Identifying a string formed from a number of hand-written characters

• US 7,881,536 B2
• Filed: 07/06/2010
• Issued: 02/01/2011
• 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, MOHAMMAD M
• Application Number:
  US12/831,244
• Publication Number:
  US 20100278430A1
• Time in Patent Office: 210 Days
• Field of Search: 382/100, 382173-179, 382186-188, 382/220, 382/229, 382309-311, 348/148, 345159-161, 345/173
• US Class Current: 382/186
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/2272 with lexical matching
• CPC Class Codes: G06V 30/268 Lexical context

Abstract

A method of identifying a string formed from a number of hand-written characters is disclosed. The method starts by determining character probabilities for each hand-written character in the string. Each character probability represents the likelihood of the respective hand-written character being a respective one of a number of predetermined characters. Next, template probabilities for the string are determined. Each template probability represents the likelihood of the string corresponding to a respective one of a number of templates. Each template represents a respective combination of character types. The step of determining the template probabilities for the string includes the sub-steps of determining the number of characters in the string, selecting templates having an identical number of characters, and obtaining a template probability for each selected template.

Claims

1. A method of identifying a string formed from a number of hand-written characters, said method comprising the steps of:

determining by a processor character probabilities for each hand-written character in the string, each character probability representing the likelihood of the respective hand-written character being a respective one of a number of predetermined characters;

determining by the processor template probabilities for the string, each template probability representing the likelihood of the string corresponding to a respective one of a number of templates, each template representing a respective combination of character types, wherein the step of determining the template probabilities for the string comprises the sub-steps of;

determining the number of characters in the string;

selecting templates having an identical number of characters; and

obtaining a template probability for each selected template.

2. The method of claim 1, wherein each predetermined character has a respective character type.

3. The method of claim 1, wherein the character types include at least one of digits, letters, and punctuation marks.

4. The method of claim 1, wherein the processor is configured to determine the character probabilities including using a character classifier.

5. The method of claim 1, wherein the template probability is determined by statistical analysis of a text corpus.

6. The method of claim 1, further comprising the steps of determining a potential character string corresponding to each template by determining the character type of each character in the string from the template, and selecting one of the predetermined characters for each character in the template, the predetermined character being selected in accordance with the determined character type and the character probability.