Multimedia Tools and Applications

, Volume 78, Issue 14, pp 19083–19113 | Cite as

A complete hand-drawn sketch vectorization framework

  • Luca DonatiEmail author
  • Simone Cesano
  • Andrea Prati


Vectorizing hand-drawn sketches is an important but challenging task. Many businesses rely on fashion, mechanical or structural designs which, sooner or later, need to be converted in vectorial form. For most, this is still a task done manually. This paper proposes a complete framework that automatically transforms noisy and complex hand-drawn sketches with different stroke types in a precise, reliable and highly-simplified vectorized model. The proposed framework includes a novel line extraction algorithm based on a multi-resolution application of Pearson’s cross correlation and a new unbiased thinning algorithm that can get rid of scribbles and variable-width strokes to obtain clean 1-pixel lines. Other contributions include variants of pruning, merging and edge linking procedures to post-process the obtained paths. Finally, a modification of the original Schneider’s vectorization algorithm is designed to obtain fewer control points in the resulting Bézier splines. All the steps presented in this framework have been extensively tested and compared with state-of-the-art algorithms, showing (both qualitatively and quantitatively) their outperformance. Moreover they exhibit fast real-time performance, making them suitable for integration in any computer graphics toolset.


Image vectorization Line extraction Unbiased thinning Bézier curves Sketch processing Correlation coefficient 



This work is funded by Adidas AG. We are really thankful to Adidas for this opportunity.


  1. 1.
    Bartolo A, Camilleri KP, Fabri SG, Borg JC, Farrugia PJ (2007) Scribbles to vectors: preparation of scribble drawings for cad interpretation. In: Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling, pp 123–130. ACMGoogle Scholar
  2. 2.
    Bessmeltsev M, Solomon J (2018) Vectorization of line drawings via polyvector fields. arXiv:1801.01922
  3. 3.
    Bo P, Luo G, Wang K (2016) A graph-based method for fitting planar b-spline curves with intersections. J Comput Des Eng 3(1):14–23Google Scholar
  4. 4.
    Chen J, Guennebaud G, Barla P, Granier X (2013) Non-oriented mls gradient fields. In: Computer graphics forum, vol 32, pp 98–109. Wiley online libraryGoogle Scholar
  5. 5.
    Chen YS (1996) The use of hidden deletable pixel detection to obtain bias-reduced skeletons in parallel thinning. In: Proceedings of the 13th international conference on pattern recognition, vol 2, pp 91–95. IEEEGoogle Scholar
  6. 6.
    Dori D, Liu W (1999) Sparse pixel vectorization: an algorithm and its performance evaluation. IEEE Trans Pattern Anal Mach Intell 21(3):202–215CrossRefGoogle Scholar
  7. 7.
    Favreau JD, Lafarge F, Bousseau A (2016) Fidelity vs. simplicity: a global approach to line drawing vectorization. ACM Trans Graph (TOG) 35(4):120CrossRefGoogle Scholar
  8. 8.
    Fišer J, Asente P, Schiller S, Sỳkora D (2016) Advanced drawing beautification with shipshape. Comput Graph 56:46–58CrossRefGoogle Scholar
  9. 9.
    Gonzalez RC, Woods RE (2007) Digital image processing 3rd editionGoogle Scholar
  10. 10.
    Han JH, Poston T (2001) Chord-to-point distance accumulation and planar curvature: a new approach to discrete curvature. Pattern Recogn Lett 22(10):1133–1144CrossRefzbMATHGoogle Scholar
  11. 11.
    Hilaire X, Tombre K (2006) Robust and accurate vectorization of line drawings. IEEE Trans Pattern Anal Mach Intell 28(6):890–904CrossRefGoogle Scholar
  12. 12.
    Igarashi T, Matsuoka S, Kawachiya S, Tanaka H (2006) Interactive beautification: a technique for rapid geometric design. In: ACM SIGGRAPH 2006 courses, p 8. ACMGoogle Scholar
  13. 13.
    Kang H, Lee S, Chui CK (2007) Coherent line drawing. In: Proceedings of the 5th international symposium on non-photorealistic animation and rendering, pp 43–50. ACMGoogle Scholar
  14. 14.
    Lambert JH (1760) Photometria: sive de mensvra et gradibvs lvminis, colorvm et vmbrae. sumptibus vidvae E. Klett typis CP DetleffsenGoogle Scholar
  15. 15.
    Lewis JP (1995) Fast normalized cross-correlation. Vision Interface 10(1):120–123Google Scholar
  16. 16.
    Li B, Lu Y, Godil A, Schreck T, Aono M, Johan H, Saavedra JM, Tashiro S (2013) SHREC’13 track: large scale sketch-based 3D shape retrievalGoogle Scholar
  17. 17.
    Lindeberg T (1998) Edge detection and ridge detection with automatic scale selection. Int J Comput Vis 30(2):117–156CrossRefGoogle Scholar
  18. 18.
    Liu X, Wong TT, Heng PA (2015) Closure-aware sketch simplification. ACM Trans Graph (TOG) 34(6):168Google Scholar
  19. 19.
    Lowe DG (1999) Object recognition from local scale-invariant features. In: International conference on computer vision, 1999, pp 1150–1157. IEEEGoogle Scholar
  20. 20.
    Noris G, Hornung A, Sumner RW, Simmons M, Gross M (2013) Topology-driven vectorization of clean line drawings. ACM Trans Graph (TOG) 32(1):4CrossRefzbMATHGoogle Scholar
  21. 21.
    Orbay G, Kara LB (2011) Beautification of design sketches using trainable stroke clustering and curve fitting. IEEE Trans Vis Comput Graph 17(5):694–708CrossRefGoogle Scholar
  22. 22.
    Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285-296):23–27Google Scholar
  23. 23.
    Saeed K, Tabędzki M, Rybnik M, Adamski M (2010) K3m: a universal algorithm for image skeletonization and a review of thinning techniques. Int J Appl Math Comput Sci 20(2):317–335CrossRefzbMATHGoogle Scholar
  24. 24.
    Sangkloy P, Burnell N, Ham C, Hays J (2016) The sketchy database: Learning to retrieve badly drawn bunnies. ACM Trans Graph (TOG) 35(4):119:1–119:12CrossRefGoogle Scholar
  25. 25.
    Schneider PJ (1990) Graphics gems. chap. An algorithm for automatically fitting digitized curves, pp 612–626. Academic Press Professional, Inc., San DiegoGoogle Scholar
  26. 26.
    Simo-Serra E, Iizuka S, Ishikawa H (2018) Mastering sketching: adversarial augmentation for structured prediction. ACM Trans Graph (TOG) 37(1):11CrossRefGoogle Scholar
  27. 27.
    Simo-Serra E, Iizuka S, Sasaki K, Ishikawa H (2016) Learning to simplify: fully convolutional networks for rough sketch cleanup. ACM Trans Graph (SIGGRAPH) 35(4):121CrossRefGoogle Scholar
  28. 28.
    Song J, Su F, Tai CL, Cai S (2002) An object-oriented progressive-simplification-based vectorization system for engineering drawings: model, algorithm, and performance. IEEE Trans Pattern Anal Mach Intell 24(8):1048–1060CrossRefGoogle Scholar
  29. 29.
    Steger C (1998) An unbiased detector of curvilinear structures. IEEE Trans Pattern Anal Mach Intell 20(2):113–125CrossRefGoogle Scholar
  30. 30.
    Suzuki S, et al (1985) Topological structural analysis of digitized binary images by border following. Comput Vis Graph Image 30(1):32–46CrossRefzbMATHGoogle Scholar
  31. 31.
    Tsai DM, Lin CT (2003) Fast normalized cross correlation for defect detection. Pattern Recogn Lett 24(15):2625–2631CrossRefGoogle Scholar
  32. 32.
    Zhang SH, Chen T, Zhang YF, Hu SM, Martin RR (2009) Vectorizing cartoon animations. IEEE Trans Vis Comput Graph 15(4):618–629CrossRefGoogle Scholar
  33. 33.
    Zhang T, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Engineering and ArchitectureUniversity of ParmaParmaItaly
  2. 2.Adidas AGHerzogenaurachGermany

Personalised recommendations