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.
- 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.Google ScholarCross Ref
- 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 Google ScholarDigital Library
- 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. Google ScholarDigital Library
- 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. Google ScholarDigital Library
- Wu C., Yang Q., and Zhang K. (2003). Human performance modeling in temporary segmentation Chinese handwriting recognizer. Acta Psychologica Sinica, 35, 4, 483--491. Google ScholarDigital Library
- 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. Google ScholarDigital Library
- 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. Google ScholarDigital Library
- Wright C.E. (1993). Evaluating the special role of time in the control of handwriting. Acta Psychologica, 82, 5--52.Google ScholarCross Ref
Index Terms
- Stroke break analysis: a practical method to study timeout value for handwriting recognition input
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 ...
Indic script family and its offline handwriting recognition for characters/digits and words: a comprehensive survey
AbstractHandwriting recognition has become an active area of research in pattern recognition and machine learning in recent years. Handwriting recognition systems have a variety of applications ranging from digital character conversion to signboard ...
Numeral characters and capital letters segmentation recognition in mixed handwriting context
ICDAR '95: Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2For the analytic on-line recognition of handwriting, the range of pattern recognition problems can be described by the severity of letter segmentation required. More difficult problems require an interaction of letter segmentation and recognition. These ...
Comments