Scribble matching

Details Scribble matching Scribble matching

1997-11-19

2000-01-25

Lee, Thomas D

Image analysis

Pattern recognition

Unconstrained handwriting

283187, 283192, 283122, G06K 918, G06K 900, G06K 946

Patent

active

060185910

ABSTRACT:
The present invention relates to scribble matching methods, ie. methods for searching samples of electronic ink without having first to translate the ink into ASCII text. The methods of the present invention find application in pen-based computer devices. The invention entails the identification and encoding of velocity minima in the input scribble. Three scribble matching algorithms are described--a syntactic matcher, a word matcher and an elastic matcher. The syntactic matcher encodes the input scribble according to the shape of the scribble in the region of the velocity minima. The word matcher encodes the input scribble according to the heights of the velocity minima from a reference line, using a continuous height encoding scheme. The elastic matcher encodes the input scribble according to a classification of the velocity minima and intermediate points. The use of velocity minima in the encoding of scribble input provides a stable set of points and leads to improved performance in comparison with known scribble matching methods.

REFERENCES:
patent: 4020463 (1977-04-01), Himmel
patent: 4524456 (1985-06-01), Araki et al.
patent: 4653107 (1987-03-01), Shojima et al.
patent: 4718103 (1988-01-01), Shojima et al.
patent: 4807143 (1989-02-01), Matsuvra
patent: 4969201 (1990-11-01), Takasaki et al.
patent: 5023913 (1991-06-01), Lipscomb
patent: 5126948 (1992-06-01), Mitchell et al.
patent: 5392363 (1995-02-01), Fujisaki et al.
patent: 5467407 (1995-11-01), Guberman et al.
patent: 5473742 (1995-12-01), Polyakov et al.
patent: 5581655 (1996-12-01), Cohen et al.
patent: 5623555 (1997-04-01), Nelson et al.
"The State of the Art in On-Line Handwriting Recognition" C. C. Tappert et al., IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, No. 8 (1990).
Daniel P. Lopresti & Andrew Tomkins. "Pictographic naming." Technical Report 007-mei-ptil-mitl-228-1, Matsushita Information Technology Laboratory, Princeton, Nov., 1992.
Daniel P. Lopresti & Andrew Tompkins. "A comparison of techniques for graphical database queries." Technical Report MITL-TR-45-93, Matsushita Information Technology Laboratory, Princeton, May, 1993.
Thierry Paquet & Yves Lecourtier. "Recognition of handwritten sentences using a restricted lexicon." Pattern Recognition. 26(3) : 391-407, 1993.
Information Theory, Aug. 29, 1960, London, GB pp. 300-316, LS Frishkopf et al `Machine reading of cursive script` *p. 301, line 27-line 29*.
Int Neural Network Conf. vol. 1, Jul. 9, 1990, Paris FR--pp. 141-144, XP145254 P Morasso et al `Self-organization of an allograph lexicon`Section "1, Introduction", Section "2.1 Segmentaton module".
Pattern Recognition, vol. 26, No. 3, 1993, pp. 451-460, XP367317 P. Morasso et al. `Recognition experiments of cursive dynamic handwriting self-organizing networks`, Section "2. Preprocessing" *figure 1*.
Pattern Recognition, vol. 26, No. 3, 1993--pp. 391-407, XP367312, T Paquet et al `Recognition of handwritten sentences using a restricted lexicon`, p. 401 Section "4.3.2 Normalizing the editing costs".
1990 IEEE Int. Conf. on Systems, Man and Cybernetics, Nov. 4, 1990 Los Angeles, CA, pp. 835-838, XP215462 DW Fincher et al "Multi-sensor data fusing using neural networks" *p. 836, left col., line 41-line 55; figure 5*.

Affiliated with

Also associated with

Rating

Scribble matching does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Scribble matching, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Scribble matching will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2321598