Paper Info
Title
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.
Year
DOI
Venue
2005
10.1145/1085777.1085827
Mobile HCI
Keywords
Field
DocType
break time distribution,stroke break distribution,timeout value,stoke break time distribution,full screen,stroke break analysis,stroke break time,handwriting recognition input,paper studies stroke break,stroke break time analysis,practical method,optimal hwr timeout,largest stroke break time,hwr stroke break distribution,timeout,timing analysis,handheld device,break,distribution,handwriting recognition,stroke
Histogram,Input method,Computer science,Segmentation,Handwriting recognition,Speech recognition,Nonparametric statistics,Timeout,Variables,Character encoding
Conference
ISBN
Citations 
PageRank 
1-59593-089-2
3
0.49
References 
Authors
8
2
Name
Order
Citations
PageRank
Yanqing Cui117913.32
Vuokko Lantz233320.79