Stroke break analysis: a practical method to study timeout value for handwriting recognition input

ABSTRACT

Handwriting recognition (HWR) input method has been considered to be one of the most usable text entry methods for handheld devices, especially for languages with large and complicated character sets such as Chinese. The paper studies stroke break times within handwritten characters and presents a new method for setting HWR timeout by examining the break time distributions. For multi-stroke character HWR input, a timeout is widely used as a segmentation technique to initiate the recognition process. In this paper, we examine the largest stroke break time in each character and explore the relationship between break time distribution and optimal HWR timeout. The study used Chinese as test material and the test independent variables were writing condition (input box, full screen) and user's posture while they were writing (hold device in hand, keep device on table). The main findings are: (1) the stroke break times are similar in full screen and input box conditions, though the users tend to write larger characters in full screen condition. (2) The stroke break times fit into a tight distribution. It is feasible to estimate optimal HWR timeout by studying stoke break time distribution. A nonparametric histogram method was used to model the stroke break distributions and it showed that typical Chinese HWR default timeouts are around 99% percentile in the distribution. (3) Differences in HWR stroke break distributions are very significant between individual users. The stroke break time analysis can also be applied to design HWR timeout customization scale.

References

1. MacKenzie I. S., and Soukoreff R. W. (2002). Text entry for mobile computing: models and methods, theory and practice. Human-Computer Interaction, 17, 147--198.
2. Goldberg D., and Richardson C. (1993). Touch-typing with a stylus, In Proceedings of the SIGCHI conference on Human factors in computing systems (INTERCHI' 93) (Amsterdam, The Netherlands, April 1993). ACM Press, New York, 80--87
3. Marila J., and Ronkainen S. (2004). Time-out in user interface: the case of mobile text input. Personal and Ubiquitous Computing, 8, 2, 110--116.
4. Silfverberg M., MacKenzie I. S., and Korhonen P. (2000). Predicting text entry speed on mobile phones. In Proceedings of the ACM conference on Human factors in computing systems (CHI'00) (The Hague, Amsterdam, April 2000). ACM Press, New York, 9--16.
5. Wu C., Yang Q., and Zhang K. (2003). Human performance modeling in temporary segmentation Chinese handwriting recognizer. Acta Psychologica Sinica, 35, 4, 483--491.
6. Hinckley K., Baudisch P., Ramos G., and Guimbretiere F.(2005). Design and analysis of delimiters for selection-action pen gesture phrases in Scriboli. In Proceeding of the SIGCHI conference on Human factors in computing systems (CHI'05) (Portland, Oregon, USA, April 2005) ACM Press, New York, 451--460.
7. Li Y., Hinckley K. Guan Z., and Landay J. A. (2005). Experimental Analysis of Mode Switching Techniques in Pen-based User Interfaces. In Proceeding of the SIGCHI conference on Human factors in computing systems (CHI'05) (Portland, Oregon, USA, April 2005) ACM Press, New York, 461--470.
8. Wright C.E. (1993). Evaluating the special role of time in the control of handwriting. Acta Psychologica, 82, 5--52.

Index Terms

• Human-centered computing

  • Human computer interaction (HCI)

    • Interaction devices

      • Touch screens