影像向量化，也稱作向量圖學，他主要是利用幾何物件像是點，線，曲線，形狀和多邊形去呈現影像。由於它的可放大無失真特性和編輯特性，
這已廣泛地使用在圖學設計，動畫，和圖標……等等。然而，對向量圖藝術家來說，在進行向量圖創造上仍然是個艱鉅的工作，尤其是複雜的圖片。
因此，最近的向量圖學研究偏向於對複雜的影像作向量化。

通常對藝術家來說，向量圖是由許多的物件組成。因此，我們論文將會提供一直觀的工具去讓藝術家設計向量圖，
特別是切割設計與向量化的功能。除了直觀使用介面之外，我們也提出一新穎的架構去呈現向量圖。我們將我們的向量圖分成外在結構和內在結構兩部分。外
在結構主要是維持直觀可編輯性的向量圖學，而內在結構利用影像特徵加強影像放大無失真性。

Image vectorization, is called vector graphics, is the use of geometrical primitives such points, lines, curves, and shapes or polygon(s) to represent images in compute graphics. Now it is widely used in Graphics Design, Flash animation, or icon…etc, due to its scalability and editability. However, it is a tedious work to manually create vector graphics for artists. Therefore, in the recent, There are some researches to try to vectorize the complex color image.

In general, the vector graphics is composed of several objects that are assigned by artists. Thus, our paper would provide a intuitive tool for artists to design vector graphics. They provide the functions of segmentation and Vectorization specifically. In addition to the intuitive interface, we propose a novel architecture to present vector graphics as well. We divide our vector graphics into explicit and implicit structure. Explicit structure would keep the intuitive editability of vector graphics and implicit structure would enhance the scalability via image saliency.

[1] F. Bookstein. Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11:567-585, 1989.
[2] A. Delong, A. Osokin, H. N. Isack, and Y. Boykov. Fast approximate energy minimization with label costs. Int. J. Comput. Vision, 96(1):1-27, 2012.
[3] L. Demaret, N. Dyn, and A. Iske. Image compression by linear splines over adaptive triangulations. In Signal Processing, pages 1604-1616, 2006.
[4] M. Finch, J. Snyder, and H. Hoppe. Freeform vector graphics with controlled thin-plate splines. ACM Trans. Graph., 30(6):166:1-166:10, 2011.
[5] S. Jeschke, D. Cline, and P. Wonka. Estimating color and texture parameters for vector graphics. Computer Graphics Forum, 30(2):523{532, Apr. 2011. This paper won the 2nd best paper award at Eurographics 2011.
[6] Y.-K. Lai, S.-M. Hu, and R. R. Martin. Automatic and topology-preserving gradient mesh generation for image vectorization. ACM Trans. Graph., 28(3):85:1-85:8, 2009.
[7] G. Lecot and B. Levy. Ardeco: Automatic region detection and conversion. In Eurographics Symposium on Rendering, 2006.
[8] Y. Li, J. Sun, C.-K. Tang, and H.-Y. Shum. Lazy snapping. ACM Trans. Graph., 23(3):303-308, 2004.
[9] Z. Liao, H. Hoppe, D. Forsyth, and Y. Yu. A subdivision-based representation for vector image editing. IEEE Transactions on Visualization and Computer Graph- ics, 99(PrePrints), 2012.
[10] R. Maharik, M. Bessmeltsev, A. She_er, A. Shamir, and N. Carr. Digital micrography. ACM Trans. Graph., 30(4):100:1-100:12, 2011.
[11] A. Orzan, A. Bousseau, H. Winnemoller, P. Barla, J. Thollot, and D. Salesin. Di_usion curves: a vector representation for smooth-shaded images. ACM Trans. Graph., 27(3):92:1-92:8, 2008.
[12] C. Rother, V. Kolmogorov, and A. Blake. "grabcut": interactive foreground extraction using iterated graph cuts. ACM Trans. Graph., 23(3):309-314, 2004.
[13] J. Sun, L. Liang, F. Wen, and H.-Y. Shum. Image vectorization using optimized gradient meshes. ACM Trans. Graph., 26(3), 2007.
[14] S. Swaminarayan and L. Prasad. Rapid automated polygonal image decomposition. In Applied Imagery and Pattern Recognition Workshop, 2006. AIPR 2006. 35th IEEE, page 28, oct. 2006.
[15] Y.-S. Wang, C.-L. Tai, O. Sorkine, and T.-Y. Lee. Optimized scale-and-stretch for image resizing. ACM Trans. Graph., 27(5):118:1-118:8, 2008.
[16] T. Xia, B. Liao, and Y. Yu. Patch-based image vectorization with automatic curvilinear feature alignment. ACM Trans. Graph., 28(5):115:1-115:10, 2009.
[17] C.-Y. Yao, M.-T. Chi, T.-Y. Lee, and T. Ju. Region-based line field design using harmonic functions. IEEE Transactions on Visualization and Computer Graphics, 18:902-913, 2012.