Line extraction in digital ink

• US 7,526,128 B2
• Filed: 02/17/2004
• Issued: 04/28/2009
• Est. Priority Date: 02/26/2003
• Status: Expired due to Fees

• Current Assignee: Silverbrook Research Pty Limited
• Original Assignee: Silverbrook Research Pty Limited
• Inventors: Silverbrook, Kia, Napper, Jonathon Leigh, Lapstun, Paul, Koubaroulis, Dimitrios
• Primary Examiner(s): Chawan; Sheela C
• Application Number:
  US10/778,090
• Publication Number:
  US 20040165774A1
• Time in Patent Office: 1,897 Days
• Field of Search: 382/179, 382/187, 382/186, 382/189, 382/203, 382/177, 382/178, 382/226, 382/311, 382/202, 382/296, 382/298, 382/309, 715/541, 715/863, 715/531, 715/502, 715/527, 715/530, 345/179, 345/173, 345/156
• US Class Current: 382/179
• CPC Class Codes: G06V 30/333 Preprocessing; Feature extraction

Abstract

A method and system of line extraction in a digital ink sequence of handwritten text data points, the method including the steps of: obtaining are provided in which a stroke sequence comprised of a sequence of are strokes is obtained, the strokes are segmented into a sequence of substrokes by applying a stroke segmentation algorithm angular differences are calculated between neighboring groups of substrokes, in the sequence of substrokes, and the positions of the extrema of the angular differences are determined, thereby indentifying the substrokes at line breaks and enabling line extraction.

Claims

1. A searchable electronic filing system including:

(a) a first database for storing a digital representation of each of a plurality of printed documents, each printed document including machine-readable identification data which distinguishes it from the others;

(b) a second database for storing annotation digital ink, the annotation digital ink representing at least one physical handwritten annotation on at least one of the printed documents;

(c) a processor configured to;

i. segment the annotation digital ink into lines by;

obtaining a stroke sequence comprised of a sequence of strokes;

removing small strokes less than a threshold length;

segmenting the strokes into a sequence of substrokes by;

computing a relative angle for each line segment connecting successive stroke data points; and

segmenting the stroke into substrokes if the difference between successive relative angles is greater than a preset threshold; and

identifying the substrokes at line breaks, thereby facilitating line extraction, by;

computing N-neighbourhood centroids;

computing angular differences between N-neighbouring substrokes, or groups of substrokes; and

computing local maxima of the angular differences in the sequence of substrokes;

ii. accept a digital ink query;

iii. match the digital ink query against at least some of the annotation digital ink in the second database, to thereby identify a corresponding one of the documents in the first database.

2. A searchable electronic filing system as claimed in claim 1 further including a handheld sensing device for generating the annotation digital ink during interaction with one of the plurality of printed documents.