Image analysis – Pattern recognition – Unconstrained handwriting
Reexamination Certificate
2005-03-17
2009-06-23
Mariam, Daniel G (Department: 2624)
Image analysis
Pattern recognition
Unconstrained handwriting
Reexamination Certificate
active
07551779
ABSTRACT:
Described is a computer-implemented system and method that detects and differentiates scratch-out gestures from other electronic ink, e.g., entered via a pen. The system and method compare boundary-based criteria to differentiate, which eliminates the need to have a specially-shaped scratch-out pattern, instead allowing a wide variety of scratch-out styles to be detected. Criteria includes boundary-based evaluations such as whether the potential scratch-out gesture intersects previously recognized words or characters, whether the scratch-out gesture has a width that is at least a threshold percentage of the width of a word or character bounding box, whether the electronic ink extends beyond the midpoint of the bounding box, and whether at least some portion of the scratch-out gesture is above a baseline of the word or character. Scratch-out gestures entered in freeform input writing areas and boxed input writing areas are supported.
REFERENCES:
patent: 5500937 (1996-03-01), Thompson-Rohrlich
patent: 5666139 (1997-09-01), Thielens et al.
patent: 5848187 (1998-12-01), Bricklin et al.
patent: 5991441 (1999-11-01), Jourjine
patent: 2003/0182630 (2003-09-01), Saund et al.
Garside Adrian J.
Guericke Daphne
Murayama Takanobu
Pennington Ernest L.
Schilling Shou-Ching
Mariam Daniel G
Microsoft Corporation
Workman Nydegger
LandOfFree
Word or character boundary-based scratch-out gesture... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Word or character boundary-based scratch-out gesture..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Word or character boundary-based scratch-out gesture... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4090919