請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/46479完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳炳宇(Bing-Yu Chen) | |
| dc.contributor.author | Chia-Jung Hung | en |
| dc.contributor.author | 洪家榮 | zh_TW |
| dc.date.accessioned | 2021-06-15T05:11:11Z | - |
| dc.date.available | 2010-07-30 | |
| dc.date.copyright | 2010-07-30 | |
| dc.date.issued | 2010 | |
| dc.date.submitted | 2010-07-23 | |
| dc.identifier.citation | [1]T. Xia, B. Liao and Y. Yu, “Patch-Based Image Vectorization with Automatic Curvi-linear Feature”, ACM SIGGRAPH Asia, 2009.
[2]Canny, J., “A Computational Approach To Edge Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, 1986. [3]Jack E. Bresenham, “Algorithm for computer control of a digital plotter”, IBM Sys-tems Journal, 1965. [4]T. W. Sederberg and T. Nishita, “Curve intersection using Bezier clipping”, Comput-er-Aided Design, 1990. [5]A. Levin, D. Lischinski and Y. Weiss, “A closed form solution to natural image mat-ting”, In Proceedings of IEEE CVPR, 2006. [6]J. Wang, M. Agrawala and M. F. Cohen, “Soft scissors: An Interactive tool for real-time high quality matting”, ACM SIGGRAPH, 2007. [7]H. Chang and H. Yan, “Vectorization of hand-drawn image using piecewise cubic Bezier curves fitting”, Pattern Recognition, 1998. [8]Q. Shan, Z. Li, J. Jia and C.K. Tang, “Fast Image/Video Upsampling”, ACM SIG-GRAPH Asia, 2008. [9]R. Fattal, “Image Upsampling via Imposed Edges Statistic”, ACM SIGGRAPH, 2007. [10]J. D. van Quwerkerk, “Image super-resolution survey”, Image and Vision Compu-ting, 2006. [11]J. Yang, J. Wright, Y. Ma and T. Huang, “Image Super-Resolution as Sparse Repre-sentation of Raw Image Patches”, IEEE Conference on Computer Vision and Pat-tern Recognition, 2008. [12]J. Sun, J. Sun, Z. Xu and H. Y. Shum, “Image Super-Resolution using Gradient Pro-file Prior”, IEEE Conference on Computer Vision and Pattern Recognition, 2008. [13]J. Wang and M. F. Cohen, “Optimized color sampling for robust matting”, IEEE Conference on Computer Vision and Pattern Recognition, 2007. [14]X. Li and M. T. Orchard, “New edge-directed interpolation”, IEEE Transactions on Image Processing, 2001. [15]Q. Wang and R. K. Ward, “A New Orientation-Adaptive Interpolation Method”, IEEE Transactions on Image Processing, 2007. [16]J. H. Elder, “Are Edges Incomplete? ”, International Journal of Computer Vision, 1999. [17]Y. W. Tai, W.S. Tong and C.K. Tang, “Perceptually-Inspired and Edge-Directed Color Image Super-Resolution”, IEEE Conference on Computer Vision and Pattern Recognition, 2006. [18]A. Giachetti and N. Asuni, “Fast Artifacts-Free Image Interpolation”, Proc. Of the British Machine Vision Conf., 2008. [19]S. Baker and T. Kanade, “Limits on Super-Resolution an How to Break Them”, IEEE Transactions on Pattern Analysis and Machine Intelligence. [20]Z. Farbman, G. Hoffer, Y. Lipman, D. Cohen-Or and D. Lischinski, “Coordinates for Instant Image Clonnig”, ACM SIGGRAPH 2009. [21]S. Dai, M. Han, W. Xu, Y. Wu and Y. Gong, “Soft Edge Smoothness Prior for Alpha Channel Super Resolution”, IEEE Conference on Computer Vision and Pattern Recognition, 2007. [22]S. Dai, M. Han, W. Xu, Y. Wu and Y. Gong, “SoftCuts: A Soft Edge Smoothed Prior for Color Image Super-Resolution”, IEEE Transactions on Image Processing, 2009. [23]Y. Cha and S. Kim, “The Error-Amended Sharp Edge (EASE) Scheme for Image Zooming”, IEEE Transactions on Image Processing, 2007. [24]N. Toronto, B. S. Morse, K. Seppi and D. Ventura, “Super-Resolution via Recapture and Bayesian Effect Modeling”, IEEE Conference on Computer Vision and Pattern Recognition, 2009. [25]A. S. Glassner, J. Arvo, D. Kirk, P. S. Heckbert and A. W. Paeth “Graphics Gems I”, Academic Press, 1990~1995. [26]R. Keys, “Cubic Convolution Interpolation for Digital Image Processing”, IEEE Transactions on Acoustics, Speech and Signal Proocessing, 1981. [27]J. Allebach, P. W. Wong, “Edge-Directed Interpolation”, International Conference on Image Processing, 1996. [28]C.B. Atkins, C.A. Bouman and J.P. Allebach, “Optimal image scaling using pixel classification”, Proceedings of International Conference on Image Processing, 2001. [29]C. Staelin, D. Greig, M. Fischer and R. Maurer, “Neural network image scaling us-ing spatial errors”, HP Laboratories Israel, 2003. [30]F.M. Candocia and J.C. Principe, “Superresolution of images based on local corre-lations”, IEEE Transactions on Neural Networks 1999. [31]S. Battiato, G. Gallo and F. Stanco, “Smart interpolation by anisotropic diffusion”, Proceedings of 12th International Conference on Image Analysis and Processing, 2003. [32]M.F. Tappen, B.C. Russell and W.T. Freeman, “Exploiting the Sparse Derivative Prior for Super-Resolution and Image Demosaicing”, 2003. [33]S. Battiato, G. Gallo and F. Stanco, “A locally-adaptive zooming algorithm for digi-tal images”, Image Vision and Computing Journal 2002. [34]N. Joshi, R. Szeliski and D. J. Kriegman, “PSF Estimation using Sharp Edge Pre-diction”, IEEE Conference on Computer Vision and Pattern Recognition, 2008 [35]Mathwork, Matlab [36]A. Foi, V. Katkovnik and K. Egiazarian, “Pointwise Shape-Adaptive DCT for High Quality Denoising and Deblocking of Grayscale and Color Images”, IEEE Transac-tions on Image Processing, 2007. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/46479 | - |
| dc.description.abstract | 隨著顯示裝置的解析度提高，高解析度內容的需求也日漸增加，因此數位影像放大的演算法也越顯重要。在數位影像當中，物體邊緣對於影像品質有很大的影響。因此近代的相關研究皆試圖強化物體邊緣，提升影像品質。
在這篇論文中，我們提出了一套將影像中的物體邊緣形狀參數化，並藉此來保留放大影像中的物體邊緣形狀的方法。因為這些物體的邊緣會混合不同區域的顏色，因此在這個系統中，我們利用混色遮罩找出這些邊緣附近區域的顏色組成，以在放大的圖像中取得該區域的顏色。 最後根據放大圖像中每個像素的位置、該位置附近的物體邊緣以及顏色組成，算出一張具有銳利邊緣的數位影像。 | zh_TW |
| dc.description.abstract | As the resolution of output device increases, the demand of high resolution content has become more and more eagerly. As a result, the image super resolution algorithm becomes more and more important.
In digital image, image edge is related to human perception heavily, so image edge is very important to image quality. Because of this, most recent research topics on computer vision that handle digital images do their best to enhance image edge to achieve better quality. In this project, we propose an edge preserving super resolution algorithm, which is related to image vectorization strongly. We first parameterize the image edges to fit edge shape, and than using these data as constraint of super resolution. However, the color nearby edge is usually a combination of two different regions. To get pure color of edge, we use matting technique to solve the problem. Finally we do super resolution based on edge shape, position and nearby color in-formation to compute a digital image with sharp edge. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T05:11:11Z (GMT). No. of bitstreams: 1 ntu-99-R97922010-1.pdf: 1964702 bytes, checksum: 1f95bb7e83577c87c16cb3454bf8ee1f (MD5) Previous issue date: 2010 | en |
| dc.description.tableofcontents | Chapter 1 Introduction ............................................................................................ 1
1.1 Motivation ...................................................................................................... 3 1.2 Organization .................................................................................................. 3 Chapter 2 Related Work .......................................................................................... 5 Chapter 3 System Overview .................................................................................... 8 Chapter 4 Edge Forming ....................................................................................... 11 4.1 Edge Detection ............................................................................................. 11 4.2 Edge Forming .............................................................................................. 13 Chapter 5 Edge Color Analysis .............................................................................. 16 5.1 Image Matting ............................................................................................. 17 5.2 Trimap Generation ...................................................................................... 19 Chapter 6 Edge Shape Approximation .................................................................. 22 6.1 Subpixel refinement ..................................................................................... 22 6.2 Edge Shape Fitting ...................................................................................... 23 Chapter 7 Polygonal Image Representation .......................................................... 25 7.1 Find Bezier Grid Samples ........................................................................... 26 7.2 Sample Bezier Curve Point ......................................................................... 28 7.3 Polygonal Image Representation................................................................. 29 7.4 Vertex Color Determination ........................................................................ 32 Chapter 8 Edge Preserving Super Resolution ....................................................... 35 8.1 Mean Value Coordinate ............................................................................... 35 8.2 Image Interpolation using MVC ................................................................. 36 8.3 Image Reblur ............................................................................................... 37 Chapter 9 Result..................................................................................................... 39 9.1 Result ........................................................................................................... 39 9.2 Limitation .................................................................................................... 49 Chapter 10 Conclusion and Future Work ............................................................. 51 Reference ................................................................................................................... 52 | |
| dc.language.iso | en | |
| dc.subject | 平均值座標系 | zh_TW |
| dc.subject | 貝式曲線 | zh_TW |
| dc.subject | 邊緣偵測 | zh_TW |
| dc.subject | 影像遮罩 | zh_TW |
| dc.subject | 向量化 | zh_TW |
| dc.subject | 影像放大 | zh_TW |
| dc.subject | 內插 | zh_TW |
| dc.subject | edge detection | en |
| dc.subject | super-resolution | en |
| dc.subject | vectorization | en |
| dc.subject | matting | en |
| dc.title | 利用線段參數化與混色遮罩輔助之圖像放大 | zh_TW |
| dc.title | Edge Preserving Image Super Resolution | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 98-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 林奕成(I-Chen Lin),林文杰(Wen-Chieh Lin) | |
| dc.subject.keyword | 影像放大,向量化,影像遮罩,邊緣偵測,貝式曲線,平均值座標系,內插, | zh_TW |
| dc.subject.keyword | super-resolution,vectorization,matting,edge detection,B, | en |
| dc.relation.page | 56 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2010-07-23 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-99-1.pdf 未授權公開取用 | 1.92 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。