI, Vol. 33, No. 12, 2011.
[17]L. Sun, S. Cho, J. Wang and J. Hays, “Edge-based blur kernel estimation using patch priors”, in Proc. IEEE Conf. ICCP, 2013.
[18]L. Sun, S. Cho, J. Wang and J. Hays, “Good image priors for non-blind deconvolution: generic vs specific”, Proc. ECCV, Vol. 8692, pp 231-246, 2014
[19]D. Krishnan and R. Fergus, “Fast image deconvolution using hyper-Laplacian priors”, in 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, pp.248-272, 2008.
[21]K. Subr, C. Soler, and F. Durand, “Edge-preserving multiscale image decomposition based on local extrema,” ACM Transactions on Graphics, pp.147:1-147:9, 2009.
[22]C. Ayan, Z. Todd, and T. F. William, “Analyzing spatially-varying blur,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2010, pp.2512–2519.
[23]S. Roth and M. J. Black, “Fields of experts: A framework for learning image priors,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2005, pp. 860–867.
[24]Y. Weiss and W. T. Freeman, “What makes a good model of natural images?,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2007, pp.1–8.
[25]C. Sang, J. Neel, Z. C. Lawrence, K. S. Bing, S. Rick, and T. F.William, “A content-aware image prior,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognition, 2010, pp. 169–176.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關論文
 
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔