簡易檢索 / 詳目顯示

回結果列表
研究生： 張民人
Chang, Min-Jen
論文名稱： 利用混合式貼圖紋理技術之變形藝術應用
Anamorphic Art Generation Using Hybrid Texture Synthesis
指導教授： 李同益
Lee, Tong-Yee
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2012
畢業學年度： 100
語文別： 英文
論文頁數： 46
中文關鍵詞： 變形影像 、變形影像藝術 、扭曲投影 、灰階值最佳化 、影像量化 、影像分割 、貼圖合成
外文關鍵詞： anamorphosis, anamorphic art, distorted projection, luminance optimization, image quantization, image segmentation, texture synthesis
相關次數： 點閱：114  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 變形影像(Anamorphosis)是一門變形的藝術，創作者藉由透視投影來扭曲原本的主題。最早的變形影像創作可以追溯至15世紀末。觀察者需要利用特殊的裝置或是在特定的位置來觀看才能看到原本的圖樣。Anamorphosis字面上是從希臘文的字首” ana-”──意思為「回頭」或是「再次」，以及” morphē”──意思為「形狀」、「型態」。意即主題需要被重新自我詮釋、自我改變型態。變形影像藝術可以分為兩大類，第一類為「透視」(perspective)，第二類為「反射」(mirror)。「透視」類需要透過特定的透射變形或是特定角度才能得到原本的影像；「反射」類則為透過特定的反射裝置，例如圓柱體，放置在圖中，使影像經過變形扭曲後，原本的樣貌將還原到該裝置上。

    本篇論文專注在「反射」類的變形影像藝術，藉由自然風景圖或是一般手繪圖來形成變形影像。使用者先指定想要呈現在圓柱體上的原始圖案，接著再指定來源背景以及該背景所對應的物件資料庫，最後指定原始圖案的特徵，即可產生出變形影像的結果。在讀入原始圖案後，先計算其在地面上的變形結果，接下來我們將變形圖分為兩類，分別為特徵部份以及非特徵部分。特徵部分根據使用者指定的特徵範圍中，從物件資料庫挑出最適合的物體放入。物體需要有較強烈的結構性，方能有凸顯特徵的作用。非特徵的部分，則利用背景圖來合成出變形圖。計算變形圖和背景圖的灰階分布差異，最佳化出結果，使得新合成的圖中，既可以有變形圖的特徵，又可自然地融入原本的背景圖中。最後我們將特徵和非特徵的部分合併，即可得到最後的反射類的變形影像。

    Anamorphic art is a distorted art using perspectival projection on subject, the earliest work can be found in the 15th century. Viewer need to use special devices or occupy a specific vantage point to reconstitute the image. The etymological origin of the word is from the Greek prefix ana- , which means back or again, and morphē, which means shape or form, indicates that the spectator must play a part and re-form the picture himself. There are two main types of anamorphic art: perspective and mirror. Perspective type is doing perspectival projection on some subject; mirror type needs a conical or cylindrical mirror to place on distorted image to return its original form by mirroring.

    In this paper, we concentrate on mirror type of anamorphic art, use natural scene or normal painting to generate mirror type of anamorphic art. In order to highlight figure’s feature, we use objects which have strong structure to fill feature. Other part we adopt synthesis method using background information to synthesize distorted image of figure image according optimization result of luminance. Finally, we combine two part of figure, to get mirror type of anamorphic art result.

    中文摘要.........................................I Abstract.......................................III 誌謝............................................V Contents.......................................VI List of Figure.................................VIII Chapter 1 Introduction........................1 1.1 Motivation and Purpose....................1 1.2 Content and System Flow...................3 Chapter 2 Related Work........................5 2.1 History...................................5 2.2 Methods...................................5 Chapter 3 Framework and Algorithm.............7 3.1 Feature Part..............................10 3.1.1 Separating IGM..........................10 3.1.2 Choose object...........................11 3.2 Non-feature Part..........................13 3.2.1 Exclude Background Feature Part.........14 3.2.2 Quantization and Segmentation...........15 3.2.3 Optimize................................17 3.2.4 Synthesize Scene........................20 Chapter 4 Results.............................23 4.1 Discussion................................41 4.2 Limitations...............................41 Chapter 5 Conclusion and Future Work..........44 Reference.....................................45

    [1] BARNES, C., SHECHTMAN, E., FINKELSTEIN, A., AND GOLDMAN, D. B. 2009. PatchMatch: A randomized correspondence algorithm for structural image editing. ACM TOG 28, 3.
    [2] BARNES, C., SHECHTMAN, E., GOLDMAN. D.B., and FINKELSTEIN, A. 2010. The Generalized PatchMatch Correspondence Algorithm. ECCV, 2010, pp.29-43.
    [3] BOYKOV, Y., AND KOLMOGOROV, V. 2004. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26, 9, 1124–1137.
    [4] BOYKOV, Y., VEKSLER, O., AND ZABIH, R. 2001. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 11, 1222–1239.
    [5] CHU, H.-K., HSU, W.-H., MITRA, N.J., COHEN-OR, D., WONG, T.-T., and LEE, T.-T. 2010, Camouflage Images. ACM Transactions on Graphics, 29, Issue 4, pp.51:3-53:5.
    [6] HERTZMANN, A., JACOBS, C., OLIVER, N., CURLESS, B., AND SALESIN, D. 2001. Image Analogies. In Proceedings of SIGGRAPH 2001, ACM Press / ACM SIGGRAPH, New-York, E. Fiume, Ed., Computer Graphics Proceedings, Annual Conference Series, ACM, 327–340.
    [7] HUNT, J.L., NICKEL, B.G., and GIGAULT, C. 2000, Anamorphic Images. American Journal of Physics, 68, pp.232-237.
    [8] KOLMOGOROV, V., AND ZABIH, R. 2002. What energy functions can be minimized via graph cuts? In ECCV, 65–81.
    [9] ROTHER, C., BLAKE, A., AND KOLMOGOROV, V. 2004. “GrabCut” - Interactive Foreground Extraction Using Iterated Graph Cuts. In Proceedings of ACM SIGGRAPH 2004.
    [10] TOMASI, C., AND MANDUCHI, R. 1998. Bilateral filtering for gray and color images. In ICCV, 839–846.

    下載圖示 校內：2013-09-06公開
    校外：2013-09-06公開
    QR CODE