臺灣博碩士論文加值系統

立體視覺成像技術廣泛的運用在各個領域，其目的是讓觀看者感知到立體效果，讓每位觀看者如身歷其中。本研究將影像的點畫風格化運用在立體視覺技術應用中，系統一開始先讓使用者輸入左右影像及相對應的左右深度圖，此外，使用者也可以調整點畫的參數，包括大小及數量，以改變點畫風格，經過系統流程後所輸出的影像可以利用紅藍眼鏡體驗到3D立體效果。我們的方法是先將左點畫L透過左對應的Disparity Map產生右點畫R，再利用右對應的Disparity Map將右點畫R產生左點畫L'，再將L' 和R變成anaglyph Image(左:紅，右:藍)，即可透過紅藍眼鏡感知立體效果。在這其中我們可能會遭遇到雙眼競爭(Binocular Rivalry)問題，其問題是因為參數中點的大小及其數量造成區域不一致，所以觀看anaglyph Image結果時會讓眼睛感到不適，對此我們提出了左右交互檢查的機制，以改善這個問題(artifact)。

Stereoscopy technique has been widely used in various fields. Its purpose is to allow viewers to perceive three-dimensional effects, so that each viewer can personally experience a stereoscopic scene. In our study, we apply image stylization technique to stereoscopic images. In the first, users should input one pair of stereoscopic images and their corresponding disparity maps. In addition, users can adjust the stippling parameters: the size and amount of stippling, to change the stippling style. After setting up parameters, our system can automatically process and output images which can make people who wear red-cyan glasses experience the 3D effect. Our approach is to generate the left stippling image named L in the first, and generate the right stippling image named R through the left corresponding disparity map, and then we use the right corresponding disparity map to generate a new left stippling image L '.Finally we let L' and R become an anaglyph Image (Left: red, right: cyan), and users can perceive three-dimensional effect through the red-cyan glasses. We might encounter the problem of binocular rivalry when processing the stereoscopic images. The problem is due to the point parameters: the size and number of points; leading to regional inconsistencies, so when users watch the anaglyph Image results, the results make users’ eyes feel uncomfortable. To address this problem, we propose an interactive mutual check mechanism to improve the results.

1. 緒論
1.1 研究動機與目的
1.2 論文架構
2. 相關文獻
2.1 立體視覺成像技術（Stereoscopy）
2.1.1 立體影像匹配（Stereoscopy correspondence）
2.1.2 立體影像處理（Stereoscopic Image Processing）
2.2 點畫（Stippling）
2.2.1 Voronoi Diagram方法
2.2.2 Delaunay Triangulation方法
3. 立體點畫系統實作
3.1 系統流程
3.2 前置處理
3.2.1 視差圖（Disparity Map）
3.2.2 遮蔽圖（Occlusion Map）
3.3 方法實作
3.3.1 點畫
3.3.2 與Disparity Map相關的處理步驟
3.3.3 左右點畫檢查機制
4. 結果
4.1 系統環境
4.2 系統參數設定
4.3 結果展示
4.4 使用者測試及評估
5. 結論與未來展望
6. 參考文獻

[1]. Christian Richardt, Lech Swirski, Ian P. Davies, Neil A. Dodgson "Predicting
Stereoscopic Viewing Comfort Using a Coherence-Based Computational Model"
In Proc. Computational Aesthetics in Graphics, Visualization, and Imaging, 2011,
pp. 97–104
[2]. Daniel Scharstein, Richard Szeliski "A Taxonomy and Evaluation of Dense
Two-Frame Stereo Correspondence Algorithm" In Proc. International Journal of
Computer Vision, volume 47, 2002, pp. 7-42
[3]. Andrea Klaus, Mario Sormann and Konrad Karner "Segment-based Stereo
Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure" In
Proc. International Conference on Pattern Recognition, 2006, pp. 15-18
[4]. Bradon M. Smith, Li Zhang and Hailin Jin "Stereo Matching with Nonparametric
Smoothness Priors in Feature Space" In Proc. IEEE Computer Society Conference
on Computer Vision and Pattern Recognition, 2009, pp. 485-492
[5]. Christoph Rhemann, Asmaa Hosni, Michael Bleyer, Carsten Rother and Margrit
Gelautz "Fast Cost-Volume Filtering for Visual Correspondence and Beyond" In
Proc. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
[6]. Lesley Northam, Paul Asente, Craig S. Kaplan "Stereoscopic 3D image stylization"
In Proc. Computers &; Graphics, volume 37, 2013, pp. 389-402
[7]. Wan-Yen Lo, Jeroen Van Baar, Claude Knaus, Matthias Zwicker and Markus Gross
"Stereoscopic 3D Copy &; Paste" In Proc. ACM SIGGRAPH Asia, volume 29, 2010,
pp. 147
[8]. Yuzhen Niu, Wu-Chi Feng, and Feng Liu. "Enabling Warping on Stereoscopic
Images" In Proc. ACM SIGGRAPH Asia, volume 31, article 183, 2012
[9]. Sheng-Jie Luo, I-Chao Shen, Bing-Yu Chen, Wen-Huang Cheng and Yung-Yu
Chuang "Perspective-aware warping for seamless stereoscopic image cloning"
In Proc. ACM SIGGRAPH Asia, volume 31, article 182, 2012
[10]. Ken-Yi Lee, Cheng-Da Chung and Yung-Yu Chuang "Scene Warping:
Layer-based Stereoscopic Image Resizing" In Proc. Computer Vision and Pattern
Recognition, 2012, pp. 773-780
[11]. Adrian Secord "Weighted Voronoi Stippling" In Proc. Non-photorealistic
Animation and Rendering, 2002, pp. 37-43

[12]. Mccool, M. and Fiume, E. 1992. "Hierarchical Poisson Disk Sampling
Distributions". In Proc. of the Graphics Interface, 1992, pp. 94–105
[13]. Yin Xu, Ligang Liu, Craig Gotsman and Steven J. Gortler "Capacity-Constrained
Delaunay Triangulation for point distributions" In Proc. Shape Modeling
International, 2011, pp. 510-516
[14]. Dorin Comaniciu and Peter Meer "Mean Shift: A Robust Approach Toward
Feature Space Analysis" In Proc. IEEE Transactions Pattern Analysis and Machine
Intelligence, volume 24, 2002, pp. 603-619
[15]. Peter Meer and Bogdan "Edge Detection with Embedded Confidence" In Proc.
IEEE Transactions Pattern Analysis and Machine Intelligence, 2001,
pp. 1351-1365
[16]. Patrick Perez, Michel Gangnet and Andrew Blake "Poisson Image Editing" In Proc.
ACM SIGGRAPH, volume 22, 2003, pp. 313-318
[17]. Middlebury Stereo Datasets "http://vision.middlebury.edu/stereo/data/"
[18]. P. F. Felzenszwalb and D. P. Huttenlocher "Efficient belief propagation for early
vision" In Proc. Computer Vision and Pattern Recognition, 2004, pp. 261-268
[19]. Hertzmann A. "Painterly rendering with curved brush strokes of multiple sizes"
In Proc. SIGGRAPH, 1998, pp. 453-460
[20]. EDISON System
"http://coewww.rutgers.edu/riul/research/code/EDISON/doc/help.html"
[21]. Jifeng Ning, Lei Zhang, David Zhang, Chengke Wu "Interactive image
segmentation by maximal similarity based region merging" In Proc. Pattern
Recognition, volume 43, 2010, pp. 445-456