Image analysis – Pattern recognition – Unconstrained handwriting
Reexamination Certificate
2000-08-22
2004-08-31
Chang, Jon (Department: 2623)
Image analysis
Pattern recognition
Unconstrained handwriting
C382S187000, C382S218000, C382S228000, C382S229000
Reexamination Certificate
active
06785417
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates generally to computer devices, and more particularly computer devices arranged to receive handwritten input.
BACKGROUND OF THE INVENTION
Contemporary computing devices allow users to enter handwritten words (e.g., in cursive handwriting and/or printed handwritten characters) and symbols (e.g., a character in Far East languages). The words and symbols can be used as is, e.g., to function as readable notes and so forth, or can be converted to text for more conventional computer uses. To convert to text, for example, as a user writes strokes representing words or other symbols onto a touch-sensitive computer screen or the like, a handwriting recognizer (e.g., trained with millions of samples, employing a dictionary, context and other rules) is able to convert the handwriting data into dictionary words or symbols. In this manner, users are able to enter textual data without necessarily needing a keyboard.
When dealing with typewritten input entered into a word processing program, it is relatively straightforward to implement a “find” or “search” feature as part of the program. With text, a user types in a search string and possibly enters some properties of the string, (e.g., bold typeface), and the program searches for a string in a document that exactly matches the word and any specified properties. Such a search is straightforward because typewritten input entered into a word processing program is defined by a limited set of codes, e.g., ASCII numeric values represent alphanumeric characters, and there is a limited set of properties a string can have. In general, the word processing program simply advances through the document attempting to match the full set of entered codes of the search string with a string of codes in a document in order to find an exact (allowing for any wildcards) match.
However, when entering handwritten ink, e.g., via an electronic ink processing program, it is virtually impossible for a user to write a word exactly the same way twice. Thus, searching is not possible via the simple “exact-string-match-or-not” operation. One attempted search method featurizes the electronic ink (e.g., handwritten data in the form of coordinates and other information) entered by a user, and searches through the document to find another piece of ink with similar features. This method is not very reliable, as for example, the same user can write two sets of ink, each of which is intended to be the same word, but that significantly vary from each other's features from the computer's perspective. A second method uses simple string comparison, using the translated text word that appears for any handwritten input. This second method is also relatively unreliable, because such a search depends on a recognizer making a correct translation for each translated word, despite the reality that recognizers are not one hundred percent accurate.
SUMMARY OF THE INVENTION
Briefly, the present invention provides a system and method for finding matches for recognized handwritten words, by comparing a given search word (a typed-in character set or handwritten word that has been recognized) against the words in a document, including recognized words and any possible alternates for those recognized words as returned by a recognizer. For handwritten (ink) words, one implementation may look for an exact match between an entered search word (and possibly alternates of the search word) and the recognized words and their alternates stored in a handwritten document. To this end, the recognized word and each alternate associated therewith are examined against an entered search word and possibly its alternates.
Numerous other variations are possible because of the use of alternates, which also may be returned with a probability ranking. For example, rather than a strict exact match test on the alternates, a scheme that looks for a percentage of matching characters can be implemented, with the user optionally adjusting the percentage, e.g., from loose to exact. Other variations include the weighting of certain characters, (e.g., the first character has to exactly match, with only a percentage of others needed), and/or factoring in the number of syllables. Since alternates are returned with a probability, the probabilities of alternates may be used, e.g., a looser match is adequate on a highly probable word, while an exact match is required on a less probable word. Other variations include length of word weighting, Bayesian combination of probabilities to determine weighting, alternate to alternate exact match, percentage of alternate to alternate matches, the percentage of the percentages and so on, and the use of word/alternate matching in conjunction with ink/feature/bitmap/image matching. Various combinations of these variations are also feasible.
Other advantages will become apparent from the following detailed description when taken in conjunction with the drawings, in which:
REFERENCES:
patent: 5594640 (1997-01-01), Capps et al.
patent: 5615285 (1997-03-01), Beernink
patent: 5675665 (1997-10-01), Lyon
patent: 5682439 (1997-10-01), Beernick et al.
patent: 5710916 (1998-01-01), Barbara et al.
patent: 5764799 (1998-06-01), Hong et al.
patent: 5812697 (1998-09-01), Sakai et al.
patent: 5828991 (1998-10-01), Skiena et al.
patent: 5855000 (1998-12-01), Waibel et al.
patent: 5857099 (1999-01-01), Mitchell et al.
patent: 5953451 (1999-09-01), Syeda-Mahmood
patent: 5960447 (1999-09-01), Holt et al.
patent: 5995664 (1999-11-01), Shimomura
patent: 6005973 (1999-12-01), Seybold et al.
patent: 6014460 (2000-01-01), Fukushima et al.
patent: 6041141 (2000-03-01), Yamamoto et al.
patent: 6111985 (2000-08-01), Hullender et al.
patent: 6473517 (2002-10-01), Tyan et al.
patent: 6493464 (2002-12-01), Hawkins et al.
patent: 2002/0013795 (2002-01-01), Dresevie et al.
patent: 2002/0049796 (2002-04-01), Dresevie et al.
patent: 07110845 (1995-04-01), None
Senda et al. “Document Image Retrieval System Using Character Candidates Generated by Character Recognition Process.” Proc. of the 2ndInt. Conf. on Document Analysis and Recognition, Oct. 20, 1993, pp. 541-546.*
Liang et al. “Efficient Algorithms for Segmentation and Recognition of Printed Characters in Document Processing.” IEEE Pacific Rim Conf. on Communications, Computers and Signal Processing, vol. 1, May 19, 1993, pp. 240-243.
Lee et al. “A New Methodology for Gray-Scale Character Segmentation and Recognition.” Proc. Of the 3rdInt. Conf. on Document Analysis and Recognition, vol. 1, Aug. 14, 1995, pp. 524-527.
Ariki et al. “Segmentation and Recognition of Handwritten Characters Using Subspace Method.” Proc. Of the 3rdInt. Conf. on Document Analysis and Recognition, vol. 1, Aug. 14, 1995, pp. 120-123.
Zhao et al. “New Method for Segmenting Unconstrained Handwritten Numeral String.” Proc. Of the 4thInt. Conf on Document Analysis and Recognition, vol. 2, Aug. 18, 1997, pp. 524-527.
Carrano. Data Abstraction and Problem Solving with C++; Walls and Mirrors. The Benjamin/Cummings Publishing Company, Inc,. 1995, pp. 150-163, 175-176, 179-180.
Morita et al. “A Fast and Compact Data Structure of Storing Multi-Attribute Relations Among Words.” IEEE In Conf. on Systems, Man and Cybernetics, vol. 3, Oct. 11, 1998, pp. 2791-2796.
Arica et al. “A New Scheme for Off-Line Handwritten Connected Digit Recognition.” Proc. KES '98, 2ndInt. Conf. on Knowledge-Based Intelligent Electronic Systems, vol. 2, Apr. 21, 1998, pp. 329-335.
Jung et al. Machine Printed Character Segmentation Method Using Side Profiles. Proc. SMC '99, IEE Int. Conf. on Systems, Man, and Cybernetics, vol. 6, Oct. 12, 1999, pp. 863-867.
Lui Charlton E.
Williamson Peter H.
Chang Jon
Law Offices of Albert S Michalik, PLLC
LandOfFree
Method and system for searching for words in ink word documents does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for searching for words in ink word documents, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for searching for words in ink word documents will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3271158