Method/system for estimating the orientation of a segment of digital ink

• US 7,630,553 B2
• Filed: 10/10/2003
• Issued: 12/08/2009
• Est. Priority Date: 11/05/2002
• Status: Expired due to Fees

• Current Assignee: Silverbrook Research Pty Limited
• Original Assignee: Silverbrook Research Pty Limited
• Inventors: Napper, Jonathon L, Lapstun, Paul
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): Akhavannik; Hadi
• Application Number:
  US10/531,733
• Publication Number:
  US 20060018561A1
• Time in Patent Office: 2,251 Days
• Field of Search: 382/186, 382312-316
• US Class Current: 382/186
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/333 Preprocessing; Feature extraction

Abstract

The invention provides a method/system for estimating the orientation of a segment of digital ink using pen orientation information. In one form, the invention is a method of estimating the orientation of a segment of digital ink, the method including the steps of: measuring the azimuth of the pen at a sampling rate during writer generation of the segment of digital ink; and estimating the orientation of the segment of digital ink using the measured azimuth of the pen at sampled points.

Claims

1. A pen-based computing system for estimating the orientation of a segment of digital ink, the system including a pen-based computing pen to input digital ink, and a processor adapted to estimate the orientation of said segment by measuring the azimuth of the pen at a sampling rate during writing of said segment by an optically imaging pen on a surface printed with tags, each tag encoding data on an identity of the surface associated with a digital description of the surface and on the respective location of that tag on the surface, the digital ink being generated by associating the digital description with the data encoded by the tags optically imaged by the pen during said writing;

determining a mean azimuth for all of the sampled points, and subtracting the determined mean azimuth from each measured azimuth of each sampled point of said segment.

2. A system as claimed in claim 1, wherein the processor is further adapted to use the estimated orientation of the segment of digital ink in a digital ink line orientation normalization technique.

3. A system as claimed in claim 1, wherein the processor is further adapted to use a single, fixed orientation estimation for a line of digital ink.

4. A system as claimed in claim 1, wherein the processor is further adapted to use an orientation estimation that varies across a line of digital ink.

5. A system as claimed in claim 1, wherein the processor is further adapted to normalize the estimated orientation to be within the range of 0°

to 360 °

.

6. A system as claimed in claim 1, wherein the segment of digital ink is more than one character of digital ink.

7. A system as claimed in claim 1, wherein the segment of digital ink is a line segment.

8. A system as claimed in claim 7, wherein the processor is further adapted to perform line segmentation by measuring a change in azimuth value.

9. A system as claimed in claim 1, wherein the processor is further adapted to use a writer independent handwriting model to estimate the orientation.

10. A system as claimed in claim 1, wherein the processor is further adapted to use a writer dependent handwriting model trained using sample digital ink input by the writer to estimate the orientation.

11. A system as claimed in claim 10, wherein the writer dependent handwriting model is trained using sample digital ink input by the writer using a consistent baseline.

12. A system as claimed in claim 10, wherein the writer dependent handwriting model is trained using arbitrary sample digital ink input by the writer.