臺灣博碩士論文加值系統

使用拼接技術所合成的全景影像大多都會具有不規則形狀的邊緣，攝影師以及大部分的使用者還是傾向於使用矩形邊緣的全景影像作為呈現結果，想要得到這樣的結果可以使用影像裁切、影像修復等「矩形化」方法，但前者會犧牲影像外部的資訊，後者則是使用影像中的內容填補所缺失的部份，這些方法無法將拍攝者所看到的視野完整地呈現給使用者，為了改善這些缺點所以出現了使用影像變形矩形化全景圖的方法。
本研究提出了一個基於伸縮與延展之內容感知變形將合成的全景影像矩形化的方法，原始的影像變形方法分為兩個部份，第一個部份是不需要網格所進行的區域變形，由此自動產生符合輸入影像的不規則形狀網格，第二部份則是透過產生出來的網格，將此網格最佳化至矩形的全域變形，本研究所提方法主要是依據重要程度圖對全域變形的方法進行修改，將影像變形過程中所產生的扭曲變形大部份轉移至影像中較為不重要的區域，如此一來便可以有效地對影像中較為重要的部份進行保護，同時為了在矩形化的過程中保護更多的資訊，本研究修改了原始的重要程度圖，使得修改過後的重要程度圖能盡可能的納入更多有效地資訊。在實驗結果中，本研究所提方法相對於原始的影像變形方法能夠較好的保護影像中的資訊不被變形的過程所影響。

The panorama images creating from stitching technique mostly have irregular boundaries. Photographer and common users generally prefer that panorama images have rectangular boundaries. To get this result, we can use the rectangling method like cropping or inpainting, but cropping method will lose the information outside the chosen inner rectangle and inpainting method will use the content that choose from the current image to fill up the missing area. These method will reduce or destroy the wide view of original panorama images. With this problem, the method of using warping to rectangling panorama images is developed.
In this paper, we present a new rectangling method for panorama images using scale-and-stretch-based content-aware warping. The original warping method for panorama images consists of two steps. The first local step use mesh-free local warping to generate the irregular mesh on the input image. The second global step optimizes this mesh to get the rectangle result. Our proposed method modifies the global step based on significance map to allow diverting the distortion due to rectangling to unimportant area, such that the impact on perceptually important features is minimized. In order to protect more content, we modify the original significance map to get more effective information. In the experimental results, our proposed method can get the better result with the scale-and-stretch-based content-aware warping.

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影像裁切(Cropping) 5
2.2影像修復(Inpainting) 7
2.3影像變形(Warping) 9
第三章 研究方法 13
3.1 區域變形(Local warping) 14
3.1.1改良的縫線雕刻(Modified seam carving) 14
3.1.2 網格放置(Mesh placement) 16
3.2 全域變形(Global warping) 17
3.2.1 伸縮與延展之變形方法(Scale-and-stretch warping method) 18
3.2.2 修改重要程度圖(Modified significance map) 21
3.2.3 比較與探討 23
第四章 實驗結果與討論 26
4.1 保護線段的實驗結果比較 27
4.2 保持突出物體比例的實驗結果比較 34
第五章 結論與未來展望 37
參考文獻 39

[1]K. He, H. Chang and J. Sun, "Rectangling panoramic images via warping", ACM Transactions on Graphics, vol. 32, no. 4, p. 1, 2013.
[2]R. Carroll, A. Agarwala and M. Agrawala, "Image warps for artistic perspective manipulation", ACM Transactions on Graphics, vol. 29, no. 4, p. 1, 2010.
[3]C. Chang and Y. Chuang, "A line-structure-preserving approach to image resizing", IEEE Conference on Computer Vision and Pattern Recognition, 2012.
[4]F. Liu, M. Gleicher, H. Jin and A. Agarwala, "Content-preserving warps for 3D video stabilization", ACM Transactions on Graphics, vol. 28, no. 3, p. 1, 2009.
[5]ADOBE, https://research.adobe.com/project/content-aware-fill/, 2009.
[6]Y. Wexler, E. Shechtman and M. Irani, "Space-Time Completion of Video", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 3, pp. 463-476, 2007.
[7]C. Barnes, E. Shechtman, A. Finkelstein and D. Goldman, "PatchMatch", ACM Transactions on Graphics, vol. 28, no. 3, p. 1, 2009.
[8]Y. Wang, C. Tai, O. Sorkine and T. Lee, "Optimized scale-and-stretch for image resizing", ACM Transactions on Graphics, vol. 27, no. 5, p. 1, 2008.
[9]S. Avidan and A. Shamir, "Seam carving for content-aware image resizing", ACM Transactions on Graphics, vol. 26, no. 99, p. 10, 2007.
[10]L. Itti, C. Koch and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 11, pp. 1254-1259, 1998.
[11]G. Zhang, M. Cheng, S. Hu and R. Martin, "A Shape-Preserving Approach to Image Resizing", Computer Graphics Forum, vol. 28, no. 7, pp. 1897-1906, 2009.
[12]R. von Gioi, J. Jakubowicz, J. Morel and G. Randall, "LSD: A Fast Line Segment Detector with a False Detection Control", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 4, pp. 722-732, 2010.
[13]Z. Zhang and B. Kang, "Improved retargeting algorithm based on optimized scale-and-stretch", Global High Tech Congress on Electronics, 2013.