System and method for converting a color formula using an artificial intelligence based conversion model

• US 20020184167A1
• 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 6,993,512 B2
• Time in Patent Office: Days
• US Class Current: 706/16
• CPC Class Codes: G06T 11/001 Texturing; Colouring; Generation of texture or colour inpainting G06T5/77

Abstract

A system and method for converting a color formula from compositions such as paints, pigments, or dye formulations, is provided. The input to the system is a first color formula. The system includes an input device for entering a plurality of color formula values and an artificial intelligence conversion model coupled to the input device. The conversion model produces an output signal for communicating a second color formula. The artificial intelligence model may be embodied in a neural network. More specifically, the conversion model may be a back propagation neural network.

Claims

1. A computer-based system for converting a color formula, comprising:

an input device for receiving a first color formula, wherein the first color formula is comprised of a plurality of ingredients and amounts; and

an artificial intelligence conversion model coupled to the input device for converting the first color formula into a second color formula.

2. A computer-based system, as set forth in claim 1, wherein the artificial intelligence conversion model produces an output signal.

3. A computer-based system, as set forth in claim 2, wherein the output signal is the second color formula.

4. A computer-based system, as set forth in claim 2, wherein the artificial intelligence conversion model is a neural network.

5. A computer based system, as set forth in claim 4, wherein the neural network is a back propagation neural network.

6. A computer-based system, as set forth in claim 4, wherein the neural network includes an input layer having a plurality of input nodes for receiving plurality of formulation ingredient amounts and an output layer having a plurality of output nodes and one of the plurality of input nodes corresponds with one of the plurality of output nodes.

7. A computer-based system, as set forth in claim 6, wherein the neural network includes a hidden layer having a plurality of weighted factors wherein one of the plurality of weighted factors corresponds to one of the plurality of input nodes and a corresponding output node.

8. A computer-based system, as set forth in claim 7, wherein each of the plurality of weighted factors is determined as a function of the first color formula.

9. A computer-based system, as set forth in claim 7, wherein the plurality of weighted factors determine the contribution of a plurality of color formulation values of the first color formula to the output signal.

10. A computer-based system, as set forth in claim 7, wherein the plurality of weighted factors are adjusted as a function of the output signal.

11. A computer-based system, as set forth in claim 7, wherein the output signal is a predicted color formula.

12. A computer-based system, as set forth in claim 11, including a comparator for comparing the predicted color formula from the output layer to an actual color formula and providing feedback to the neural network.

13. A computer-based system, as set forth in claim 12, wherein the plurality of weighted factors are adjusted as a function of the feedback received by the neural network from the comparator.

15. A computer-based system, as set forth in claim 14, wherein the output signal is a second color formula.

16. A computer-based system, as set forth in claim 14, wherein the artificial intelligence conversion model is a neural network.

17. An artificial intelligence model, as set forth in claim 16, wherein the neural network is a feed-forward back propagation neural network.

18. An artificial intelligence model, as set forth in claim 14, including a hidden layer having a plurality of weighted factors wherein one of the plurality of weighted factors corresponds to one of the plurality of input nodes and the corresponding one of the plurality of output nodes.

19. A computer-based system, as set forth in claim 18, wherein each of the plurality of weighted factors is determined as a function of the first color formula.

20. An artificial intelligence model, as set forth in claim 18, wherein the plurality of weighted factors determine the contribution of the plurality of color formulation values of the first color formula to the output signal.

21. An artificial intelligence model, as set forth in claim 18, wherein the plurality of weighted factors are adjusted as a function of the output signal.

22. An artificial intelligence model, as set forth in claim 18, wherein the output signal is a predicted color formula.

23. An artificial intelligence model, as set forth in claim 22, including a comparator for comparing the predicted color formula from the output layer to an actual color formula and providing feedback to the neural network.

24. An artificial intelligence model, as set forth in claim 23, wherein the plurality of weighted factors are adjusted as a function of the feedback received by the neural network from the comparator.

25. An artificial intelligence system, as set forth in claim 24, wherein the plurality of weighted factors are adjusted as a function of the feedback received by the neural network.

27. A method, as set forth in claim 26, including the step of determining the contribution of the plurality of color formulation values to the output signal.

28. A method, as set forth in claim 27, including the step of applying a weighted factor to determine the contribution of the plurality of color formulation values to the output signal.

29. A method, as set forth in claim 28, including the step of comparing the output signal to an actual color formula.

30. A method, as set forth in claim 29, including the step of training the artificial intelligence model for converting the first color formula.

31. A method, as set forth in claim 30, wherein the artificial intelligence model is a neural network and the method includes the step of providing feedback to the neural network from the output signal for adjusting the weighted factor.

14. An artificial intelligence based conversion model for converting a color formula, comprising:

an input layer having a plurality of input nodes for receiving a plurality of color formulation values, wherein the plurality of color formulation values correspond with a first color formula; and

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

wherein the output layer produces an output signal.

26. A method for converting a color formula using an artificial intelligence conversion model, including the steps of:

providing a plurality of color formulation values to the model, wherein the plurality of color formulation values correspond to a first color formula; and

producing an output signal.

32. A method for converting a color formula using a computer based model, the model being embodied in a neural network having an input layer and an output layer, including the steps of:

providing a plurality of color formulation values to the neural network, wherein the plurality of color values correspond to a first color formula; and

producing an output signal.

33. A method, as set forth in claim 32 including the step of applying a weighted factor to determine the contribution of the plurality color formulation values to the output signal.

34. A method, as set forth in claim 33, including the step of adjusting the weighted factor according to the output signal.

35. A method, as set forth in claim 34, including the step of providing feedback from the output signal to the neural network for the purpose of training.

36. A method, as set forth in claim 35, including the step of adjusting the weighted factor according to the feedback received by the neural network.

37. A method for training a neural network having an input layer, a hidden layer, and an output layer, the neural network being adapted to convert a color formula, comprising the steps of:

providing a plurality of sets of color formulation values to the input layer, wherein each of the plurality of color values corresponds with a first color formula;

applying a weighted factor to the plurality of sets of color values in the hidden layer to produce an output signal;

providing the output signal to a comparator;

providing an actual formula to the comparator for comparing the actual formula to the output signal for producing an error count;

comparing the error count to an error limit to determine error variation; and

providing error feedback to the neural network corresponding to the error variation, wherein the weighted factor is adjusted according to the error feedback.