動畫是老少咸宜的影片，使用色塊構成的動畫角色與聲優的配音讓觀眾體會到藝術家想傳達的精神，而向量化的重點主要在於，向量化能壓縮影像資訊，取得放大不失真的特性，並增加影像的可編輯性，例如筆觸的粗細與明暗。本論文將動畫影格中的觸與色塊分別做向量化處理，能產生有銳利筆觸的向量化結果，並維持了筆觸在動畫中的連續性。在過去的影像向量化由於沒有筆觸與色塊分開向量化的概念，在筆觸的向量化上並沒有針對筆觸的特性最佳化，而我們的方法能讓筆觸與色塊各自以最佳的表示方式記錄及生成，並在動畫中維持連續性。在我們的系統中，輸入資料為動畫連續影格，處理的過程分程單張影像分解與影片連續性處理。單張影像的處理，首先將原圖做白平衡後，從影條中萃取出筆觸與顏色邊界曲線，將顏色邊界曲線三角化並分割顏色區塊。找尋影格中顏色區塊與筆觸計算對應關係，藉由對應關係能維持動畫中區塊與筆觸的連續性。我們的系統能輸入一段動畫影片經過處理，得到筆觸明顯，不閃爍跳動的動畫向量化結果。

This paper presents a vectorization system for cartoon animation.
Our vectorization method is based on processing separately from stroke and region. We can generate outputs that are visually flicker-free and with clear stroke. We use image decomposition algorithm to do vectorization separately on stroke and region, and supporting color model for each region.
To ensure temporal coherence in the output, we use region tracking algorithm for all frames to maintain region's color and shape.
The contributions of this paper are:
1) individual handling for strokes during image decomposition process to produce results with sharpen strokes.
2) generating flicker-free results by maintaining region coherence for all frames.

[1] G. Lecot and B. L′evy, “ARDECO: Automatic Region DEtection and Conversion,” in 17th Eurographics Symposium on Rendering - EGSR’06, (Nicosia/-
Cyprus), pp. 349–360, June 2006.
[2] J. Sun, L. Liang, F. Wen, and H.-Y. Shum, “Image vectorization using optimized gradient meshes,” Association for Computing Machinery, Inc., July 2007.
[3] Y.-K. Lai, S.-M. Hu, and R. R. Martin, “Automatic and topology-preserving
gradient mesh generation for image vectorization,” ACM Trans. Graph., vol. 28,
pp. 85:1–85:8, July 2009.
[4] Z. Liao, H. Hoppe, D. A. Forsyth, and Y. Yu, “A subdivision-based representation for vector image editing.,” IEEE Trans. Vis. Comput. Graph., vol. 18,
no. 11, pp. 1858–1867, 2012.
[5] P. Selinger, “Potrace: a polygon-based tracing algorithm,” 2003.
[6] S.-H. Zhang, T. Chen, Y.-F. Zhang, S.-M. Hu, and R. R. Martin, “Vectorizing cartoon animations,” IEEE Transactions on Visualization and Computer
Graphics, vol. 15, no. 4, pp. 618–629, 2009.
[7] M. ming Cheng, “Curve structure extraction for cartoon images,” 2009.
[8] J. Chen, Q. Lei, Y. Miao, and Q. Peng, “Vectorization of line drawing image
based on junction analysis,” SCIENCE CHINA Information Sciences, vol. 58,
no. 7, pp. 1–14, 2015.
[9] G. Noris, A. Hornung, R. W. Sumner, M. Simmons, and M. Gross, “Topologydriven vectorization of clean line drawings,” ACM Trans. Graph., vol. 32,
pp. 4:1–4:11, Feb. 2013.
56
[10] B. Whited, B. Whited, J. Rossignac, J. Rossignac, G. Slabaugh, T. Fang, and
G. Unal, “Pearling: Stroke segmentation with crusted pearl strings,” in Proceedings of the 1st International Workshop on Image Mining Theory and Applications IMTA 2008, pp. 103–112, 2008.
[11] C.-C. Weng, H. Chen, and C.-S. Fuh, “A novel automatic white balance method
for digital still cameras.,” in ISCAS (4), pp. 3801–3804, IEEE, 2005.
[12] D. G. Lowe, “Object recognition from local scale-invariant features,” in Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2,
ICCV ’99, (Washington, DC, USA), pp. 1150–, IEEE Computer Society, 1999.
[13] C. Steger, “An unbiased detector of curvilinear structures.,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, no. 2, pp. 113–125, 1998.
[14] J. C. Bowers, J. Leahey, and R. Wang, “A ray tracing approach to diffusion
curves,” in Proceedings of the Twenty-second Eurographics Conference on Rendering, EGSR’11, (Aire-la-Ville, Switzerland, Switzerland), pp. 1345–1352, Eurographics Association, 2011.
[15] J. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern
Anal. Mach. Intell., vol. 8, pp. 679–698, June 1986.
[16] D. Comaniciu, P. Meer, and S. Member, “Mean shift: A robust approach toward
feature space analysis,” IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 24, pp. 603–619, 2002.
[17] G. Farneb‥ack, “Two-frame motion estimation based on polynomial expansion,”
in Image Analysis, pp. 363–370, Springer, 2003.
57
[18] S. Jeschke, D. Cline, and P. Wonka, “A gpu laplacian solver for diffusion curves
and poisson image editing,” Transaction on Graphics (Siggraph Asia 2009),
vol. 28, pp. 1–8, Dec. 2009.
[19] D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int.
J. Comput. Vision, vol. 60, pp. 91–110, Nov. 2004.
[20] A. Orzan, A. Bousseau, H. Winnemﾜller, P. Barla, l. Thollot, and D. Salesin,
“Diffusion curves: A vector representation for smooth-shaded images,” in ACM
Transactions on Graphics (Proceedings of SIGGRAPH 2008), vol. 27, 2008.
[21] X. Sun, G. Xie, Y. Dong, S. Lin, W. Xu, W. Wang, X. Tong, and B. Guo,
“Diffusion curve textures for resolution independent texture mapping,” ACM
Trans. Graph., vol. 31, pp. 74:1–74:9, July 2012.
[22] H. Winnem‥oller, A. Orzan, L. Boissieux, and J. Thollot, “Texture design and
draping in 2d images,” Computer Graphics Forum (Proceedings of the Eurographics Symposium on Rendering 2009), vol. 28, no. 4, pp. 1091–1099, 2009.