IP Library Granted Patent US 7,414,753
Granted Patent B2
US 7,414,753 · App. 10/840,539 · Granted Aug 19, 2008

Color characterization using nonlinear regression

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,414,753
App. No.
10/840,539
Granted
Aug 19, 2008
Kind
B2
Abstract

A color characterization process utilizing nonlinear regression analysis to characterize a color input device. The color input device is used to generate a bitmap of device dependent values from a color target. The bitmap of device dependent color values is used to generate a forward model that maps device dependent color values to color values in a device independent color space using a nonlinear regression analysis that minimizes a color difference metric between the reference color values and the set of device dependent color values mapped through the forward model. The color difference metric is chosen to represent human perceived color differences in the device independent color space. The performance of the nonlinear regression analysis may be improved by initializing the nonlinear regression analysis using an initial forward model generated from a linear regression analysis.

Claims (57)

1. A method of color characterization for a color input device, comprising:

receiving a set of device dependent color values corresponding to a set of reference color values in a device independent color space; and

generating a forward model that maps device dependent color values to color values in the device independent color space using a regression analysis that minimizes a color difference metric between the reference color values and the color values in the device independent color space, wherein the color values are mapped from the device dependent color values corresponding to the reference color values through the forward model, and wherein the color difference metric defines a non-linear regression analysis.

2. The method of claim 1 , wherein the color difference metric is a measure of human perceived color differences.

3. The method of claim 2 , wherein the measure of human perceived color differences is CIE94.

4. The method of claim 2 , wherein the measure of human perceived color differences is CIEDE2000.

5. The method of claim 1 , further comprising: generating an initial forward model using linear regression analysis; and

initializing the non-linear regression analysis using the initial forward model.

6. The method of claim 5 , wherein the linear regression analysis uses a color distance metric.

7. The method of claim 6 , wherein the device independent color space is CIELUV and the color distance metric is a Euclidean distance between color values.

8. The method of claim 1 , wherein the non-linear regression analysis includes an iterative process, the iterative process comprising:

generating a trial forward model;

generating a color difference measurement using the trial forward model, the set of device dependent color values, and the set of reference color values in the device independent color space; and

terminating the iterative process when the color difference measurement is less than a color difference error threshold.

9. The method of claim 8 , wherein:

the device independent color space is CIELUV; and

the color difference error threshold is one.

10. The method of claim 8 , wherein the iterative process is terminated after a specified number of iterations.

11. A data processing system for characterizing a color input device, comprising:

a processor; a memory coupled to the processor, the memory having program instructions executable by the processor stored therein, the program instructions comprising:

instructions to receive a set of device dependent color values corresponding to a set of reference color values in a device independent color space; and

instructions to generate a forward model that maps device dependent color values to color values in the device independent color space using a regression analysis that minimizes a color difference metric between the reference color values and the color values in the device independent color space, wherein the color values are mapped from the device dependent color values corresponding to the reference color values through the forward model, and wherein the color difference metric defines a non-linear regression analysis.

12. The data processing system of claim 11 , wherein the color difference metric is a measure of human perceived color differences.

13. The data processing system of claim 12 , wherein the measure of human perceived color differences is CIE94.

14. The data processing system of claim 12 , wherein the measure of human perceived color differences is CIEDE2000.

15. The data processing system of claim 11 , the program instructions further comprising:

instructions to generate an initial forward model using linear regression analysis; and

instructions to initialize the non-linear regression analysis using the initial forward model.

16. The data processing system of claim 15 , the program instructions further comprising using color distance metric as an objective function for the linear regression analysis.

17. The data processing system of claim 16 , wherein the device independent color space is CIELUV, the program instructions further comprising instructions to generate the color distance metric by calculating a Euclidean distance between color values in CIELUV.

18. The data processing system of claim 11 , wherein the non-linear regression analysis comprises an iterative process, the program instructions further comprising:

instructions to generate a trial forward model;

instructions to generate a color difference measurement using the trial forward model, the set of device dependent color values, and the set of reference color values in the device independent color space; and

instructions to terminate the iterative process when the color difference measurement is less than a color difference error threshold.

19. The data processing system of claim 18 , wherein:

the device independent color space is CIELUV; and

the color difference error threshold is one.

20. The data processing system of claim 11 , wherein the non-linear regression analysis includes an iterative process, the program instructions further comprising instructions to terminate the iterative process after a specified number of iterations.

21. A data processing system readable media having program instructions stored thereon, the program instructions comprising:

receiving a set of device dependent color values corresponding to a set of reference color values in a device independent color space; and

generating a forward model that maps device dependent color values to color values in the device independent color space using a regression analysis that minimizes a color difference metric between the reference color values and the color values in the device independent color space, wherein the color values are mapped from the device dependent color values corresponding to the reference color values through the forward model, and wherein the color difference metric defines a non-linear regression analysis.

22. The data processing system readable media of claim 21 , wherein the color difference metric is a measure of human perceived color differences.

23. The data processing system readable media of claim 22 , wherein the measure of human perceived color differences is CIE94.

24. The data processing system readable media of claim 22 , wherein the measure of human perceived color differences is CIEDE2000.

25. The data processing system readable media of claim 21 , the program instructions further comprising:

generating an initial forward model using linear regression analysis; and

initializing the non-linear regression analysis using the initial forward model.

26. The data processing system readable media of claim 25 , the program instructions further comprising using color distance metric as an objective function for the linear regression analysis.

27. The data processing system readable media of claim 26 , wherein the device independent color space is CIELUV, the program instructions further comprising generating the color distance metric by calculating a Euclidean distance between color values in CIELUV.

28. The data processing system readable media of claim 21 , wherein the non-linear regression analysis comprises an iterative process, the program instructions further comprising:

generating a trial forward model;

generating a color difference measurement using the trial forward model, the set of device dependent color values, and the set of reference color values in the device independent color space; and

terminating the iterative process when the color difference measurement is less than a color difference error threshold.

29. The data processing system readable media of claim 28 , wherein:

the device independent color space is CIELUV; and

the color difference error threshold is one.

30. The data processing system readable media of claim 21 , wherein the non-linear regression analysis includes an iterative process, the program instructions further comprising terminating the iterative process after a specified number of iterations.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 9, 2014
From: MICROSOFT CORPORATION
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 034541/0477 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 7, 2008
From: CANON KABUSHIKI KAISHA
To: CANON KABUSHIKI KAISHA; MICROSOFT CORPORATION
Reel/Frame 021379/0753 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 6, 2004
From: TIN, SIU-KEI
To: CANON KABUSHIKI KAISHA
Reel/Frame 015315/0231 →