Abstract
We develop a method to automatically segment a font’s glyphs into a set of overlapping and intersecting strokes with the aim of generating artistic stylizations. The segmentation method relies on a geometric analysis of the glyph’s outline, its interior, and the surrounding areas and is grounded in perceptually informed principles and measures. Our method does not require training data or templates and applies to glyphs in a large variety of input languages, writing systems, and styles. It uses the medial axis, curvilinear shape features that specify convex and concave outline parts, links that connect concavities, and seven junction types. We show that the resulting decomposition in strokes can be used to create variations, stylizations, and animations in different artistic or design-oriented styles while remaining recognizably similar to the input font.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, StrokeStyles: Stroke-based Segmentation and Stylization of Fonts
- 2017. Spectral clustering based on local PCA. J. Mach. Learn. Res. 18, 1 (2017), 253–309. Google ScholarDigital Library .
- 2015. Forms of Rockin’: Graffiti Letters and Popular Culture. Dokument Press.Google Scholar .
- 1999. Ligature instabilities in the perceptual organization of shape. Comput. Vis. Image Understand. 76, 3 (1999), 231–243. Google ScholarDigital Library .
- 2018. Multi-content GAN for few-shot font style transfer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7564–7573. Google ScholarCross Ref .
- 2001. Class-dependent Features and Multicategory Classification. Ph. D. Dissertation. Southampton University.Google Scholar .
- 2019. Learning a stroke-based representation for fonts. Comput. Graph. Forum 38, 1 (2019), 429–442. Google ScholarCross Ref .
- 1995. QHull. The Geometry Center, University of Minnesota.Google Scholar .
- 2001. On evolute cusps and skeleton bifurcations. In Proceedings of the International Conference on Shape Modeling and Applications. IEEE, 134–140. Google ScholarCross Ref .
- 2019. Sketching and layering graffiti primitives. In Proceedings of the 8th ACM/Eurographics Expressive Symposium on Computational Aesthetics and Sketch Based Interfaces and Modeling and Non-Photorealistic Animation and Rendering. 51–59. Google ScholarDigital Library .
- 2017. Dynamic graffiti stylisation with stochastic optimal control. In Proceedings of the 4th International Conference on Movement Computing. Association for Computing Machinery.
Article no. 18 .Google ScholarDigital Library . - 2018. Expressive curve editing with the sigma lognormal model. In Proceedings of the 39th Annual European Association for Computer Graphics Conference: Short Papers. Eurographics Association, 33–36.Google ScholarDigital Library .
- 2020. Kinematics reconstruction of static calligraphic traces from curvilinear shape features. In Proceedings of the Lognormality Principle and its Applications in e-Security, e-Learning and e-Health, , , and (Eds.).
Series in Machine Perception and Artificial Intelligence , Vol. 88. Chapter 11, 237–268.DOI: Google ScholarCross Ref . - 1973. Biological shape and visual science (part I). J. Theor. Biol. 38, 2 (1973), 205–287. Google ScholarCross Ref .
- 2015. Traditional and new principles of perceptual grouping. In The Oxford Handbook of Perceptual Organization, Johan Wagemans (Ed.). Oxford University Press, 57–87.Google Scholar .
- 2014. Learning a manifold of fonts. ACM Trans. Graph. 33, 4 (2014).
Article no. 91 .Google ScholarDigital Library . - 2017. An automatic stroke extraction method using manifold learning. In Proceedings of the European Association for Computer Graphics: Short Papers (EG’17). Eurographics Association, 65–68.
DOI: Google ScholarDigital Library . - 1982. Skeletons: A link between theoretical and physical letter descriptions. Pattern Recogn. 15, 1 (1982), 11–22. Google ScholarCross Ref .
- 2017. The influence of graffiti writing in contemporary typography. Street Art Urban Creativ. Sci. J. 3, 2 (2017), 65–83. Google ScholarCross Ref .
- 2006. Segmentation of object outlines into parts: A large-scale integrative study. Cognition 99, 3 (2006), 275–325. Google ScholarCross Ref .
- 2012. Feedback-guided stroke placement for a painting machine. In Proceedings of the 8th Annual Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging. Eurographics Association, 25–33.Google ScholarDigital Library .
- 2017. Learning the geometric structure of manifolds with singularities using the tensor voting graph. J. Math. Imag. Vis. 57, 3 (2017), 402–422. Google ScholarDigital Library .
- 2013. Encyclopedia of Distances. Springer. Google ScholarCross Ref .
- 2008. A fast and simple heuristic for metro map path simplification. In Proceedings of the International Symposium on Visual Computing. Springer, 22–30. Google ScholarDigital Library .
- 2012. Optimality of human contour integration. PLOS Comput. Biol. 8, 5 (2012), 1–17. Google ScholarCross Ref .
- 2009. CGAL: The computational geometry algorithms library. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (GIS’09). 538–539. Google ScholarDigital Library .
- 2009. Tangential cover for thick digital curves. Pattern Recogn. 42, 10 (2009), 2279–2287. Google ScholarDigital Library .
- 2016. Fidelity vs. simplicity: A global approach to line drawing vectorization. ACM Trans. Graph. 35, 4 (2016).
Article no. 120 .Google ScholarDigital Library . - 2015. Bayesian hierarchical grouping: Perceptual grouping as mixture estimation. Psychol. Rev. 122, 4 (2015), 575–597. Google ScholarCross Ref .
- 2011. Animated construction of line drawings. In ACM Trans. Graph. 30 (2011). 1–10. Google ScholarDigital Library .
- 2011. An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes. Pattern Recogn. 44, 8 (2011), 1761–1776. Google ScholarDigital Library .
- 2013. Osculating curves: Around the tait-kneser theorem. Math. Intell. 35, 1 (2013), 61–66. Google ScholarCross Ref .
- 2003. On the local form and transitions of symmetry sets, medial axes, and shocks. Int. J. Comput. Vis. 54, 1 (
Aug. 2003), 143–157. Google ScholarCross Ref . - 2008. Stroke-by-Stroke Glyph Animation.
Technical Report . Creativity and Graphics Lab (CraGL) at George Mason University, Fairfax, Virginia.Google Scholar . - 2009. Multi-manifold semi-supervised learning. In Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, David van Dyk and Max Welling (Eds.), Vol. 5. PMLR, 169–176. https://proceedings.mlr.press/v5/goldberg09a.html.Google Scholar .
- 2018. A neural representation of sketch drawings. In Proceedings o f the 6th International Conference on Learning Representations (ICLR’18).Google Scholar .
- 2016. My text in your handwriting. ACM Trans. Graph. 35, 3 (2016).
Article no. 26 .Google ScholarDigital Library . - 2005. Bayesian hierarchical clustering. In Proceedings of the 22nd International Conference on Machine learning (ICML’05). ACM, 297–304. Google ScholarDigital Library .
- 1997. Coherent processing of character skeletal forms. Comput. Graph. 21, 6 (1997), 727–736. Google ScholarCross Ref .
- 1984. Parts of recognition. Cognition 18, 1-3 (1984), 65–96. Google ScholarCross Ref .
- 1997. Salience of visual parts. Cognition 63, 1 (1997), 29–78. Google ScholarCross Ref .
- 1982. Variations on a theme as the essence of imagination. Sci. Am. 247, 4 (1982), 14–21.Google ScholarCross Ref .
- 1994. Drawing and animation using skeletal strokes. In Proceedings of the21st Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH’94), 109–118. Google ScholarDigital Library .
- 1993. Skeletal strokes. In Proceedings of the 6th Annual ACM Symposium on User Interface Software and Technology (UIST’93). 197–206. Google ScholarDigital Library .
- 2001. Parameterizable fonts based on shape components. IEEE Comput. Graph. Appl. 21, 3 (2001), 70–85. Google ScholarDigital Library .
- 2006. An improved representation for stroke-based fonts. In ACM SIGGRAPH 2006 Sketches. Google ScholarDigital Library .
- 2013. Toward perception-based shape decomposition. In Proceedings of the Asia Conference onComputer Vision (ACCV’12).
Lecture Notes in Computer Science , Vol. LNCS 7725. Springer, 188–201. Google ScholarDigital Library . - 2003. Handbook of Elasticity Solutions. Springer Netherlands. Google ScholarCross Ref .
- 1994. Digital Typefaces: Description and Formats. Springer. Google ScholarCross Ref .
- 2018. Semantic segmentation for line drawing vectorization using neural networks. Comput. Graph. Forum 37, 2 (2018), 329–338.
DOI: Google ScholarCross Ref . - 2018. Make Me a Hanzi Dataset. Retrieved from https://github.com/skishore/makemeahanzi.Google Scholar .
- 1979. Mathematical typography. Bull. Am. Math. Soc. 1, 2 (1979), 337–373. Google ScholarCross Ref .
- 2020. Generating handwriting via decoupled style descriptors. In Proceedings of the European Conference on Computer Vision (ECCV’20). 764–780.Google ScholarDigital Library .
- 2015. Human-level concept learning through probabilistic program induction. Science 350, 6266 (2015), 1332–1338. Google ScholarCross Ref .
- 2015. Re-typograph phase I: A proof-of-concept for typeface parameter extraction from historical documents. In Document Recognition and Retrieval XXII, and (Eds.), Vol. 9402. International Society for Optics and Photonics, SPIE, 80–91.
DOI: Google ScholarCross Ref . - 1998. Discrete approach to curve evolution. In Mustererkennung 1998. Springer, 85–92. Google ScholarCross Ref .
- 2009. From Spiral to Spline: Optimal Techniques in Interactive Curve Design. Ph.D. Dissertation. EECS Department, University of California, Berkeley.Google Scholar .
- 1987. Symmetry-curvature duality. Comput. Vis. Graph. Image Process. 38, 3 (1987), 327–341. Google ScholarCross Ref .
- 1988. A process-grammar for shape. Artif. Intell. 34, 2 (
March 1988), 213–247. Google ScholarDigital Library . - 2015. A computational model of the short-cut rule for 2D shape decomposition. IEEE Trans. Image Process. 24, 1 (2015), 273–283. Google ScholarCross Ref .
- 2011. Bone graphs: Medial shape parsing and abstraction. Comput. Vis. Image Understand. 115, 7 (
July 2011), 1044–1061. Google ScholarDigital Library . - 2008. From skeletons to bone graphs: Medial abstraction for object recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’08). Google ScholarCross Ref .
- 2007. Separating parts from 2D shapes using relatability. In Proceedings of the IEEE 11th International Conference on Computer Vision (ICCV’07). Google ScholarCross Ref .
- 2014. A survey on automated metro map layout methods. In Proceedings of the 1st Schematic Mapping Workshop. University of Essex, UK.Google Scholar .
- 2005. The Stroke—Theory of Writing. Hyphen Press.
Translated from the Dutch original of 1985 by Peter Enneson .Google Scholar . - 1992. Voronoi skeletons: Theory and applications. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’92). 63–69. Google ScholarCross Ref .
- 2019. Revisiting the medial axis for planar shape decomposition. Comput. Vis. Image Understand. 179 (2019), 66–78. Google ScholarDigital Library .
- 1989. Trace inference, curvature consistency, and curve detection. IEEE Trans. Pattern Anal. Mach. Intell. 11, 8 (1989), 823–839. Google ScholarDigital Library .
- 2015. Flexyfont: Learning transferring rules for flexible typeface synthesis. In Computer Graphics Forum, Vol. 34. 245–256. Google ScholarDigital Library .
- 2000. Online and off-line handwriting recognition: A comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 22, 1 (2000), 63–84. Google ScholarDigital Library .
- 1985. Intersections. 266–322. Google ScholarCross Ref .
- 2005. Artistic brushstroke representation and animation with disk B-spline curve. In Proceedings of the ACM SIGCHI International Conference on Advances in Computer Entertainment Technology. 88–93. Google ScholarDigital Library .
- 1998. Pruning medial axes. Comput. Vis. Image Understand. 69, 2 (1998), 156–169. Google ScholarDigital Library .
- 2003. Constraint-based approach for automatic hinting of digital typefaces. ACM Trans. Graph. 22, 2 (2003), 131–151. Google ScholarDigital Library .
- 1996. Extraction of typographic elements from outline representations of fonts. Comput. Graph. Forum 15, 3 (1996), 259–268. Google ScholarCross Ref .
- 1995. Parts of visual form: Computational aspects. IEEE Trans. Pattern Anal. Mach. Intell. 17, 3 (1995), 239–251. Google ScholarDigital Library .
- 2001. Part-based representations of visual shape and implications for visual cognition. In Advances in Psychology. Vol. 130. 401–459. Google ScholarCross Ref .
- 1999. Parsing silhouettes: The short-cut rule. Percept. Psychophys. 61, 4 (1999), 636–660. Google ScholarCross Ref .
- 2016. Visual perception of shape altered by inferred causal history. Sci. Rep. 6, 36245 (2016). Google ScholarCross Ref .
- 2014. A geometric approach to stroke extraction for the chinese calligraphy robot. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA’14). 3207–3212. Google ScholarCross Ref .
- 2010. Example-based automatic font generation. In Smart Graphics.
Lecture Notes in Computer Science, Vol. 6133 . 127–138. Google ScholarCross Ref . - 2017. Animated construction of chinese brush paintings. IEEE Trans. Vis. Comput. Graph. 24, 12 (2017), 3019–3031. Google ScholarCross Ref .
- 1951. Theory of Elasticity. McGraw–Hill. Google Scholar .
- 2018. Perceptual organization. In Stevens’ Handbook of Experimental Psychology and Cognitive Neuroscience, Sensation, Perception, and Attention. Vol. 2. Chapter 18, 803–872.
4th Edition .Google ScholarCross Ref . - 2011. Measuring 3D point configurations in pictorial space. i-Perception 2, 1 (2011), 77–111. Google ScholarCross Ref .
- 2002. Learning-based cursive handwriting synthesis. In Proceedings of the 8th IEEE International Workshop on Frontiers in Handwriting Recognition. 157–162. Google ScholarCross Ref .
- 2013. Interview with Charles Bigelow. TUGboat 34, 2 (2013), 136–167.Google Scholar .
- 2002. Processing and visualization for diffusion tensor MRI. Med. Image Anal. 6, 2 (2002), 93–108. Google ScholarCross Ref .
- 2001. Orientation, scale, and discontinuity as emergent properties of illusory contour shape. Neural Comput. 13, 8 (
August 2001), 1683–1711. Google ScholarDigital Library . - 2012. Computationally evaluating and reproducing the beauty of chinese calligraphy. IEEE Intell. Syst.3 (2012), 63–72. Google ScholarDigital Library .
- 2002. Early computation of part structure: Evidence from visual search. Percept. Psychophys. 64, 7 (2002), 1039–1054. Google ScholarCross Ref .
- 1998. Extraction of perceptually salient contours by striate cortical networks. Vis. Res. 38, 5 (1998), 719–741. Google ScholarCross Ref .
- 2017. Synthesizing ornamental typefaces. Comput. Graph. Forum 36, 1 (2017), 64–75. Google ScholarDigital Library .
- 1997. Linear-time sleeve-fitting polyline simplification algorithms. In Proceedings of the 13th AutoCarto Symposium, Vol. 13. 214–223. https://cartogis.orgGoogle Scholar .
- 2016. Legible compact calligrams. ACM Trans. Graph. 35, 4, Article 122 (2016), 12 pages.
Article no. 122 .Google ScholarDigital Library .
Index Terms
- StrokeStyles: Stroke-based Segmentation and Stylization of Fonts
Recommendations
Stroke Segmentation and Recognition from Bangla Online Handwritten Text
ICFHR '12: Proceedings of the 2012 International Conference on Frontiers in Handwriting RecognitionThis paper deals with recognition of online handwritten Bangla (Bengali) text. Here, at first, we segment cursive words into strokes. A stroke may represent a character or a part of a character. We selected a set of Bangla words written by different ...
Effective radical segmentation of offline handwritten Chinese characters towards constructing personal handwritten fonts
DocEng '12: Proceedings of the 2012 ACM symposium on Document engineeringEffective radical segmentation of handwritten Chinese characters can greatly facilitate the subsequent character processing tasks, such as Chinese handwriting recognition/identification and the generation of Chinese handwritten fonts. In this paper, a ...
An Algorithm for Segmentation of Conglutinate Manuscript Financial Chinese Characters Based on the Character of Stroke
PACIIA '08: Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application - Volume 01In electronic commerce and the infomationization of finance, the recognition of manuscript financial Chinese characters by means of computer is a realm of significance and challeng. The key in this realm is the segmentation of the image of Chinese ...
Comments