System and method for automated symbolic recognition including database modeling

• US 7,242,805 B1
• Filed: 04/18/2003
• Issued: 07/10/2007
• Est. Priority Date: 04/18/2003
• Status: Expired due to Fees

• Current Assignee: Kamran Reihani
• Original Assignee: Kamran Reihani
• Inventors: Reihani, Kamran
• Primary Examiner(s): Mancuso; Joseph
• Assistant Examiner(s): DULANEY, KATHLEEN YUAN
• Application Number:
  US10/419,479
• Time in Patent Office: 1,544 Days
• Field of Search: 382/198, 382/202, 382/177, 382/224
• US Class Current: 382/198
• CPC Class Codes: G06V 30/347 Sampling; Contour coding; Stroke extraction
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

An automated symbolic recognition system and method includes multiple representations of each alphanumeric in the database by identifying a finite number of exemplars per alphanumeric symbol.

Claims

1. A method of automatically recognizing alphanumeric symbols, comprising:

(a) providing a digital representation of a set of unrecognized alphanumeric symbols;

(b) storing multiple models for each alphanumeric symbol, the models comprising at least one generic model, and at least one exemplar model;

(c) computing a symbolic representation of each unrecognized alphanumeric symbol comprising a finite set of arcpolys based on the stored alphanumeric symbol models so that the unrecognized symbols can be recognized; and

(d) providing a set of topological relationships for each pair of arcpolys each comprises a one-of-nine topological connection code and separation, and wherein topological relational features are also automatically classified.

2. The method of claim 1, wherein the at least one generic model comprises a plurality of generic models and the at least one exemplar model comprises a plurality of exemplar models.

3. The method of claim 1, wherein each alphanumeric symbol comprises a set of structural symbols the a set of topological connection code symbols, and wherein structural symbols describe an arcpoly'"'"'s shape and orientation.

4. The method of claim 3, wherein each structural symbol comprises a pair of logical and subclass symbols.

5. The method of claim 3, wherein each member of the set of topological connection code symbols comprises topological connection code(s) mappings to two pairs of logical and subclass symbols.

6. A system for automatically recognizing alphanumeric symbols, comprising:

(a) means for receiving a digital representation of a set of unrecognized alphanumeric symbols;

(b) means for storing multiple models for each alphanumeric symbol, the models comprising at least one generic model, and at least one exemplar model;

(c) means for computing a symbolic representation of each unrecognized alphanumeric symbol comprising a finite set of arcpolys based on the stored alphanumeric symbol models so that the unrecognized symbols can be recognized; and

(d) means for providing a set of topological relationships for each pair of arcpolys each comprises a one-of-nine topological connection code and separation, and wherein topological relational features are also automatically classified.

7. The system of claim 6, wherein the at least one generic model comprises a plurality of generic models and the at least one exemplar models comprises a plurality of exemplar models.

8. The system of claim 6, wherein each alphanumeric model comprises a set of structural symbols and the set of topological connection code symbols.

9. The system of claim 8, wherein each structural symbol comprises a pair of logical and subclass symbols.

10. The system of claim 8, wherein each member of the set of topological connection code symbols comprises topological connection code(s) mappings to two pairs of logical and subclass symbols.

11. A method of automatically recognizing alphanumeric symbols, comprising:

(a) providing a digital representation of a set of unrecognized alphanumeric symbols;

(b) providing a database comprising;

dynamic variables determined experimentally by conducting multiple experiments on multiple users;

(c) computing a symbolic representation of each unrecognized alphanumeric symbol comprising a finite set of arcpolys based on the stored alphanumeric symbol models so that the unrecognized symbols can be recognized; and

(d) providing a set of topological relationships for each pair of arcpolys each comprises a one-of-nine topological connection code and separation, and wherein topological relational features are also automatically classified.

12. A system of automatically recognizing alphanumeric symbols, comprising:

(a) means for receiving digital representation of a set of unrecognized alphanumeric symbols;

(b) means for storing comprising;

dynamic variables determined experimentally by conducting multiple experiments on multiple users;

(c) means for computing a symbolic representation of each unrecognized alphanumeric symbol comprising a finite set of arcpolys in conjunction with the storing means so that the unrecognized symbols can be recognized; and

(d) means for providing a set of topological relationships for each pair of arcpolys each comprises a one-of-nine topological connection code and separation, and wherein topological relational features are also automatically classified.