Electronic Ink Indexing
Handwritten text; Online handwriting
With the proliferation of personal digital assistants (PDAs) and pen-based handheld devices, it is important that computers understand handwritten text (or electronic ink). In this pen-based environment, one can have handwritten file contents, handwritten file names, handwritten directory names, handwritten email messages, handwritten signatures, etc. With the large bodies of handwritten content, indexing techniques are essential in order to search for the relevant content. The fact that the data is handwritten makes the problem more difficult than in conventional situations. No two persons handwrite a word in exactly the same way. Even the same person cannot write a word in the same way twice. This makes the indexing and retrieval of handwritten data a hard problem.
Retrieval techniques for handwritten data have to be scalable so that they can handle the continually growing sizes of multimedia data, e.g.,...
- 1.Lopresti DP, Tomkins A. Approximate matching of hand-drawn pictograms. In: Proceedings of the 3rd International Workshop on Frontiers in Handwriting Recognition; 1993. p. 102–11.Google Scholar
- 3.Rabiner LR, Juang BH. Fundamentals of speech recognition. Englewood Cliffs: Prentice Hall; 1993.Google Scholar
- 4.Sin BK, Kim JH. A statistical approach with HMMs for on-line cursive Hangul (Korean script) recognition. In: Proceedings of the 2nd International Conference on Document Analysis and Recognition; 1993. p. 147–50.Google Scholar
- 5.Bakis R. Continuous speech word recognition via centisecond acoustic states. In: Proceedings of the 91st Mts. of the Acoustical Society of America; 1976.Google Scholar
- 6.Aref WG, Vallabhaneni P, Barbará D. On training hidden Markov models for recognizing handwritten text. In: Proceedings of the International Workshop on Frontiers of Handwriting Recognition; 1994.Google Scholar
- 8.Rubine DH. The automatic recognition of gestures. PhD Dissertation, Carnegie Mellon University, Pittsburgh, December, 1991. Also Technical Report Number CMU-CS-91-202.Google Scholar
- 11.de la Briandais R. File searching using variable length keys. In: Proceedings of the Western Joint Computer Conference; 1959. p. 295–8.Google Scholar
- 12.Aref WG, Barbará D, Lopresti DP, Tomkins A. Ink as a first-class multimedia object. In: Jajodia S, Subramanian VS, editors. Multimedia database systems: issues and research directions. Berlin: Springer; 1995.Google Scholar
- 13.Kamel I. Fast retrieval of cursive handwriting. In: Proceedings of the International Conference on Information and Knowledge Management; 1996. p. 91–8.Google Scholar
- 14.Kamel I, Barbará D. Retrieving electronic ink by content. In: Proceedings of the International Workshop on Multimedia Database Systems; 1996. p. 54–61.Google Scholar