System and method for automated symbolic recognition including symbolic modeling

• US 7,295,710 B1
• Filed: 01/11/2007
• Issued: 11/13/2007
• 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): Mehta; Bhavesh M
• Assistant Examiner(s): DULANEY, KATHLEEN YUAN
• Application Number:
  US11/652,307
• Time in Patent Office: 306 Days
• Field of Search: 382/200
• US Class Current: 382/200
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18162 related to a structural representation of the pattern
• CPC Class Codes: G06V 30/32 Digital ink

Abstract

An automated symbolic recognition system and method includes pre-stored symbolic models to support a three phase symbolic reshaping scheme during the symbol recognition process that includes: (a) deriving dissimilarity level from alphanumeric ID'"'"'s net topological variation and the integration of each of its arcpoly structural variation(s) signifying a reasonably accurate confidence level for the goodness of recognition, thus establishing a mechanism that derives dissimilarity level (or cost value) between image and database features including shape, size and topological relationship, (b) determining the reshaping or transformation of an arcpoly to another arcpoly by introducing variations to the original arcpoly to alter its shape and orientation and deriving at each step, the new cost value as a function of variation(s) present and imposed, and (c) determining the equivalent representation of an arcpoly by a succession of smaller and adjoining arcpoly(s) in order, or vice versa.

Claims

1. A computer readable storage medium having stored therein a computerized database used to automatically recognize alphanumeric symbols, comprising:

a set of logical symbols comprising a finite class of arcpolys, wherein each arc and line member has a unique orientation; and

a set of subclass symbols per logical symbol representing a finite subclass of arcpolys, each subclass member having a unique extreme point size and/or depth size;

wherein each subclass symbol is characterized by a group of features and wherein the database is accessed by program code that performs symbolic reshaping on one or more arcpolys to obtain different symbolic representations of an unrecognized alphanumeric symbol; and

wherein 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 computerized database of claim 1, additionally comprising a set of variances comprising (1) a set of arcpoly variance types, (2) a set of counterpart dissimilarity values and (3) a topological dissimilarity value per pair of arcpolys'"'"' relative location.

3. The computerized database of claim 1, wherein one or more arcpolys form a polyline and the unrecognized alphanumeric symbol is formed from one or more polylines, and a reduced list of candidate alphanumeric symbols is generated based on a plurality of alphanumeric symbol models of the unrecognized alphanumeric symbol.

4. The computerized database of claim 3, wherein the reduced candidate list is generated by undergoing multiple series of elimination of candidate alphanumeric symbols.

5. The computerized database of claim 1, wherein the symbolic reshaping includes a phase comprising:

criteria-based region growing and splitting of arcpolys so that they better conform to a plurality of alphanumeric symbol models included in the stored candidate list; and

computing a multi-stage post-processing of arcpolys so that they better conform to a plurality of alphanumeric symbol models.

6. The computerized database of claim 3, wherein the reduced list of candidate alphanumeric symbols is a subset of a stored candidate list, and wherein the stored candidate list is associated with the plurality of the symbolic models derived from arcpolys via an inverse mapping.

7. The computerized database of claim 6, wherein the inverse mapping comprises establishing a set of links from each symbolic representation to each alphanumeric symbol in the stored candidate list.

8. The computerized database of Claim 7, wherein symbolic reshaping for the unrecognized alphanumeric symbol comprises an ordered sequence of structural, topological and/or combined reshaping of each arcpoly, each time generating a new reduced alphanumeric candidate symbol list and dissimilarity value, until a candidate alphanumeric symbol is validated.

9. The computerized database of claim 1, wherein reshaping of an arcpoly comprises applying at least one of:

multi-level unit rotations, changes in extreme points size, and depth size on the arcpoly, each time transforming the arcpoly into a new arcpoly having a new orientation and/or new shape.

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

a first data storage having a set of logical symbols comprising a finite class of arcpolys, wherein each arc and line member of the logical symbol set has a unique orientation;

a second data storage having a set of subclass symbols per logical symbol representing a finite subclass of arcpolys, each subclass member having a unique extreme point size and/or depth size;

a third data storage having a digital representation of a set of modeled alphanumeric symbols;

a fourth data storage having structural and topological multi-type variances and counterpart dissimilarity values comprising the following;

(a) unit change extreme points size, (b) unit change depth size, (c) extra image structure size, (d) missing stored symbol size, (e) unit change single extreme point position, (f) unit change single extreme point extension, and (g) unit rotation; and

program code accessing the data storages and adapted to automatically classify the arcpolys of each unrecognized alphanumeric symbol into a selected set of logical symbol and subclass symbol pairs such that each unrecognized alphanumeric symbol can be recognized, and wherein the program code performs symbolic reshaping on one or more arcpolys to obtain different symbolic representations of an unrecognized alphanumeric symbol.

11. The system of claim 10, wherein one or more arcpolys form a polyline and the unrecognized alphanumeric symbol is formed from one or more polylines, and a reduced list of candidate alphanumeric symbols is generated based on a plurality of alphanumeric symbol models of the unrecognized alphanumeric symbol.

12. The system of claim 11, wherein the reduced list of candidate alphanumeric symbols is generated by undergoing multiple series of elimination of candidate alphanumeric symbols.

13. The system of claim 12, wherein the symbolic reshaping includes a phase comprising:

criteria-based region growing and splitting of arcpolys so that they better conform to the plurality of alphanumeric symbol models included in a stored candidate list; and

computing a multi-stage post-processing of arcpolys so that they better conform to the plurality of alphanumeric symbol models.

14. The system of claim 11, wherein the reduced list of candidate alphanumeric symbols is a subset of a stored candidate list, and wherein the stored candidate list is associated with the plurality of the alphanumeric symbolic models derived from arcpolys via an inverse mapping.

15. The system of claim 14, wherein the inverse mapping comprises establishing a set of links from each symbolic representation to each alphanumeric symbol in the stored candidate list.

16. The system of claim 11, additionally comprising a set of variances comprising (1) a set of arcpoly variance types, (2) a set of counterpart dissimilarity values and (3) a topological dissimilarity value per pair of arcpolys'"'"' relative location.

17. The system of claim 16, wherein symbolic reshaping for the unrecognized alphanumeric symbol comprises an ordered sequence of structural, topological and/or combined reshaping of each arcpoly, each time generating a new reduced alphanumeric candidate symbol list and dissimilarity value, until a candidate alphanumeric symbol is validated.

18. The system of claim 11, wherein symbolic reshaping on one of the one or more arcpolys comprises applying at least one of:

multi-level unit rotations, changes in extreme points size, and depth size on the arcpoly, each time transforming the arcpoly into a new arcpoly having a new orientation and/or new shape.

19. The system of claim 18, wherein the reshaping of one of the one or more arcpolys further comprises at least one of:

arc-to-arc rotation, line-to-line rotation, arc depth size variance, arc extreme points size variance, extra or missing arc extension(s) on each (or both) extreme point(s), line extreme points size variance, topological variance, and combined variances.

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

means for storing data having a set of logical symbols comprising a finite class of arcpolys, wherein each arc and line member of the logical symbol set has a unique orientation;

means for storing data having a set of subclass symbols per logical symbol representing a finite subclass of arcpolys, each subclass member having a unique extreme point size and/or depth size;

means for providing a set of topological relationships for each pair of arcpolys each comprising a one-of-nine topological connection code and separation, and wherein topological relational features are also automatically classified;

means for storing data having a digital representation of a set of modeled alphanumeric symbols;

means for storing data having structural and topological multi-type variances and counterpart dissimilarity values comprising the following;

(a) unit change extreme points size, (b) unit change depth size, (c) extra image structure size, (d) missing stored symbol size, (e) unit change single extreme point position, (f) unit change single extreme point extension, and (g) unit rotation; and

means for accessing the stored data adapted to automatically classify the arcpolys of each unrecognized alphanumeric symbol into a selected set of logical symbol and subclass symbol pairs such that each unrecognized alphanumeric symbol can be recognized.