INTELLIGENT ALIGNMENT SYSTEM AND METHOD FOR COLOR SENSING DEVICES

• US 20170131147A1
• Filed: 05/01/2015
• Published: 05/11/2017
• Est. Priority Date: 05/01/2015
• Status: Active Grant

• Current Assignee: Variable Inc.
• Original Assignee: Variable Inc.
• Inventors: Yu, George Yang, Temple, Andrew Richard, McGehee, Jeff
• Granted Patent: US 10,156,477 B2
• Time in Patent Office: Days
• CPC Class Codes: G01J 2003/467 Colour computing
• CPC Class Codes: G01J 3/0264 Electrical interface; User interface
• CPC Class Codes: G01J 3/0272 Handheld
• CPC Class Codes: G01J 3/462 Computing operations in or between colour spaces; Colour management systems
• CPC Class Codes: G01J 3/465 taking into account the colour perception of the eye; using tristimulus detection
• CPC Class Codes: G01J 3/50 using electric radiation detectors
• CPC Class Codes: G01J 3/524 Calibration of colorimeters
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

A computer-implemented intelligent alignment method for a color sensing device (12) which initially obtains a raw sense value measured by the color sensing device and converts the raw sense value to a tristimulus value (S401). The color sensing device may be calibrated using a known set of colors (S402). Raw readings received from the color sensing device may be mapped to known tristimulus values (S403), and mapped values may be converted to a standard reference illuminant color space (S404). A client-server system may be provided in which a color sensing device and one or more servers collectively execute operations according to the present disclosure.

Claims

1. A computer-implemented intelligent alignment method for a color sensing device, the method comprising

obtaining a raw sense value measured by the color sensing device;

converting the raw sense value to a tristimulus value;

calibrating the color sensing device using a known set of colors;

mapping raw readings received from the color sensing device to known tristimulus values; and

converting mapped values to a standard reference illuminant color space.

2. The method according to claim 1, further comprising:

grouping at least one color sensing device according to a maximum permissible Δ

E value for each color across batching color set, wherein the maximum permissible Δ

E value relates to a maximum color space distance associated with a perceived color difference when viewed by a human eye;

learning relationships between inputs and outputs to produce a model for future inputs;

receiving an unadjusted color reading as input; and

generating an adjusted color reading according to the model.

3. The method according to claim 1, further comprising:

storing raw scan data and reference scan data;

executing a K Nearest Neighbor (KNN) algorithm to search for K nearest scan to an unadjusted color reading; and

returning a weighted average of K reference scans associated with the unadjusted color reading.

4. The method according to claim 1, further comprising:

training an Artificial Neural Network (ANN);

receiving an unadjusted color reading; and

returning a color based upon an ANN continuous representation associated with the training data.

5. The method according to claim 3, further comprising:

developing a material ANN associated with different material type and surface data;

operating upon the returned color using the material ANN; and

providing an adjusted color based upon a material or surface type associated with the material ANN.

7. The method according to claim 1, wherein the step of calibrating the color sensing device using a known set of colors further comprises:

transmitting a sensor identification (ID) associated with the color sensing device to a client device;

requesting calibration data associated with the color sensing device to a cloud service;

returning response data or matching data in response to the calibration data request from the cloud service; and

performing adjustment operations corresponding to the response data and/or matching data.

8. The method according to claim 1, wherein the step of calibrating the color sensing device using a known set of colors further comprises:

transmitting a raw sensor reading and a sensor identification (ID) to a client device;

transmitting the raw sensor reading and sensor ID along with an adjustment type to a cloud service;

performing adjustment operations by the cloud service corresponding to the raw sensor reading, sensor ID, and adjustment type; and

returning at least one of aligned color data and match data to the client device.

9. The method according to claim 1, further comprises:

comparing the mapped raw readings to data associated with a reference device.

10. The method according to claim 9, wherein the reference device comprises a spectrometer or spectrophotometer.

11. The method according to claim 9, wherein the reference device comprises at least one other color sensing device having a Δ

E value associated with the color sensing device.

12. The method according to claim 9, further comprising:

learning relationships between the mapped raw readings and data associated with the reference device to produce a correlation model; and

adjusting a color reading according to the correlation model.

6. (canceled)

13. (canceled)

14. (canceled)

15. A client-server system comprising:

a color sensing device; and

one or more servers configured to execute operations comprising

obtaining a raw sense value measured by the color sensing device;

converting the raw sense value to a tristimulus value;

calibrating the color sensing device using a known set of colors;

mapping raw readings received from the color sensing device to known tristimulus values; and

converting mapped values to a standard reference illuminant color space.

16. The system of claim 15, wherein the operations further comprise:

grouping at least one color sensing device according to a maximum permissible Δ

E value for each color across batching color set, wherein the maximum permissible Δ

E value relates to a maximum color space distance associated with a perceived color difference when viewed by a human eye;

learning relationships between inputs and outputs to produce a model for future inputs;

receiving an unadjusted color reading as input; and

generating an adjusted color reading according to the model.

17. The system according to claim 15, wherein the operations further comprise:

storing raw scan data and reference scan data;

executing a K Nearest Neighbor (KNN) algorithm to search for K nearest scan to an unadjusted color reading; and

returning a weighted average of K reference scans associated with the unadjusted color reading.

18. The system according to claim 15, wherein the operations further comprise:

training an Artificial Neural Network (ANN);

receiving an unadjusted color reading; and

returning a color based upon an ANN continuous representation associated with the training data.

19. The system according to claim 17, wherein the operations further comprise:

developing a material ANN associated with different material type and surface data;

operating upon the returned color using the material ANN; and

providing an adjusted color based upon a material or surface type associated with the material ANN.

20. The system according to claim 15, wherein calibrating the color sensing device using a known set of colors further comprises:

transmitting a sensor identification (ID) associated with the color sensing device to a client device;

requesting calibration data associated with the color sensing device to a cloud service;

returning response data or matching data in response to the calibration data request from the cloud service; and

performing adjustment operations corresponding to the response data or matching data.

21. The system according to claim 15, wherein calibrating the color sensing device using a known set of colors further comprises:

transmitting a raw sensor reading and a sensor identification (ID) to a client device;

transmitting the raw sensor reading and sensor ID along with an adjustment type to a cloud service;

performing adjustment operations by the cloud service corresponding to the raw sensor data, sensor ID, and adjustment type; and

returning at least one of aligned color data and match data to the client device.

22. The system according to claim 15, wherein the operations further comprise:

comparing the mapped raw readings to data associated with a reference device.

23. The system according to claim 22, wherein the reference device comprises at least one other color sensing device having a Δ

E value associated with the color sensing device.