Medication identification and verification

• US 9,098,900 B2
• Filed: 10/27/2011
• Issued: 08/04/2015
• Est. Priority Date: 10/29/2010
• Status: Active Grant

• Current Assignee: Mint Solutions Holding BV
• Original Assignee: Mint Solutions Holding BV
• Inventors: Helgason, Ivar S., Reynisson, Gauti Thor, Runarsdottir, Maria
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US13/882,094
• Publication Number:
  US 20130279774A1
• Time in Patent Office: 1,377 Days
• Field of Search: 382128-134, 356/301, 424/464
• US Class Current: 1/1
• CPC Class Codes: A61J 1/03 for pills or tablets containers for pills or tablets with special dispensing means therefor B65D83/04
• CPC Class Codes: A61J 2200/70 Device provided with specific sensor or indicating means
• CPC Class Codes: A61J 2205/20 Colour codes
• CPC Class Codes: A61J 2205/40 by shape or form, e.g. by using shape recognition
• CPC Class Codes: A61J 7/0084 for multiple medicaments
• CPC Class Codes: G06T 17/10 Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• CPC Class Codes: G06V 20/66 Trinkets, e.g. shirt buttons or jewellery items recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 2201/06 Recognition of objects for industrial automation
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

A pill identification system includes a device which is configured to collect three-dimensional image data of surfaces of one or more pills, generate geometric features of the pill(s) from the three-dimensional image data, and identify the pill(s) using the geometric features. In some embodiments, the identified pills can be verified for patient administration by comparing the identified pills to prescription information.

Claims

1. A system comprising:

an imaging device configured to collect surface image data of one or more pills;

a controller configured to control the imaging device to collect the image data of the one or more pills;

the system being configured to generate a three-dimensional point cloud using the surface image data of the one or more pills;

the system being configured to generate geometric data for each pill from the three-dimensional point cloud; and

the system being configured to determine the identity of each of the one or more pills based on at least the geometric data generated from the three-dimensional point cloud.

2. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills by applying a set of rules to the geometric data for each pill.

3. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills by comparing the geometric data of each of the one or more pills to a database containing geometric data associated with a plurality of known pills.

4. A system as in claim 1, wherein the system comprises a structured light scanner and the imaging device comprises a first camera configured to capture images of light reflecting from the one or more pills.

5. A system as in claim 4, wherein the structured light scanner comprises a laser light source and the first camera is configured to capture images of laser light reflecting from the one or more pills.

6. A system as in claim 5, wherein the laser light source comprises a 650 nm laser diode module.

7. A system as in claim 4, wherein the first camera is configured to obtain a visual image of the one or more pills when the pills are fully illuminated.

8. A system as in claim 4, wherein the structured light scanner is configured to generate the three-dimensional point cloud data regarding surfaces of the one or more pills.

9. A system as in claim 1, wherein the imaging device comprises a stereoscopic imager.

10. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills additionally based on a measured pill color.

11. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills additionally based on a measured pill weight.

12. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills additionally based on determined pill markings.

13. A system as in claim 1, wherein the geometric data generated from the three-dimensional point cloud comprises pill markings, and the system is configured to determine the identity of each of the one or more pills based on at least the pill markings.

14. A system as in claim 1, wherein the geometric data generated from the three-dimensional point cloud comprises pill surface texture, and the system is configured to determine the identity of each of the one or more pills based on at least the pill surface texture.

15. A system as in claim 1, wherein the system is configured to determine the identity of each of the one or more pills additionally based on information received from a radio frequency identification tag.

16. A system as in claim 1, wherein the identity of each of the one or more pills comprises an indication of a dosage amount contained by each of the one or more pills.

17. A system as in claim 1, wherein the system is configured to record the identity and quantity of each of the one or more pills.

18. A system as in claim 1, wherein the system is configured to provide an indication of whether the one or more pills should be administered to a patient.

19. A system as in claim 1, further comprising a chamber which is configured to be closed to ambient light.

20. A system as in claim 1, further comprising a pill support and a chamber configured to house the pill support.

21. A system as in claim 20, wherein the pill support comprises a tray which is removable from the chamber.

22. A system as in claim 1, further comprising a second camera configured to obtain a visual image of the one or more pills when the pills are fully illuminated.

23. A system as in claim 1, wherein the one or more pills comprise at least one of a pill, a capsule, tablet or a caplet.

24. A system as in claim 1, wherein the one or more pills comprise a plurality of pills, and a first pill of the plurality of pills contains a first medication which is different from a second medication contained in a second pill of the plurality of pills.

25. A system as in claim 1, wherein the one or more pills comprise a single pill.

26. A method comprising:

collecting surface image data of one or more pills;

generating a three-dimensional point cloud of surface data for each of the one or more pills;

generating geometric data from the three-dimensional point cloud data;

using a computer processor to identify the one or more pills based on at least the geometric data generated from the point cloud data.

27. A method as in claim 26, wherein collecting surface image data comprises operating a structured light scanner to collect surface image data of the one or more pills.

28. A method as in claim 27, wherein operating a structured light scanner comprises applying laser light to surfaces of the one or more pills and using a first camera to capture images of laser light reflecting from the surfaces of the one or more pills.

29. A method as in claim 28, wherein applying laser light comprises using a 650 nm laser diode module.

30. A method as in claim 26, collecting surface image data comprises operating a stereoscopic imager to collect surface image data of the one or more pills.

31. A method as in claim 26, wherein identifying the one or more pills comprises applying a set of rules to the geometric data for each pill.

32. A method as in claim 26, wherein identifying the one or more pills comprises comparing the geometric data of each pill to a database containing geometric data associated with a plurality of known pills.

33. A method as in claim 26, further comprising comparing the identities of each of the one or more pills to a list of pills approved for administration to a patient.

34. A method as in claim 26, further comprising recording the identity and quantity of each of the one or more pills.

35. A method as in claim 26, wherein the geometric data includes geometric data regarding a dividing line on a pill, and identifying the pill comprises identifying the pill based on at least the geometric data regarding the dividing line.

36. A method as in claim 35, wherein the geometric data includes a thickness of the dividing line on a pill, and identifying the pill comprises identifying the pill based on at least the thickness of the dividing line.

37. A method as in claim 26, wherein the geometric data includes geometric data regarding surface texture of the more or more pills, and identifying the one or more pills comprises identifying the one or more pills based on at least the surface texture.

38. A method as in claim 37, wherein identifying the one or more pills comprises identifying the one or more pills additionally based on a measured pill color.

39. A method as in claim 26, wherein identifying the one or more pills comprises identifying the one or more pills additionally based on a measured pill weight.

40. A method as in claim 26, wherein identifying the one or more pills comprises determining a dosage amount of each of the one or more pills.

41. A method as in claim 26, wherein the one or more pills comprise a plurality of pills, and a first pill of the plurality of pills contains a first medication which is different from a second medication contained in a second pill of the plurality of pills.

42. A method of performing surface scanning, the method comprising:

projecting a laser light pattern onto a three-dimensional surface, the laser light comprising laser light within at least one of the red and infrared spectrum;

receiving, with a camera, laser light reflected from a portion of the three-dimensional surface; and

using light only from at least one of a green and blue spectrum of the reflected light to determine the location of the portion of the three-dimensional surface from which the reflected light reflected.

43. A method as in claim 42, wherein projecting a laser light pattern onto a three-dimensional surface comprises projecting the laser light pattern onto a pill surface to generate three-dimensional scanning data, and the method further comprises:

generating geometric data from the three-dimensional scanning data; and

identifying the pill based on at least the geometric data generated from the scanning data.