NSF Award
8821869
There is a widely recognized need for improved user interfaces that will make computers easier to use for people with no technical training, and that will improve the general efficiency and ergonomics of many computer applications where the conventional keyboard is too limited. One promising approach is based on handwriting and gesture recognition, which will enable people to use common handwriting skills to communicate with computers for a wide range of applications such as text edition, form filling, and interactive graphics. But what is needed before handwriting/gesture interface can become widely popular is accurate and reliable recognition of normal cursive handwriting. The Phase I study examined a new cursive handwriting recognition system consisting of a front- end Dynamic Programming (DP) algorithm, extensions to the DP algorithm to find the vest match and all plausible alternatives, dictionary matching, rules-based discrimination to resolve "confusions," and syntax constraints. Prospects for eventual commercialization were judged to be very promising based on tests with a data base of cursive words which resulted in 99.2% correct recognition in user-independent mode, and 99.9% in user-dependent mode. Phase II will perform the basic research needed to fully develop the recognition system for eventual commercialization. This includes collecting a comprehensive data base of cursive handwriting, further algorithm research and testing, human factors design, and development of a real-time engineering prototype.
