Method for determining acceptability of proposed color solution using an artificial intelligence model

• US 20050240543A1
• Filed: 04/28/2005
• Published: 10/27/2005
• 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., Soss, James
• Granted Patent: US 7,536,231 B2
• Time in Patent Office: Days
• US Class Current: 706/16
• 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
• 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: G06N 3/02 Neural networks

Abstract

A method for determining if a proposed color solution, such as paint, pigments, or dye formulations, is acceptable, is provided. The inputs to the system are the actual color values of an item, differential color values, a proposed color solution, and second color values associated with the proposed color solution. The system includes an artificial intelligence model to analyze the inputs and produce an output for communicating whether the proposed color solution is acceptable. The artificial intelligence model may be embodied in a neural network.

Claims

1. A method of determining an acceptability of a proposed color solution for an item using a computer and an artificial intelligence model, said method comprising the steps of:

determining actual color values associated with the item;

inputting the actual color values into the computer;

determining the proposed color solution and associated second color values;

calculating the differences between the actual color values and the second color values by utilizing the computer to define differential color values;

inputting the actual color values and the differential color values into the artificial intelligence model;

determining if the proposed color solution is acceptable by utilizing the artificial intelligence model; and

producing an output indicative of the acceptability of the proposed color solution.

2. A method as set forth in claim 1 wherein the step of determining the proposed color solution and associated second color values is further defined as searching a database for the proposed color solution based on the inputted actual color values.

3. A method as set forth in claim 1 further including the step of transforming the output into a desired format.

4. A method as set forth in claim 3 wherein the step of transforming the output is further defined as transforming the output into a numerical variable indicative of the acceptability of the output.

5. A method as set forth in claim 4 wherein the step of transforming the output is further defined as transforming the output into a fuzzy variable set.

6. A method as set forth in claim 3 wherein the step of transforming the output is further defined as transforming the output into a descriptive output indicative of the acceptability of the output and displaying the descriptive output.

7. A method as set forth in claim 1 further including the step of training the artificial intelligence model for determining acceptability.

8. A method as set forth in claim 7 wherein the step of training the artificial intelligence model includes the step of comparing the output to a known acceptability of the proposed color solution.

9. A method as set forth in claim 7 wherein the artificial intelligence model is a neural network and further including the step of providing feedback to the neural network from the output.

10. A method as set forth in claim 9 wherein the neural network includes an input layer and an output layer and further including the step of providing feedback from the output to the input layer.

11. A computer-based method for providing an acceptability of a proposed color solution to a customer over a computer network, said method comprising the steps of:

receiving actual color values from the customer located at a remote location;

delivering the actual color values from the remote location to a central location over the computer network;

inputting the actual color values into a computer;

searching a composite solution database associated with the computer and determining a proposed color solution and associated second color values based on the inputted actual color values;

calculating the differences between the actual color values and the second color values utilizing the computer to define differential color values;

inputting the actual color values and the differential color values into an artificial intelligence model;

determining if the proposed color solution is acceptable by utilizing the artificial intelligence model; and

producing an output indicative of the acceptability of the proposed color solution.

12. A method as set forth in claim 11 further including the step of delivering the output from the central location to the remote location over the computer network.

13. A method as set forth in claim 11 further including the step of transforming the output into a desired format.

14. A method as set forth in claim 13 wherein the step of transforming the output is further defined as transforming the output into a numerical variable indicative of the acceptability of the output.

15. A method as set forth in claim 14 wherein the step of transforming the output is further defined as transforming the output into a fuzzy variable set.

16. A method as set forth in claim 13 wherein the step of transforming the output is further defined as transforming the output into a descriptive output indicative of the acceptability of the output and displaying the descriptive output.

17. A method of training a neural network having an input layer, a hidden layer, and an output layer, the neural network being adapted to determine the acceptability of a proposed color solution, comprising the steps of:

inputting actual color values and differential color values to the input layer;

inputting a proposed color solution associated with the inputted actual color values and the inputted differential color values into the input layer;

using a weighted factor to the color values in the hidden layer to produce an output indicative of the acceptability of the proposed color solution;

providing the output to a comparator;

inputting a known acceptability of the proposed color solution to the comparator;

comparing the output and the known acceptability for producing an error value;

comparing the error value 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.

18. A method as set forth in claim 17 further including the step of calculating the differences between the actual color values and second color values to define the differential color values.