This Article 
 Bibliographic References 
 Add to: 
Vectorizing Cartoon Animations
July/August 2009 (vol. 15 no. 4)
pp. 618-629
Song-Hai Zhang, Tsinghua University, Beijing
Tao Chen, Tsinghua University, Beijing
Yi-Fei Zhang, Tsinghua University, Beijing
Shi-Min Hu, Tsinghua University, Beijing
Ralph R. Martin, Cardiff University, Cardif
We present a system for vectorizing 2D raster format cartoon animations. The output animations are visually flicker free, smaller in file size, and easy to edit. We identify decorative lines separately from colored regions. We use an accurate and semantically meaningful image decomposition algorithm, supporting an arbitrary color model for each region. To ensure temporal coherence in the output, we reconstruct a universal background for all frames and separately extract foreground regions. Simple user-assistance is required to complete the background. Each region and decorative line is vectorized and stored together with their motions from frame to frame. The contributions of this paper are: 1) the new trapped-ball segmentation method, which is fast, supports nonuniformly colored regions, and allows robust region segmentation even in the presence of imperfectly linked region edges, 2) the separate handling of decorative lines as special objects during image decomposition, avoiding results containing multiple short, thin oversegmented regions, and 3) extraction of a single patch-based background for all frames, which provides a basis for consistent, flicker-free animations.

[1] G. Lecot and B. Levy, “Ardeco: Automatic Region Detection and Conversion,” Proc. 17th Eurographics Symp. Rendering, pp.349-360, 2006.
[2] J. Sun, L. Liang, F. Wen, and H.-Y. Shum, “Image Vectorization Using Optimized Gradient Meshes,” ACM Trans. Graphics, vol. 26, no. 3, p.11, 2007.
[3] D. Sýkora, J. Buriánek, and J. Žára, “Colorization of Black-and-White Cartoons,” Image and Vision Computing, vol. 23, no. 9, pp.767-852, 2005.
[4] D. Sýkora, J. Buriánek, and J. Žára, “Sketching Cartoons by Example,” Proc. Second Eurographics Workshop Sketch-Based Interfaces and Modeling, pp.27-34, 2005.
[5] D. Sýkora, J. Buriánek, and J. Zára, “Video Codec for Classical Cartoon Animations with Hardware Accelerated Playback,” Proc. First Int'l Symp. Advances in Visual Computing, vol. 3804, pp.43-50, 2005.
[6] D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp.603-619, May 2002.
[7] Y. Qu, T.-T. Wong, and P.-A. Heng, “Manga Colorization,” ACM Trans. Graphics (Proc. ACM SIGGRAPH '06), vol. 25, no. 3, pp.1214-1220, 2006.
[8] C.L. Zitnick, N. Jojic, and S.B. Kang, “Consistent Segmentation for Optical Flow Estimation,” Proc. Int'l Conf. Computer Vision, pp.II: 1308-1315, 2005.
[9] M.P. Kumar, P.H.S. Torr, and A. Zisserman, “Learning Layered Motion Segmentation of Video,” Proc. Int'l Conf. Computer Vision, pp.I: 33-40, 2005.
[10] J. Xiao and M. Shah, “Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp.1644-1659, Oct. 2005.
[11] C. Stauffer and W.E.L. Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” Computer Vision and Pattern Recognition, pp.2246-2252, 1999.
[12] H.W. Kang and S.Y. Shin “Tour Into The Video: Image-Based Navigation Scheme for Video Sequences of Dynamic Scenes,” , Proc. ACM Symp. Virtual Reality Software and Technology (VRST'02), pp.73-80, 2002.
[13] A. Monnet, A. Mittal, N. Paragios, and V. Ramesh, “Background Modeling and Subtraction of Dynamic Scenes,” Proc. Ninth IEEE Int'l Conf. Computer Vision (ICCV '03), p. 1305, 2003.
[14] I. Koprinska and S. Carrato, “Temporal Video Segmentation: A Survey,” Signal Processing Image Comm., vol. 16, pp.477-500, Jan. 2001.
[15] Y. Gong and X. Liu, “Video Shot Segmentation and Classification,” Proc. Int'l Conf. Pattern Recognition (ICPR '00), vol. 1, pp.860-863, 2000.
[16] D.G. Lowe, “Object Recognition from Local Scale-Invariant Features,” Proc. Int'l Conf. Computer Vision, pp.1150-1157, 1999.
[17] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp.679-698, 1986.
[18] F. Bernardini and C.L. Bajaj, “Sampling and Reconstructing Manifolds Using Alpha-Shapes,” Proc. Ninth Canadian Conf. Computational Geometry, pp.193-198, 1997.
[19] C. Steger, “An Unbiased Detector of Curvilinear Structures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 2, pp.113-125, Feb. 1998.
[20] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision. Chapman and Hall, 1993.
[21] C.M. Georgescu, “Synergism in Low Level Vision,” Proc. Int'l Conf. Pattern Recognition, pp.150-155, 2002.
[22] A. Meijster, J.B.T.M. Roerdink, and W.H. Hesselink, “A General Algorithm for Computing Distance Transforms in Linear Time,” Math. Morphology and its Applications to Image and Signal Processing, pp.331-340, 2000.
[23] B. Price and W. Barrett, “Object-Based Vectorization for Interactive Image Editing,” The Visual Computer, vol. 22, no. 9, pp.661-670, 2006.

Index Terms:
Cartoon vectorization, trapped-ball segmentation, image decomposition, foreground extraction.
Song-Hai Zhang, Tao Chen, Yi-Fei Zhang, Shi-Min Hu, Ralph R. Martin, "Vectorizing Cartoon Animations," IEEE Transactions on Visualization and Computer Graphics, vol. 15, no. 4, pp. 618-629, July-Aug. 2009, doi:10.1109/TVCG.2009.9
Usage of this product signifies your acceptance of the Terms of Use.