Optical processing of surfaces to determine cleanliness

• US 8,229,204 B2
• Filed: 12/01/2009
• Issued: 07/24/2012
• Est. Priority Date: 06/29/2009
• Status: Active Grant

• Current Assignee: Ecolab USA Incorporated (Ecolab, Inc.)
• Original Assignee: Ecolab, Inc.
• Inventors: Wagner, Christopher C.
• Primary Examiner(s): Punnoose, Roy M
• Application Number:
  US12/628,478
• Publication Number:
  US 20100328476A1
• Time in Patent Office: 966 Days
• Field of Search: 382/108, 382/141
• US Class Current: 382/141
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30124 Fabrics; Textile; Paper
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06V 10/141 Control of illumination

Abstract

Techniques are described for determining cleanliness of various surfaces by processing images of the surfaces. The surfaces may comprise, for example, drinking glasses, dishes, fabric swatch arrays, Tosi plates, ceramic tiles, or stainless steel coupons. In one example, a system includes a camera to capture a digital image of a surface, a light source to illuminate the surface, a housing to enclose the surface, the camera, and the light source in a light-tight environment, and an analysis computer to receive the digital image, calculate a luminosity value for the surface from the digital image, and determine a cleanliness value for the surface from the calculated luminosity value. The analysis computer may automatically configure an environment in which to capture the digital image such that the environment is suited for the particular surface to be analyzed. The analysis computer may also cause the camera to automatically capture the digital image.

Claims

1. A method comprising:

receiving, with a computing device, an identification of a ware type corresponding to a surface;

automatically configuring, with the computing device, an environment in which to capture a digital image of the surface based on the identification of the ware type;

receiving, with the computing device, the digital image of a surface;

calculating a luminosity value for the surface from the digital image; and

determining, with the computing device, a cleanliness value for the surface from the calculated luminosity value.

3. The method of claim 1, wherein the environment comprises at least one of a lighting arrangement, a lighting position relative to the surface, a housing, an internal coloring of the housing, a camera position relative to the surface, a camera aperture, and a camera shutter speed.

4. The method of claim 3,

wherein receiving the identification of the ware type comprises receiving an identification that the ware type comprises one of a drinking glass, a plate, and a stainless steel coupon, and

wherein automatically configuring the environment comprises positioning an array of light-emitting diodes (LEDs) such that light emitted by the LEDs of the array is aimed at the surface.

5. The method of claim 3,

wherein receiving the identification of the ware type comprises receiving an identification that the ware type comprises one of a fabric swatch array and a ceramic tile, and

wherein automatically configuring the environment comprises enabling an array of light-emitting diodes (LEDs) configured to provide diffused lighting to illuminate the surface.

6. The method of claim 1 wherein receiving a digital image of a surface includes receiving the digital image of the surface from a camera that captures the digital image of the surface.

7. The method of claim 1, wherein calculating the luminosity value for the surface comprises:

calculating a histogram from luminosity values of pixels of the digital image, wherein the histogram comprises a plurality of bins corresponding to a range of the luminosity values, and wherein each bin of the histogram comprises a bin index and a bin value representative of a number of pixels in the digital image that have the luminosity value corresponding to the bin index; and

calculating an average luminosity value from the histogram.

8. The method of claim 1, wherein determining a cleanliness value comprises correlating the calculated luminosity value to predetermined cleanliness values.

9. The method of claim 8, wherein the predetermined cleanliness values correspond to known cleanliness values for control surfaces of a same ware type as the received identification of the ware type.

10. The method of claim 1, further comprising:

determining a threshold luminosity value; and

counting a number of pixels in the digital image for which corresponding luminosity values exceed the threshold luminosity value,

wherein determining the cleanliness value further comprises determining the cleanliness value from the luminosity value for the surface and the counted number of pixels.

2. A method comprising:

automatically configuring, based on a ware type identification, an environment in which to capture a digital image of at least a portion of a surface corresponding to the ware type identification;

analyzing, with a computing device, the digital image and calculating a luminosity value for the at least a portion of the surface based on the analysis; and

determining, with the computing device, a cleanliness value for the at least a portion of the surface based on the calculated luminosity value.

11. A system comprising:

a camera to capture a digital image of a surface;

a light source to illuminate the surface;

a housing to enclose the surface, the camera, and the light source in a light-tight environment; and

an analysis computer to receive a ware type identification corresponding to the surface, configure an environment within the housing in which to capture the digital image based on the ware type, receive the digital image, analyze the digital image and calculate a luminosity value for the surface based on the analysis, and determine a cleanliness value for the surface based on the calculated luminosity value.

12. The system of claim 11, wherein the analysis computer is configured to automatically enable the light source and to control the camera to capture the digital image.

13. The system of claim 11, further comprising a light source actuator coupled to the light source to control an angle of the light source with respect to the surface.

14. The system of claim 11, further comprising a camera actuator coupled to the camera and to control a height of the camera with respect to the surface.

15. The system of claim 11, wherein the surface corresponds to a stainless steel coupon, and wherein the housing comprises an interior color of white.

16. The system of claim 11, wherein the surface corresponds to a drinking glass, and wherein the housing comprises an interior color of black.

17. The system of claim 11, wherein the surface corresponds to one of a fabric swatch array or a ceramic tile, and wherein the housing comprises an interior color of black.

18. The system of claim 11, wherein the surface corresponds to a dish, wherein the housing comprises an interior color of black.

19. The system of claim of claim 11, wherein the analysis computer is configured to calculate the luminosity value for the digital image by calculating a histogram from luminosity values of pixels of the digital image, wherein the histogram comprises a plurality of bins corresponding to a range of the luminosity values, and wherein each bin of the histogram comprises a bin index and a bin value representative of a number of pixels in the digital image that have the luminosity value corresponding to the bin index, and calculating an average luminosity value from the histogram.

20. The system of claim 11, wherein the analysis computer is configured to determine the cleanliness value by correlating the calculated luminosity value to predetermined cleanliness values, wherein the predetermined cleanliness values correspond to known cleanliness values for control wares of the same ware type as the ware type corresponding to the surface depicted in the digital image.

21. The system of claim 11, wherein the light source comprises a direct-lighting array of light-emitting diodes (LEDs) and a diffused-lighting array of LEDs.

22. The system of claim 21, wherein the analysis computer enables the direct-lighting array of LEDs when a ware corresponding to the surface comprises one of a drinking glass, a stainless steel coupon, or a dish.

23. The system of claim 21, wherein the analysis computer enables the diffused-lighting array of LEDs when a ware corresponding to the surface comprises one of a fabric swatch array or a ceramic tile.

24. The system of claim 11, further comprising a washing apparatus to wash the surface, wherein the analysis computer is configured to automatically disable the washing apparatus when the analysis computer determines that the surface has achieved a cleanliness value that exceeds a threshold.

25. A non-transitory computer-readable medium encoded with instructions for causing a programmable processor to:

receive an identification of a ware type corresponding to the surface;

automatically configure an environment in which to capture the digital image of the surface based on the identification of the ware type;

receive a digital image of a surface;

calculate a luminosity value for the surface from the digital image; and

determine a cleanliness value for the surface from the calculated intensity value.

26. The non-transitory computer-readable medium of claim 25, further encoded with instructions to automatically configure an environment in which to capture the digital image of the surface based on the identification of the ware type, wherein the environment comprises at least one of a lighting arrangement, a lighting position relative to the surface, a housing, an internal coloring of the housing, a camera position relative to the surface, a camera aperture, and a camera shutter speed.

27. The non-transitory computer-readable medium of claim 26,

wherein the instructions to receive the identification comprise instructions to receive an identification that the ware type comprises one of a drinking glass, a plate, and a stainless steel coupon, and

wherein the instructions to automatically configure an environment comprise instructions to position an array of light-emitting diodes (LEDs) such that light emitted by the LEDs of the array is aimed at the surface.

28. The non-transitory computer-readable medium of claim 26,

wherein the instructions to receive the identification comprise instructions to receive an identification that the ware type comprises one of a fabric swatch array and a ceramic tile, and

wherein the instructions to automatically configure an environment comprise instructions to configure an array of light-emitting diodes (LEDs) configured to provide diffused lighting to illuminate the surface.

29. The non-transitory computer-readable medium of claim 25, further encoded with instructions to control a camera that captures the digital image of the surface.

30. The non-transitory computer-readable medium of claim 25, wherein the instructions to calculate a luminosity value for the surface comprise instructions to:

calculate a histogram from luminosity values of pixels of the digital image, wherein the histogram comprises a plurality of bins corresponding to a range of the luminosity values, and wherein each bin of the histogram comprises a bin index and a bin value representative of a number of pixels in the digital image that have the luminosity value corresponding to the bin index; and

calculate an average luminosity value from the histogram.

31. The non-transitory computer-readable medium of claim 25, wherein the surface corresponds to a ware type, wherein the instructions to determine a cleanliness value comprise instructions to correlate the calculated luminosity value with predetermined cleanliness values, wherein the predetermined cleanliness values correspond to known cleanliness values for control wares of the same ware type as the ware type corresponding to the surface depicted in the digital image.