Method and system for measuring color difference

• US 5,751,450 A
• Filed: 05/22/1996
• Issued: 05/12/1998
• Est. Priority Date: 05/22/1996
• Status: Expired due to Term

• Current Assignee: Microscan Systems Inc (Omron Corporation)
• Original Assignee: Medar Incorporated (Nadex (Thailand) Co. Ltd.)
• Inventors: Robinson, David A.
• Primary Examiner(s): Lee, Thomas D.
• Assistant Examiner(s): Grant, II, Jerome
• Application Number:
  US08/651,455
• Time in Patent Office: 720 Days
• Field of Search: 358/504, 358/519, 358/520, 358/522, 358/530, 358/518, 395/131, 395/132, 382/167, 382/168, 345/153, 364/526
• US Class Current: 358/504
• CPC Class Codes: G01J 2003/466 Coded colour; Recognition of predetermined colour; Determining proximity to predetermined colour
• CPC Class Codes: G01J 3/46 Measurement of colour; Colour measuring devices, e.g. colorimeters measuring colour temperature G01J5/60

Abstract

A method and system are provided for automatically and quantitatively measuring color difference between a color distribution of an object and a reference color image using "color distance" in a color system. A template representing the reference color image is stored in a memory of a machine vision system. The machine vision system generates a sample color image of the object and processes the template together with the sample color image to obtain a total color distance. Color distance may be measured either in a Euclidean or "City Block" fashion. Preferably, a look-up table stores the template. The color system may be either intensity dependent or independent. The total color distance can either be presented or displayed to an operator of the machine vision system or else can be used in an automatic feedback loop of a controller of a machine or process.

Claims

1. A method for automatically measuring color difference between color distribution of an object and a reference color image of the object in a machine vision system having a memory, the method comprising the steps of:

storing a template in the memory of the machine vision system, the template representing the reference color image of the object and having a first set of pixels;

generating a sample color image of the object having the color distribution and having a second set of pixels; and

processing the template and the sample color image together on a pixel-by-pixel basis to obtain a total color distance accumulated over matched pixels in the first and second sets of pixels in an area of the object, the total color distance representing a statistically meaningful color measurement between the color distribution and the reference color image of the object in a color system.

2. The method of claim 1 wherein the method further comprises the step of filtering the sample color image based on the total color distance.

3. The method of claim 2 wherein the sample color image includes a plurality of regions and wherein the step of filtering removes at least one region of the sample color image.

4. The method of claim 2 wherein the region of the sample color image is similar to a preselected hue or color.

5. The method of claim 1 further comprising the step of identifying the object based on the total color distance.

6. The method of claim 1 wherein the method further comprises the step of matching the color distribution of the object to the reference color image if the total color distance is within a predetermined, acceptable range.

7. The method as claimed in claim 1 further comprising the step of creating the template wherein the step of creating includes the step of generating the reference color image from a reference object having a reference color distribution.

8. The method as claimed in claim 7 including the step of converting the reference color image into two monochrome images.

9. The method as claimed in claim 7 wherein the step of creating includes the step of generating a plurality of reference color images.

10. The method as claimed in claim 9 wherein the step of creating includes the step of generating a mean template image including a plurality of pixels based on the plurality of reference color images, each of the pixels having a mean value and a distance value over the plurality of reference color images and wherein the template is based on the mean template image.

11. The method as claimed in claim 1 wherein the color system is intensive dependent.

12. The method as claimed in claim 1 wherein the color system is intensity independent.

13. The method as claimed in claim 1 further comprising the steps of providing a machine and adjusting the machine based on the total color distance.

14. The method as claimed in claim 13 wherein the step of adjusting is performed automatically.

15. The method as claimed in claim 1 wherein the template is based on a template image including a plurality of pixels, each of the pixels having a mean value and a distance value to define a color range.

16. The method as claimed in claim 1 wherein the quantitative distance is Euclidean distance.

17. The method as claimed in claim 1 wherein the quantitative distance is City Block distance.

18. The method as claimed in claim 1 wherein each of the first and second sets of pixels includes one or more pixels.

19. The method as claimed in claim 1 wherein the number of pixels in the first and second sets of pixels is substantially the same.

20. The method as claimed in claim 1 wherein the number of pixels in the first and second sets of pixels is different.

21. A color measuring system for automatically measuring color difference between a color distribution of an object and a reference color image of the object in a machine vision system, the system comprising:

a memory for storing a template, the template representing the reference color image of the object and having a first set of pixels;

means for generating a sample color image of the object having the color distribution and having a second set of pixels; and

a processor for processing the template and the sample color image together on a pixel-by-pixel basis to obtain a total color distance accumulated over matched pixels in the first and second sets of pixels in an area of the object, the total color distance representing a statistically meaningful color measurement between the color distribution and the reference color image of the object in a color system.

22. The system as claimed in claim 21 further comprising a filter for filtering the sample color image based on the total color distance.

23. The system as claimed in claim 22 wherein the sample color image includes a plurality of regions and wherein the filter removes at least one region of the sample color image.

24. The system as claimed in claim 23 wherein the region of the sample color image is similar to a preselected hue or color.

25. The system as claimed in claim 21 wherein the system further comprises means for identifying the object based on the total color distance.

26. The system as claimed in claim 21 wherein the system further comprises means for matching the color distribution to the reference color image if the total color distance is within a predetermined, acceptable range.

27. The system as claimed in claim 21 further comprising means for creating the template wherein the means for creating the template includes means for generating the reference color image from a reference object having a reference color distribution.

28. The system as claimed in claim 27 including means for converting the reference color image into two monochrome images.

29. The system as claimed in claim 27 wherein the means for creating includes means for generating a plurality of reference color images.

30. The system as claimed in claim 29 wherein the means for creating includes means for generating a mean template image including a plurality of pixels based on the plurality of reference color images, each of the pixels having a mean value and a distance value over the plurality of reference color images and wherein the template is based on the mean template image.

31. The system as claimed in claim 21 wherein the color system is intensity dependent.

32. The system as claimed in claim 21 wherein the color system is intensity independent.

33. The system as claimed in claim 21 further comprising a machine and means for adjusting the machine based on the total color distance.

34. The system as claimed in claim 33 wherein the means for adjusting is a controller.

35. The system as claimed in claim 21 wherein the template is based on a template image having a plurality of pixels, each of the pixels having a mean value and a distance value to define a color range.

36. The system as claimed in claim 21 wherein the quantitative distance is Euclidean distance.

37. The system as claimed in claim 21 wherein the quantitative distance is City Block distance.

38. The method as claimed in claim 21 wherein each of the first and second sets of pixels includes one or more pixels.

39. The system as claimed in claim 21 wherein the number of pixels in the first and second sets of pixels is substantially the same.

40. The system as claimed in claim 21 wherein the number of pixels in the first and second sets of pixels is different.