Method and Apparatus for Identifying Embossed Characters

• US 20110150346A1
• Filed: 12/19/2009
• Published: 06/23/2011
• Est. Priority Date: 12/19/2009
• Status: Active Grant

• Current Assignee: MedAvail, Inc. (Walgreens Boots Alliance Incorporated)
• Original Assignee: MedAvail, Inc. (Walgreens Boots Alliance Incorporated)
• Inventors: Panetta, Richard
• Granted Patent: US 8,577,145 B2
• Time in Patent Office: Days
• US Class Current: 382/218
• CPC Class Codes: A47F 1/04 Racks or containers with arrangements for dispensing articles , e.g. by means of gravity or springs
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06K 15/024 for printing on segmented surfaces, e.g. sticker sheets, label rolls
• CPC Class Codes: G06K 7/10712 Fixed beam scanning
• CPC Class Codes: G06K 7/12 using a selected wavelength, e.g. to sense red marks and ignore blue marks
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/12 Detection or correction of errors, e.g. by rescanning the pattern
• CPC Class Codes: G06V 30/1429 Identifying or ignoring parts by sensing at different wavelengths
• CPC Class Codes: G06V 30/1434 Special illumination such as grating, reflections or deflections, e.g. for characters with relief

Abstract

In a method and apparatus for identifying an embossed character, light of one color is directed in one direction across the embossed character to illuminate certain character parts and light of another color is directed in another direction across the embossed character to illuminate other character parts. Image data for the two colors are captured and are subjected to separate image processing to detect edges highlighted by the directed light. The processed images are combined and supplemented with OCR analysis before being compared with predicted characters. Based on the comparison, a determination is made as to the probable identity of the character.

Claims

1. A method of identifying an embossed character comprising directing first light in a first direction across the embossed character to illuminate first parts of the character, recording first image data representing the character illuminated by the first light, directing second light in a second direction across the embossed character to illuminate second parts of the character, recording second image data representing the character illuminated by the second light, combining the first image data and the second image data to produce combined image data, comparing the combined image data to reference data, and on the basis of the comparison, identifying the character.

2. A method as claimed in claim 1, further comprising, the first light having a first color and the second light having a second color.

3. A method as claimed in claim 1, further comprising directing each of the first and the second light at a low angle of incidence to a plane of a surface within which the embossed character is formed.

4. A method as claimed in claim 1, further comprising the first direction being orthogonal to the second direction.

5. A method as claimed in claim 1 further comprising subjecting each of the first and second images to image processing prior to combining the first and second image data.

6. A method as claimed in claim 5, in which the image processing includes detecting character edges.

7. A method as claimed in claim 6, in which the first image data is scanned in the first direction to detect first character edges and the second image data is scanned in the second direction to detect second character edges.

8. A method as claimed in claim 1, further comprising obtaining a supplementary image of the character and processing data representing the combined image with data representing the supplementary image, and based on the processed data, identifying the character.

9. A method as claimed in claim 7, further comprising obtaining the supplementary image data using an OCR (optical character recognition) technique.

10. A method as claimed in claim 1, further comprising comparing the combined image data with predicted image data to derive a recognition confidence factor depending on a degree of matching of the combined image data to the predicted image data.

11. A method as claimed in claim 10, further comprising adjusting imaging conditions to maximize the recognition confidence factor.

12. A method as claimed in claim 10, further comprising adjusting at least one of package position and orientation to maximize the recognition confidence factor.

13. A system for identifying an embossed character comprising a lighting sub-system for directing first light in a first direction across the embossed character to illuminate first parts of the character and for directing second light in a second direction across the embossed character to illuminate second parts of the character, and an imaging sub-system for recording first image data representing the character illuminated by the first light and recording second image data representing the character illuminated by the second light, and a processing sub-system having a filtering module to filter the first image data to obtain first edge data corresponding to the light directed in the first direction and to filter the second image data to obtain second edge data corresponding to the light directed in the second direction, a combining module for combining the first image data and the second image data to produce combined image data, and an identification module to identify the character from the combined image data.

14. A system as claimed in claim 13, further comprising, the lighting sub-system including a first light source having light output of a first color and a second light source having light output at a second color.

15. A system as claimed in claim 14, further comprising the lighting sub-system having directing means to direct each of the first and the second light at a low angle of incidence to a plane of a surface within which the embossed character is formed.

16. A system as claimed in claim 15, further comprising the directing means operable to direct the first light in the first direction and the second light in the second direction, the first and second directions being orthogonal to one another.

17. A system as claimed in claim 13, further comprising an OCR reader for obtaining supplementary image data representing the character, and a processing module to aggregate and process the combined image data with the supplementary image data to produce output data, the processing module operable to identify the character based on the output data.

18. A system as claimed in claim 17, further comprising a comparator module for comparing the output data with predicted image data, and for applying a recognition confidence factor depending on a degree of matching of the output data and the predicted image data.

19. A method of serializing packages brought to an inspection station, the method comprising capturing an image of the package, machine reading at least a part of the image to derive first data, transmitting the image to a remote station for manual reading of another part of the image to derive second data, and applying to the package a machine readable tag coded for at least a part of the first data and at least a part of the second data.