System and method for organizing color values using an artificial intelligence based cluster model

• US 20020184171A1
• Filed: 06/05/2001
• Published: 12/05/2002
• Est. Priority Date: 06/05/2001
• Status: Active Grant

• Current Assignee: BASF Corporation (BASF SE)
• Original Assignee: BASF Corporation (BASF SE)
• Inventors: McClanahan, Craig J.
• Granted Patent: US 6,892,194 B2
• Time in Patent Office: Days
• US Class Current: 706/20
• CPC Class Codes: G01J 3/462 Computing operations in or between colour spaces; Colour management systems
• CPC Class Codes: G01J 3/463 Colour matching
• CPC Class Codes: G01J 3/52 using colour charts
• CPC Class Codes: G06N 3/02 Neural networks
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

A system and method for organizing a plurality of sets color values into a plurality of color groups, such as paint, pigments, or dye formulations, is provided. The inputs to the system are the color values of a proposed paint, dye or colorant formulation and color measurement angles. The system includes an input device for entering a plurality of sets of color values and an artificial intelligence cluster model coupled to the input device. The cluster model produces an output signal indicative of the one color group to which a set of color values belongs. The artificial intelligence model may be embodied in a neural network. More specifically, the cluster model may be a self-organizing map neural network.

Claims

1. A computer-based system for organizing a plurality of sets of color values, comprising:

an input device being adapted to receive the plurality of sets of color values; and

,

an artificial intelligence cluster model coupled to the input device and being adapted to organize the plurality of sets into a plurality of color groups as a function of the plurality of sets of color values.

2. A computer-based system, as set forth in claim 1, wherein the artificial intelligence cluster model uses an iterative process to organize the plurality of sets into the plurality of color groups.

3. A computer-based system, as set forth in claim 1, wherein the input device is adapted to receive a number of color groups input signal for determining the plurality of color groups.

4. A computer-based system, as set forth in claim 3, wherein the number of color groups input signal is calculated.

5. A computer-based system, as set forth in claim 1, wherein one of the plurality of color groups having less than a minimum of sets of color values is removed.

6. A computer-based system, as set forth in claim 1, wherein the artificial intelligence cluster model is a neural network.

7. A computer-based system, as set forth in claim 6, wherein the neural network is a self-organizing map neural network.

8. A computer-based system for matching an input set of color values with one of a plurality of color groups, comprising:

an input device being adapted to receive the input set of color values; and

,

an artificial intelligence cluster model coupled to the input device and being adapted to select the one of the plurality of color groups as a function of the input set of color values.

9. A computer-based system, as set forth in claim 8, wherein the artificial intelligence model is adapted to organize the plurality of color groups based on a plurality of test sets of color values.

10. A computer-based system, as set forth in claim 8, wherein the artificial intelligence cluster model is a neural network.

11. A computer-based system, as set forth in claim 10, wherein the neural network is a self-organizing map neural network.

12. A computer-based system, as set forth in claim 10, wherein the neural network includes an input layer having a plurality of input nodes for receiving the plurality of sets and an output layer coupled to the input layer and having a plurality of output nodes, wherein one of the plurality of input nodes corresponds to one of the plurality of the output nodes.

13. A computer-based system, as set forth in claim 12, including a plurality of connections for connecting one of the plurality of output nodes to one of the plurality of input nodes.

14. A computer-based system, as set forth in claim 13, including a weighted factor associated with each of the plurality of connections for selecting one of the plurality of color groups as a function of one of the plurality of sets.

15. A computer-based system, as set forth in claim 14, including an output signal output by the output layer.

16. An artificial intelligence model, as set forth in claim 15, wherein the output signal is indicative of the one of the plurality color groups.

17. An artificial intelligence model, as set forth in claim 15, wherein each color group is associated with a formulation.

18. An artificial intelligence model, as set forth in claim 17, wherein the output signal is the formulation.

19. A computer-based system, as set forth in claim 15, wherein the weighted factor is adjusted as a function of the output signal.

20. An artificial intelligence cluster model for organizing a plurality of sets of color values, comprising:

an input layer having a plurality of input nodes and being adapted for receiving the plurality of sets of color values; and

an output layer coupled to the input layer and having a plurality of output nodes wherein one of the plurality of output nodes corresponds with one of the plurality of input nodes;

wherein the artificial intelligence cluster model is adapted to organize the plurality of sets of color values into a plurality of color groups as a function of the plurality of sets of color values.

21. An artificial intelligence cluster model, as set forth in claim 20, wherein the model is a neural network.

22. An artificial intelligence model, as set forth in claim 21, wherein the neural network is a self-organizing map neural network.

24. An artificial intelligence model, as set forth in claim 23, wherein the artificial intelligence model is adapted to organize the plurality of color groups based on a plurality of test sets of color values.

25. An artificial intelligence model, as set forth in claim 23, wherein each of the plurality of color groups is associated with a formulation.

26. An artificial intelligence model, as set forth in claim 23, including a plurality of connections for connecting one of the plurality of output nodes to one of the plurality of input nodes.

27. An artificial intelligence model, as set forth in claim 26, including a weighted factor associated with each of the plurality of connections for selecting the one of the plurality of color groups as a function of one of the input set of color values.

28. An artificial intelligence model, as set forth in claim 27, including an output signal output by the output layer.

29. An artificial intelligence model, as set forth in claim 28, wherein the output signal is indicative of the one color group.

30. An artificial intelligence model, as set forth in claim 29, wherein each color group is associated with a formulation.

31. An artificial intelligence model, as set forth in claim 30, wherein the output signal is the formulation.

32. An artificial intelligence model, as set forth in claim 28, wherein the weighted factor is adjusted as a function of the output signal.

33. An artificial intelligence model, as set forth in claim 23, wherein the model is a neural network.

34. An artificial intelligence model, as set forth in claim 33, wherein the neural network is a self-organizing map neural network.

36. A computer system, as set forth in claim 35, wherein the proposed color solution is chosen from a plurality of color solutions and the artificial intelligence cluster model is adapted to determine if a new color solution is required.

37. A computer system, as set forth in claim 35, wherein the artificial intelligence cluster model is adapted to determine if a new color solution should be published on another media.

38. A computer system, as set forth in claim 35, wherein the artificial intelligence cluster model is adapted to determine is additional color samples are required.

39. A computer system, as set forth in claim 35, wherein the artificial intelligence cluster model includes a plurality of color groups and a formulation associated with each color group, wherein the artificial intelligence model is adapted to select one of the plurality of color groups as a function of the solution request, and wherein the search routine is adapted for providing the proposed color solution as a function of a formulation associated with the one color group.

40. A computer system, as set forth in claim 35, wherein the artificial intelligence model is a neural network.

41. A computer system, as set forth in claim 40, wherein the artificial intelligence model is a self-organizing map neural network.

23. An artificial intelligence cluster model for matching an input set of color values with one of a plurality of color groups, comprising:

an input layer having a plurality of input nodes and being adapted for receiving the input set of color values; and

an output layer coupled to the input layer and having a plurality of output nodes wherein one of the plurality of output nodes corresponds with one of the plurality of input nodes;

wherein the artificial intelligence cluster model is adapted to select the one of a plurality of color groups as a function of the input set of color values.

35. A computer system for providing a color solution to a customer, comprising:

a first module located at a remote location and being adapted to receive a solution request including color values from an operator; and

a second module coupled to the first module and being located at a central location, the second module including a composite solution database and a search routine coupled to the composite solution database and being adapted to receive the solution request from the first module and to provide a proposed color solution as a function of the solution request; and

,

an artificial intelligence cluster model coupled to the search routine for analyzing the proposed color solution.

42. A method for organizing a plurality of sets of color values using an artificial intelligence cluster model, wherein the model includes an input layer having a plurality of input nodes and being adapted for receiving a plurality of sets of color values, an output layer coupled to the input layer and having a plurality of output nodes wherein one of the plurality of output nodes corresponds with one of the plurality of input nodes, wherein the artificial intelligence cluster model is adapted to organize the plurality of sets into a plurality of color groups, including the steps of:

providing the plurality of sets to the model; and

organizing the plurality of sets into a plurality of color groups.

43. A method, as set forth in claim 42, including the step of matching an input set of color values with one of the plurality of color groups.

44. A method, as set forth in claim 42, wherein the model further comprises a plurality of connections for connecting one of the plurality of output nodes to one of the plurality of input nodes, the method including the step of applying a weighted factor to each of the plurality of connections for organizing the plurality of color groups based on a plurality of test sets of color values.

45. A method, as set forth in claim 44, including the step of matching an input set of color values with one of the plurality of color groups.

46. A method, as set forth in claim 45, including the step of producing an output signal.

47. A method, as set forth in claim 46, including the step of adjusting the weighted factor as a function of the output signal.

48. A method, as set forth in claim 42, including the step of training the artificial intelligence model for selecting one of the plurality of color groups as a function of an input set of color values.

49. A method, as set forth in claim 42, wherein the artificial intelligence model is a neural network.

50. A method, as set forth in claim 49, wherein the neural network is

a self-organizing map neural network.

51. A method for organizing a plurality of sets of color values using a computer based model, the model being embodied in a neural network having an input layer and an output layer including a plurality of color groups, including the steps of:

providing the plurality of sets to the neural network; and

organizing the plurality of sets into the plurality of color groups.

52. A method, as set forth in claim 51, including the step of matching an input set of color values with one of the plurality of color groups.

53. A method, as set forth in claim 52, including the step of applying a weighted factor to select one of the plurality of color groups.

54. A method, as set forth in claim 53, including the step of producing an output signal.

55. A method, as set forth in claim 54, including the step of adjusting the weighted factor as a function of the output signal.

57. A computer-based method, as set forth in claim 56, including the steps of:

choosing the proposed color solution from a plurality of color solutions; and

,

using the artificial intelligence cluster model to determine if a new color solution is required.

58. A computer-based method, as set forth in claim 56, including the step of using the artificial intelligence cluster model to determine if a new color solution should be published on another media.

59. A computer-based method, as set forth in claim 56, including the step of using the artificial intelligence cluster model to determine is additional color samples are required.

60. A computer-based method, as set forth in claim 56, wherein the artificial intelligence cluster model includes a plurality of color groups and a formulation associated with each color group and the method includes the steps of:

using the artificial intelligence cluster model to select one of the plurality of color groups as a function of the solution request; and

,

providing the proposed color solution as a function of a formulation associated with the one color group.

61. A computer-based method, as set forth in claim 56, including the step of producing an output signal indicative of the proposed color solution.

56. A computer-based method for providing a color solution to a customer over a computer network, including the steps of:

receiving a solution request, including an input set of color values, from an operator located at a remote location;

delivering the solution request from the remote location to a central location over the computer network;

searching a composite solution database and determining a proposed color solution as a function of the solution request; and

,

analyzing the proposed color solution using an artificial intelligence cluster model.

62. A method for training a neural network having an input layer, an output layer including a plurality of color groups and a connection associated with the input layer and the output layer, the neural network being adapted to organize a plurality of test sets of color values into a plurality of color groups and select one of the plurality of color groups based on one of the plurality of test sets of color values, comprising the steps of:

providing the plurality of test sets to the input layer;

applying a weighted factor to the connection to select one of the plurality of color groups based on one of the plurality of test sets;

producing an output signal; and

adjusting the weighted factor based on the output signal.