System and method for selecting segmentation parameters for optical character recognition

Patent metadata

Field	Value
Publication number	US-9317767-B2
Application number	US-201213653948-A
Country	US
Kind code	B2
Filing date	Oct 17, 2012
Priority date	Oct 17, 2012
Publication date	Apr 19, 2016
Grant date	Apr 19, 2016

Abstract

A computer-implemented method for selecting at least one segmentation parameter for optical character recognition is provided. The method can include receiving an image having a character string that includes one or more characters. The method can also include receiving a character string identifying each of the one or more characters. The method can also include automatically generating at least one segmentation parameter. The method can also include performing segmentation on the image having the character string using the at least one segmentation parameter. The method can also include determining if a resultant segmentation satisfies one or more criteria and if the resultant segmentation satisfies the one or more criteria, selecting the at least one segmentation parameter.

First claim

What is claimed is:

1. A computer-implemented method for selecting at least one segmentation parameter for optical character recognition comprising:
receiving, using one or more computing devices, an image having a character string that includes one or more characters;
receiving, using the one or more computing devices, a character string identifying each of the one or more characters;
automatically generating, using the one or more computing devices, at least one segmentation parameter;
performing segmentation, using the one or more computing devices, on the image having the character string using the at least one segmentation parameter, wherein segmentation is configured to separate each character of the character string;
determining, using the one or more computing devices, if a resultant segmentation satisfies an ASCII uniformity criteria; and
if the resultant segmentation satisfies the ASCII uniformity criteria, selecting the at least one segmentation parameter.

2. The computer-implemented method of claim 1 , further comprising:
providing, using the one or more computing devices, a user-selectable option associated with the segmentation, the user-selectable option configured to allow a user to indicate either a correct segmentation or an incorrect segmentation.

3. The computer-implemented method of claim 1 , further comprising:
providing, using the one or more computing devices, a user-selectable option configured to allow a user to manually generate a manually generated segmentation.

4. The computer-implemented method of claim 1 , further comprising:
determining, using one or more computing devices, if a resultant segmentation satisfies one or more criteria based on the criteria being set to a threshold value or an optimization value.

5. The computer-implemented method of claim 1 , further comprising:
generating, using the one or more computing devices, a database of images each having its own character string and correct segmentation regions for each character.

6. The computer-implemented method of claim 1 , further comprising:
receiving, using the one or more computing devices, an indication of a correct segmentation for the character string having a correct set of segmentation parameters.

7. The computer-implemented method of claim 6 , further comprising:
applying, using the one or more computing devices, the correct set of segmentation parameters to a second image in a database.

8. The computer-implemented method of claim 1 , wherein the at least one segmentation parameter includes one or more of polarity, line refinement, angle search range, skew search range, normalization mode, stroke width, binarization threshold, border fragments, pixel count, fragment contrast threshold, character height, character width, intercharacter gap, intracharacter gap, fragment distance to main line, fragment merge mode, minimum character aspect, character width type, analysis mode, pitch metric, pitch type, minimum pitch, space insertion, width of space character.

9. A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon, which when executed by a processor, cause the processor to perform operations comprising:
receiving, using one or more computing devices, an image having a character string that includes one or more characters;
receiving, using the one or more computing devices, a character string identifying each of the one or more characters;
automatically generating, using the one or more computing devices, at least one segmentation parameter;
performing segmentation, using the one or more computing devices, on the image having the character string using the at least one segmentation parameter, wherein segmentation is configured to separate each character of the character string;
determining, using the one or more computing devices, if a resultant segmentation satisfies an ASCII uniformity criteria; and
if the resultant segmentation satisfies the A criteria, selecting the at least one segmentation parameter.

10. The computer program product of claim 9 , wherein operations further comprise:
providing, using the one or more computing devices, a user-selectable option associated with the segmentation, the user-selectable option configured to allow a user to indicate either a correct segmentation or an incorrect segmentation.

11. The computer program product of claim 9 , wherein operations further comprise:
providing, using the one or more computing devices, a user-selectable option configured to allow a user to manually generate a manually generated segmentation.

12. The computer program product of claim 9 , wherein operations further comprise:
determining, using one or more computing devices, if a resultant segmentation satisfies one or more criteria based on the criteria being set to a threshold value or an optimization value.

13. The computer program product of claim 12 , wherein operations further comprise:
generating, using the one or more computing devices, a database of images each having its own character string and correct segmentation regions for each character.

14. The computer program product of claim 9 , wherein operations further comprise:
receiving, using the one or more computing devices, an indication of a correct segmentation for the character string having a correct set of segmentation parameters.

15. The computer program product of claim 14 , wherein operations further comprise:
applying, using the one or more computing devices, the correct set of segmentation parameters to a second image in a database.

16. The computer program product of claim 9 , wherein the at least one segmentation parameter includes one or more polarity, line refinement, angle search range, skew search range, normalization mode, stroke width, binarization threshold, border fragments, pixel count, fragment contrast threshold, character height, character width, intercharacter gap, intracharacter gap, fragment distance to main line, fragment merge mode, minimum character aspect, character width type, analysis mode, pitch metric, pitch type, minimum pitch, space insertion, width of space character.

17. A computing system configured for selecting at least one segmentation parameter for optical character recognition comprising:
one or more processors configured to receive an image having a character string that includes one or more characters, the one or more processors further configured to receive a character string identifying each of the one or more characters, the one or more processors further configured to automatically generate at least one segmentation parameter, the one or more processors further configured to perform segmentation on the image having the character string using the at least one segmentation parameter, wherein segmentation is configured to separate each character of the character string, the one or more processors further configured to determine if a resultant segmentation satisfies an ASCII uniformity criteria and if the resultant segmentation satisfies the ASCII uniformity criteria, the one or more processors further configured to select the at least one segmentation parameter.

18. The computing system of claim 17 , wherein the one or more processors are further configured to receive an indication of a correct segmentation for the character string having a correct set of segmentation parameters and to apply the correct set of segmentation parameters to a second character string.

Assignees

• Cognex Corp

Inventors

• Zadeh Ali
• Petry John

Classifications

• G06K9/344 Primary

  Physics · mapped topic

• G06K9/00409

  Physics · mapped topic

• G06K9/00436

  Physics · mapped topic

• G06V30/333 Primary

  Preprocessing; Feature extraction · CPC title

• G06V30/153 Primary

  using recognition of characters or words · CPC title