CLASSIFYING A STRING FORMED FROM HAND-WRITTEN CHARACTERS

• US 20110293186A1
• Filed: 08/07/2011
• Published: 12/01/2011
• Est. Priority Date: 10/15/2001
• Status: Active Grant

• Current Assignee: Silverbrook Research Pty Limited
• Original Assignee: Silverbrook Research Pty Limited
• Inventors: Napper, Jonathon Leigh
• Granted Patent: US 8,285,048 B2
• Time in Patent Office: Days
• 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 classifying a character string formed from a known number of hand-written characters is disclosed. The method starts by determining character probabilities for each hand-written character in the character string. Each character probability represents a likelihood of the respective hand-written character being a respective one of a plurality of predetermined characters. Each predetermined character has a respective character type. Character templates having the known number of characters are next identified. Each character template has a respective predetermined probability and represents a respective combination of character types. Character sequence probabilities corresponding to each of the character templates having the known number of characters are next determined. The character sequence probabilities are a function of the predetermined probability of the respective character template and the character probabilities of the hand-written character in the character string. The character string is classified as the sequence of characters having the highest character sequence probability.

Claims

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

identifying by a processor character templates having the known number of characters, each character template having a respective predetermined probability of occurrence in a text corpus and representing a respective combination of character types;

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

determining by the processor character sequence probabilities corresponding to each of the character templates having the known number of characters, the character sequence probabilities being a function of the predetermined probability of the respective character template and the character probabilities of the hand-written characters in the character string matching the character types of the character template; and

classifying by the processor the character string as the sequence of characters having the highest character sequence probability.

2. The method of claim 1, wherein the function is of the predetermined probability of the respective character template and the character probabilities having character types corresponding to the combination of character types represented by the respective character template.

3. The method of claim 1, wherein the function is of the predetermined probability of the respective character template and the highest character probabilities having character types corresponding to the combination of character types represented by the respective character template.

4. The method of claim 1, wherein the character types include digits, letters, and punctuation marks.