Classifying an input character

• US 7,848,574 B2
• Filed: 03/30/2010
• Issued: 12/07/2010
• Est. Priority Date: 10/15/2001
• Status: Expired due to Fees

• Current Assignee: Silverbrook Research Pty Limited
• Original Assignee: Silverbrook Research Pty Limited
• Inventors: Napper, Jonathon Leigh
• Primary Examiner(s): Ahmed; Samir A.
• Assistant Examiner(s): Rashidian; Mehdi
• Application Number:
  US12/750,587
• Publication Number:
  US 20100189352A1
• Time in Patent Office: 252 Days
• Field of Search: 382/159, 382/164, 382/171, 382/173, 382/177, 382/179, 382/181, 382185-187, 382/216, 382226-228, 382/259, 382/300, 382202-203, 382/209, 382/213, 382/224
• 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 30/244 using graphical properties, e.g. alphabet type or font

Abstract

A method for classifying an input character is disclosed. Character models are used. Each character model is associated with an output character and defines a model specific segmentation scheme for that output character and an associated segment model. The model specific segmentation scheme defines a minimum length corresponding to a number of points in a stroke of the output character and a minimum length threshold. Using each of the character models, the input character is decomposed into segments and the segments are evaluated against the segment model of the respective character model to produce a score indicative of the conformity of the segments with the segment model. The character model that produced the highest score is selected and the input character is classified as the output character associated with the character model that produces the highest score.

Claims

1. A method for classifying an input character, the method comprising the steps of, in a processing system, using a processor to implement:

(a) for each of a plurality of character models, each character model being associated with an output character and defining a model specific segmentation scheme for that output character and an associated segment model, the model specific segmentation scheme defining a minimum length corresponding to a number of points in a stroke of the output character and a minimum length threshold;

(i) decomposing the input character into one or more segments in accordance with the model specific segmentation scheme of the respective character model; and

(ii) evaluating the one or more segments against the segment model of the respective character model to produce a score indicative of the conformity of the one or more segments with the segment model;

(b) selecting the character model that produced the highest score; and

,

(c) classifying the input character as the output character associated with the character model that produces the highest score.

2. The method of claim 1, wherein each character model has a plurality of associated model specific segmentation schemes.

3. The method of claim 2, wherein the method includes for each character model, determining whether the input character is able to be segmented with one of the segmentation schemes, and if the input character is unable to be segmented, changing the segmentation scheme.

4. The method of claim 1, wherein the method includes classifying the input character as any one of a letter, a number, or a punctuation mark.

5. The method of claim 1, wherein the score rewards closer conformance to an ideal.

6. The method of claim 1, wherein the method includes defining different rules for decomposing the input character into one or more segments for different character models.

7. The method of claim 1, wherein fuzzy logic rules are used in evaluating the one or more segments against the segment model of the respective character model.