請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/26762
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕(Yung-Yu Chuang) | |
dc.contributor.author | Yen-Hung Chen | en |
dc.contributor.author | 陳彥宏 | zh_TW |
dc.date.accessioned | 2021-06-08T07:24:25Z | - |
dc.date.copyright | 2008-07-26 | |
dc.date.issued | 2008 | |
dc.date.submitted | 2008-07-17 | |
dc.identifier.citation | [1] Soonmin Bae, Sylvain Paris and Fr edo Durand. Two-scale tone management for photographic look. In Proceedings of ACM SIGGRAPH, 2006.
[2] Yung-Yu Chuang, Brian Curless, David H. Salesin and Richard Szeliski. A bayesian approach to digital matting. In Proceedings of IEEE CVPR, pages 264{271, 2001. [3] Elmar Eisemann and Fr edo Durand Flash Photography Enhancement via Intrinsic Relighting. In Proceedings of ACM SIGGRAPH, 2004 [4] Pedro F. Felzenszwalb and Daniel P. Huttenlocher. E cient Graph-Based Image Segmentation. In International Journal of Computer Vision, 59:(2), 2004. [5] Leo Grady Random Walks for Image Segmentation. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(11):1768{1783, 2006. [6] Anat Levin, Dani Lischinski and Yair Weiss. A closed form solution to natural image matting. In Proceedings of IEEE CVPR, 2007. [7] Sylvain Paris and Fr edo Durand. A Fast Approximation of the Bilateral Filterusing a Signal Processing Approach. In Proceedings of European Conference on Computer Vision, 2006 [8] Mark A. Ruzon and Carlo Tomasi Alpha estimation in natural images. In Proceedings of IEEE CVPR, pages 18{25, 2000. [9] Jian Sun, Jiaya Jia, Chi-Keung Tang and Heung-Yeung Shum. Poisson Matting. In Proceedings of ACM SIGGRAPH, 23(3):315{321, 2004. [10] JueWang and Michael F. Cohen. An iterative optimization approach for unified image segmentation and matting. In Proceedings of ICCV, pages 936{943, 2005. [11] Jue Wang and Michael F. Cohen. Optimized color sampling for robust matting. In Proceedings of IEEE CVPR, pages 1{8, 2007. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/26762 | - |
dc.description.abstract | 影像透明度分析(Image matting)指的是分析影像中每一個像素是屬於前景、背景、或是兩者的混合,而每一個像素由多少比例的前景和背景組成可用alpha這個參數來表示。過去各種影像透明度的方法均需要一些使用者輸入,例如,在前景和背景劃上筆劃或是用trimap來表示前景、背景和不確定的像素,才能得生出合理的alpha值。我們在這篇論文提出一種新的方法來自動算出每個像素的alpha值,且不需要任何使用者的輸入。
我們假設背景離前景有一定的距離,而且照片是在較淺或有限的景深下拍攝,因此前景清楚而背景模糊。我們首先利用這個假設產生出一個粗略的trimap,再用這個trimap來初步估計所有不確定像素的alpha值,最後再將整張照片的alpha值做最佳化,便能得出精確的alpha值。 | zh_TW |
dc.description.abstract | Image matting is the problem of determining each pixel in an image whether it is foreground, background, or a mixture of foreground and background while 'alpha' value is the parameter of portion of foreground and background in each pixel. Previous matting approaches are constrained by requiring certain amount of user input, for example, foreground/background strokes or trimap, to generate reasonable results. In this paper, we present an approach to automatically generate an alpha matte without any user input.
We assume that the background is distant from the oreground and images are taken in narrow or limited depth of eld so the foreground is in focus while the background is blurred. We rst generate a rough trimap under our assumption and then use this trimap to initially estimate alpha value of each unknown pixel. And after further optimization, a high quality alpha matte can be achieved. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T07:24:25Z (GMT). No. of bitstreams: 1 ntu-97-R95922067-1.pdf: 4673539 bytes, checksum: d2fad0d632fa94f134a42a3589bebdaf (MD5) Previous issue date: 2008 | en |
dc.description.tableofcontents | 1 Introduction 1
2 Related Work 3 2.1 Propagation-based Approaches 3 2.2 Sampling-based Approaches 4 2.3 Combined Approaches 4 3 Overview 5 3.1 Taking Pictures 5 4 Automatically Generated Trimap 8 4.1 Textureness 8 4.2 Image Segmentation 10 4.3 Generating Trimap 10 5 Matting Algorithm 14 5.1 Optimized Color Sampling 14 5.2 Assigning Weight for Optimization 17 5.3 Solving for Optimal alpha 19 6 Results and Discussion 21 7 Conclusion and Future Work 26 Bibliography 27 | |
dc.language.iso | en | |
dc.title | 基於景深之自動化透明度分析 | zh_TW |
dc.title | Automatic Matting Based on Depth of Field | en |
dc.type | Thesis | |
dc.date.schoolyear | 96-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 歐陽明(Ming Ouhyoung),梁容輝(Rung-Huei Liang) | |
dc.subject.keyword | 透明度分析,景深, | zh_TW |
dc.subject.keyword | matting,depth-of-field, | en |
dc.relation.page | 36 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2008-07-18 | |
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-97-1.pdf 目前未授權公開取用 | 4.56 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。