Abstract
Converting a scanned or shot line drawing image into a vector graph can facilitate further editand reuse, making it a hot research topic in computer animation and image processing. Besides avoiding noiseinfluence, its main challenge is to preserve the topological structures of the original line drawings, such as linejunctions, in the procedure of obtaining a smooth vector graph from a rough line drawing. In this paper, wepropose a vectorization method of line drawings based on junction analysis, which retains the original structureunlike done by existing methods. We first combine central line tracking and contour tracking, which allowsus to detect the encounter of line junctions when tracing a single path. Then, a junction analysis approachbased on intensity polar mapping is proposed to compute the number and orientations of junction branches.Finally, we make use of bending degrees of contour paths to compute the smoothness between adjacent branches,which allows us to obtain the topological structures corresponding to the respective ones in the input image.We also introduce a correction mechanism for line tracking based on a quadratic surface fitting, which avoidsaccumulating errors of traditional line tracking and improves the robustness for vectorizing rough line drawings.We demonstrate the validity of our method through comparisons with existing methods, and a large amount ofexperiments on both professional and amateurish line drawing images.
创新点
本文提出一种基于交叉点分析的线条矢量化方法, 克服了现有方法难以保持拓扑结构的不足。通过中心路径跟踪和轮廓路径跟踪相结合的方式, 准确检测交叉点的出现提出一种基于极坐标亮度映射的交叉点分析方法, 计算交叉点的分支数量和朝向; 利用轮廓路径的弯曲角度判断交叉点相邻分支间的光顺度, 从而获得与原图一致的拓扑结构。
Similar content being viewed by others
References
Chen T, Cheng M M, Tan P, et al. Sketch2Photo: Internet image montage. ACM Trans Graph, 2009, 28: 1–10
Xu K, Chen K, Fu H B, et al. Sketch2Scene: sketch-based co-retrieval and co-placement of 3D models. ACM TransGraph, 2013, 32: 1–12
Lai Y K, Hu S M, Martin R R, et al. Automatic and topology-preserving gradient mesh generation for image vectorization. ACM Trans Graph, 2009, 28: 1–8
Lee B S, Kazi R H, Smith G. SketchStory: telling more engaging stories with data through freeform sketching. IEEETrans Vis Comput Graph, 2013, 19: 2416–2425
Yoo I, Vank J, Nizovtseva. Sketching human character animations by composing sequences from large motion database. Vis Comput, 2014, 30: 213–227
Fu H B, Zhou S Z, Liu L G, et al. Animated construction of line drawings. ACM Trans Graph, 2011, 30: 1–10
Zhang T, Suen C Y. A fast parallel algorithm for thinning digital patterns. Commun ACM, 1984, 27: 236–239
Hilaire X, Tombre K. Improving the accuracy of skeleton-based vectorization. Graphics recognition algorithms andapplications. Berlin/Heidelberg: Springer, 2002. 273–288
Sezgin T M, Davis R. Handling overtraced strokes in hand-drawn sketches. In: Proceedings of Making Pen-BasedInteraction Intelligent and Natural. New York: AAAI Fall Symposium, 2004. 1–4
Hilaire X, Tombre K. Robust and accurate vectorization of line drawings. IEEE Trans Patt Anal Mach Intell, 2006,28: 890–904
Bonnici A, Camilleri K P. Scribble vectorization using concentric sampling circles. In: Proceedings of InternationalConference on Advanced Engineering Computing and Applications in Sciences. Los Alamitos: IEEE Computer Society,2009. 89–94
Bonnici A, Camilleri K. A circle-based vectorization algorithm for drawings with shadows. In: Proceedings of theInternational Symposium on Sketch-Based Interfaces and Modeling. New York: ACM, 2013. 69–77
Zou J J, Yan H. Line image vectorization based on shape partitioning and merging. In: Proceedings of InternationalConference on Pattern Recognit, Barcelona, 2000. 994–997
Zou J J, Yan H. Cartoon image vectorization based on shape subdivision. In: Proceedings of Computer GraphicsInternational. Los Alamitos: IEEE Computer Society, 2001. 225–231
Wenyin L, Dori D. Sparse pixel tracking: a fast vectorization algorithm applied to engineering drawings. In: Proceedingsof International Conference on Pattern Recognit, Vienna, 1996. 808–812
Dori D, Liu W. Sparse pixel vectorization: an algorithm and its performance evaluation. IEEE Trans Patt Anal MachIntell, 1999, 21: 202–215
Whited B, Rossignac J, Slabaugh G, et al. Pearling: stroke segmentation with crusted pearl strings. IEEE Trans PattAnal Mach Intell, 2009, 19: 277–283
Noris G, Hornung A, Sumner R W, et al. Topology-driven vectorization of clean line drawings. ACM Trans Graph,2013, 32: 1–11
Sun J, Liang L, Wen F, et al. Image vectorization using optimized gradient meshes. ACM Trans Graph, 2007, 26:1–11
Xia T, Liao B, Yu Y. Patch-based image vectorization with automatic curvilinear feature alignment. ACM TransGraph, 2009, 28: 1–10
Chiang J Y, Tue S, Leu Y. A new algorithm for line image vectorization. Patt Recog, 1998, 31: 1541–1549
Chang H H, Yan H. Vectorization of hand-drawn image using piecewise cubic B´ezier curves fitting. Patt Recog, 1998,31: 1747–1755
Liu K, Huang Y S, Suen C Y. Identification of fork points on the skeletons of handwritten Chinese characters. IEEETrans Patt Anal Mach Intell, 1999, 21: 1095–1100
Rajan P, Hammond T. From paper to machine: extracting strokes from images for use in sketch recognition. In:Proceedings of the 5th Eurographics conference on Sketch-Based Interfaces and Modeling, Annecy, 2008. 41–48
Yang Y, Zhu C, Sun Q. Vectorization of linear features on color scanning topographic maps (in Chinese). J ComputAid Des Comput Graph, 2009, 21: 533–541
Song J, Su F, Cai S. The segmentation of text from line based on the line recognition in scanning engineering drawings(in Chinese). J Nanjing Univ, 2001, 37: 535–541
Wong J, Guo C. An improved image template thinning algorithm (in Chinese). J Image Graph, 2004, 9: 297–301
Liu R, Li Y. Study of auto-vectorization based on scan-thinning algorithm (in Chinese). Acta Geodaetica et CartographicaSinica, 2012, 41: 309–314
Lu Z, Zhang Q. Line contour tracking in engineering drawing vectorization (in Chinese). J Image Graph, 1997, 2:878–882
Bartolo A, Camilleri K P, Fabri S G, et al. Scribbles to vectors: preparation of scribble drawings for CAD interpretation.In: Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling. New York: ACM, 2007.123–130
Nieuwenhuizen P R, Kiewiet O, Bronsvoort W F. An integrated line tracking and vectorization algorithm. ComputGraph Forum, 1994, 13: 349–359
Kyprianidis J E, Kang H. Image and video abstraction by coherence-enhancing filtering. Comput Graph Forum, 2011,30: 593–602
Bartolo A, Camilleri K P, Fabri S G, et al. Line tracking algorithm for scribbled drawings. In: Proceedings ofInternational Symposium on Communications, Control and Signal Processing, St Julians, 2008. 554–559
Wang S D, Ma Z Y, Liu X H, et al. Coherence-enhancing line drawing for color images. Sci China Inf Sci, 2013, 56:110903
Pham T A, Delalandre M, Barrat S, et al. Accurate junction detection and characterization in line-drawing images. Patt Recog, 2014, 47: 282–295
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chen, J., Lei, Q., Miao, Y. et al. Vectorization of line drawing image based on junction analysis. Sci. China Inf. Sci. 58, 1–14 (2015). https://doi.org/10.1007/s11432-014-5246-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-014-5246-x