Skip to main content
SpringerLink
Log in

A statistical handwriting model for style-preserving and variable character synthesis

  • Original Paper
  • Published:
International Journal on Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

Synthesizing handwritten-style characters is an interesting issue in today’s handwriting analysis field. The purpose of this study is to artificially generate training data, foster a deep understanding of human handwriting, and promote the use of the handwritten-style computer fonts, in which the individuality or variety of the synthesized characters is considered important. Research considering such two properties together, however, is very rare. In this paper, a handwriting model is proposed to synthesize various handwritten characters while preserving the writer’s individuality from a limited number of training data, using a statistical approach. The proposed model is verified in single- and multiple-stroke characters, such as Arabic numbers, small English letters, and Japanese Kanji letters. Synthesized characters are evaluated in three ways. First, they are analyzed visually using the selected samples, and the relationship between the training and synthesized characters is explained. Second, the personalities and varieties of all the data are evaluated using a conventional writer verification method. Third, a questionnaire is developed and administered to evaluate the subjective responses of the users regarding the personal styles of the synthesized characters. The results prove that the proposed model stably synthesizes personalized characters by being invariant to the number of training data, whereas the variety increases gradually as the data increase.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Baxendale D., Renshaw I.D.: The large scale searching of handwriting samples. J. Forensic Sci. Soc. 19(4), 245–251 (1979)

    Article  Google Scholar 

  2. Chang W.-D., Shin J.: Dynamic positional warping: dynamic time warping for online handwriting. Int. J. Pattern Recogn. Artif. Intell. 23(5), 967–986 (2009)

    Article  Google Scholar 

  3. Cho S.-J., Kim J.H.: Bayesian network modeling of strokes and their relationships for on-line handwriting recognition. Pattern Recogn. 37, 253–264 (2004)

    Article  MATH  Google Scholar 

  4. Choi, H., Cho, S.-J., Kim, J.H.: Generation of handwritten characters with Bayesian network based on-line handwriting recognizers. In: Proceedings of ICDAR’03, vol. 2, pp. 995–999 (2003)

  5. Choi H., Cho, S.-J., Kim, J.H.: Writer dependent online handwriting generation with Bayesian network. In: Proceedings of IWFHR’04, pp. 130–135 (2004)

  6. Choi H., Kim J.H.: Probabilistic synthesis of personal-style handwriting. IEICE Trans. E 92(D (4), 653–661 (2009)

    Google Scholar 

  7. Devroye L., McDougall M.: Random fonts for the simulation of handwriting. Electron. Publish. 8(4), 281–294 (1995)

    Google Scholar 

  8. van Galen G.P.: Handwriting: issues for a psychomotor theory. Hum. Move. Sci. 10(2–3), 165–191 (1991)

    Article  Google Scholar 

  9. Gupta G.K., Joyce R.C.: Using position extrema points to capture shape in on-line handwritten signature verification. Pattern Recogn. 40, 2811–2817 (2007)

    Article  MATH  Google Scholar 

  10. Guyon, I.: Handwriting synthesis from handwritten glyphs. In: Proceedings of IWFHR’96, pp. 309–312 (1996)

  11. Hilton, O.: Scientific Examination of Questioned Documents, Revised Edition. CRC Press LLC: Boca Raton, FL (1993)

  12. Jain A.K., Griess F.D., Connell S.D.: On-line signature verification. Pattern Recogn. 35, 2963–2972 (2002)

    Article  MATH  Google Scholar 

  13. Jawahar, C.V., Balasubramanian, A.: Synthesis of online handwriting in Indian languages. In: Proceedings of IWFHR’06, pp. 108–113 (2006)

  14. Kameya H., Mori S., Oka R.: A segmentation-free biometric writer verification method based on continuous dynamic programming. Pattern Recogn. Lett. 27, 567–577 (2006)

    Article  Google Scholar 

  15. Kapoor T.S., Kapoor M., Sharma G.P.: Study of the form and extent of natural variation in genuine writings with age. J. Forensic Sci. Soc. 25(5), 371–375 (1985)

    Article  Google Scholar 

  16. Kim, B.-H., Koo, K.-M., Park, Y.-M., Cha, E.-Y: A study on quantization method using ART2 for contents-based image retrieval (in Korean). In: Proceedings of 22th Conference on Korea Information Processing Society, vol. 11, no. 2 (2004)

  17. Lee D.-H., Cho H.-G.: A new synthesizing method for handwriting Korean scripts. Int. J. Pattern Recogn. AI 12(11), 45–61 (1998)

    Article  Google Scholar 

  18. Lee J., Yoon H.-S., Sho J., Chun B.T., Chung Y.K.: Using geometric extrema for segment-to-segment characteristics comparison in online signature verification. Pattern Recogn. 37(1), 93–103 (2004)

    Article  MATH  Google Scholar 

  19. Lin Z., Wan L.: Style-preserving English handwriting synthesis. Pattern Recogn. 40(7), 2097–2109 (2007)

    Article  MATH  Google Scholar 

  20. Mori, M., Suzuki, A., Shio, A., Ohtsuka, S.: Generating new samples from handwritten numerals based on point correspondence. In: Proceedings of IWFHR’00, pp. 281–290 (2000)

  21. Nakamura, Y., Kidode, M.: Online writer verification using Kanji handwriting. In: MRCS’06: LNCS, vol. 4105, pp. 207–214. Springer, Hedelberg (2006)

  22. Ney H.: The use of one-stage dynamic programming algorithm for connected word recognition. IEEE Trans. Acoust. Speech Signal Process. ASSP 32(2), 263–271 (1984)

    Article  Google Scholar 

  23. Niels, R., and Vuurpijl, L.: Generating copybooks from consistent handwriting styles. In: Proceedings of ICDAR, vol. 2, pp. 1009–1013 (2007)

  24. Osborn A.S.: Questioned Documents, pp. 231. The Lawyers’ Co-operative Publishing Co, Rochester (1910)

    Google Scholar 

  25. Ota, I., Yamamoto, R., Sako, S., Sagayama, S.: Online handwritten Kanji recognition based on inter-stroke grammar. In: Proceedings of ICDAR’07, vol. 2, pp. 1188–1192 (2007)

  26. Plamondon R.: A kinematic theory of rapid human movements, part I: movement representation and generation. Biol. Cybern. 72(4), 295–307 (1995)

    Article  MATH  Google Scholar 

  27. Plamondon R.: A kinematic theory of rapid human movements, part II: movement time and control. Biol. Cybern. 72(4), 309–320 (1995)

    Article  MATH  Google Scholar 

  28. Plamondon R., Guerfali W.: The generation of handwriting with delta-lognormal synergies. Biol. Cybern. 78, 119–132 (1998)

    Article  MATH  Google Scholar 

  29. Plamondon R., Guerfali W., LI X.: The generation of oriental characters: new perspectives for automatic handwriting processing. Int. J. Pattern Recogn. AI 12(1), 31–44 (1998)

    Article  Google Scholar 

  30. Rabiner L., Juang B.-H.: Fundamentals of Speech Recognition, pp. 209–213. PTR Prentice Hall, Englewood Cliffs (1993)

    Google Scholar 

  31. Setlur S., Govindaraju V.: Generating manifold samples from a handwritten word. Pattern Recogn. Lett. 15, 901–905 (1994)

    Article  Google Scholar 

  32. Shin J.: On-line cursive hangul recognition that uses DP matching to detect key segmentation points. Pattern Recogn. 37, 2101–2112 (2004)

    Article  MATH  Google Scholar 

  33. Sin B.-K., Kim J.H.: Network-based approach to Korean handwriting analysis. Int. J. Pattern Recogn. AI 12(2), 233–249 (1998)

    Article  Google Scholar 

  34. Srihari S.N., Cha S.H., Arora H., Lee S.: Individuality of handwriting. J. Forensic Sci. Soc. 47(4), 856–872 (2002)

    Google Scholar 

  35. Varga,T., Bunke, H.: Generation of synthetic training data for an HMM-based handwriting recognition system. In: Proceedings of ICDAR’03, vol. 1, pp. 618–622 (2003)

  36. Varga, T., Kilchhofer, D., Bunke, H.: Template-based synthetic handwriting generation for the training of recognition systems. In: Proceedings of 12th conference of the international graphonomics society, pp. 206–211 (2005)

  37. Wada, Y., Ohkawa, K., Sumita, K.: Generation of diversiform characters using a computational handwriting model and a genetic algorithm. In: ICANN’01: LNCS, vol. 2130, pp. 1217–1224. Springer, Hedelberg (2001)

  38. Wang J., Wu C., Xu Y.-Q., Shum H.-Y.: Combining shape and physical models for online cursive handwriting synthesis. Int. J. Doc. Anal. Recogn. 7(4), 1433–2833 (2004)

    Google Scholar 

  39. Zheng, Y., Doermann, D.: Handwriting matching and its application to handwriting synthesis. In: Proceedings of ICDAR’05, pp. 861–865 (2005)

Download references

Author information

Authors and Affiliations

  1. Graduate School of Computer Science and Engineering, The University of Aizu, Tsuruga, Ikki-machi, Aizuwakamatsu City, Fukushima, 965-8580, Japan

    Won-Du Chang & Jungpil Shin

Authors
  1. Won-Du Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jungpil Shin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jungpil Shin.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Chang, WD., Shin, J. A statistical handwriting model for style-preserving and variable character synthesis. IJDAR 15, 1–19 (2012). https://doi.org/10.1007/s10032-011-0147-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-011-0147-7

Keywords

Search

Navigation