Method for analyzing cursive writing

• US 5,940,533 A
• Filed: 12/19/1995
• Issued: 08/17/1999
• Est. Priority Date: 04/20/1994
• Status: Expired due to Fees

• Current Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Original Assignee: US Philips Corporation (Koninklijke Philips N.V.)
• Inventors: Gentric, Philippe
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US08/564,258
• Time in Patent Office: 1,337 Days
• Field of Search: 382/185, 382/186, 382/187, 382/203, 382/230, 382/177, 382/178, 382/179, 382/229, 382/155, 382/189, 706/13
• US Class Current: 382/186
• CPC Class Codes: G06F 18/21 Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
• CPC Class Codes: G06V 30/2272 with lexical matching
• CPC Class Codes: G06V 30/373 using a special pattern or subpattern alphabet

Abstract

Information is extracted from a hand-written text by means of a graphics tablet (1). The curves thus obtained make it possible to recognize primitives, namely basic forms, representing a way of writing a part of a letter. More accomplished forms, called allographs, are constructed from primitives in order to construct a letter or in even a group of two or three letters. When the series of codes corresponds to a known object from a dictionary of allographs (3), each defined by the sequence of codes of its primitives, the corresponding allograph is recognized. The genetic algorithm is used to improve the population of strings. "Descendants", obtained by combining two starting strings (7), are constructed from a limited-quantity selection of strings (9), from among which descendants the most appropriate are in turn chosen, this gradually optimizing the population. Applications: recognition of cursive writing.

Claims

1. A method for analyzing cursive writing, said method comprising the steps of

recognizing elementary forms in a word to be recognized that is written with cursive writing;

reconstructing target allographs from the elementary forms;

searching a dictionary of a plurality of defined allographs for a set of defined allographs identical to or resembling the target allographs;

delivering a plurality of strings of characters based on the set of defined allographs capable of corresponding to the word to be recognized;

performing a reproduction procedure on the plurality of strings based on a starting population of parent strings, by constructing descendant strings, each descendant string being obtained by crossing, at least some of the descendant strings being appended to the starting population.

2. A method according to claim 1, wherein the starting population includes a selection of only the most appropriate parent strings, additionally the most appropriate parent strings being chosen from among the descendant strings for addition to the starting population of parent strings.

3. A method according to claim 2, wherein:

a refined population is obtained following the reproduction procedure; and

the reproduction procedure is performed again on the obtained refined population.

4. A method according to claim 2, wherein each of the parent strings is picked at random from the starting population.

5. A method according to claim 2, wherein mutations are introduced during some of the crossings.

6. A method according to claim 1, wherein each of the parent strings is picked at random from the starting population.

7. A method according to claim 1, wherein crossing combines elements picked from two parent strings of the starting population.

8. A method according to claim 7, wherein for each of the parent strings, at least one of the elements which is picked therefrom to construct a descendant string is picked therefrom at random.

9. A method according to claim 8, wherein mutations are introduced during some of the crossings.

10. A method according to claim 7, wherein mutations are introduced during some of the crossings.

11. A method according to claim 1, wherein mutations are introduced during some of the crossings.

12. A method according to claim 1, wherein:

a refined population is obtained following the reproduction procedure; and

the reproduction procedure is performed again on the obtained refined population.

13. A method according to claim 12, wherein each of the parent strings is picked at random from the starting population.

14. A method according to claim 12, wherein mutations are introduced during some of the crossings.

15. A method according to claim 6, wherein mutations are introduced during some of the crossings.