Method and device for identification of effect pigments in a target coating

Patent metadata

Field	Value
Publication number	US-12174073-B2
Application number	US-202017755885-A
Country	US
Kind code	B2
Filing date	Nov 12, 2020
Priority date	Nov 14, 2019
Publication date	Dec 24, 2024
Grant date	Dec 24, 2024

Abstract

Disclosed herein is a computer-implemented method, a respective device, and a non-transitory computer-readable medium. The method includes:
obtaining color values, texture values and digital images of a target coating, retrieving from a database one or more preliminary matching formulas based on the color and/or texture values obtained for the target coating, determining sparkle points within the respective obtained images and within the respective images associated with the one or more preliminary matching formulas, creating subimages of each sparkle point from the respective images, providing the created subimages to a convolutional neural network, the convolutional neural network being trained to correlate a respective subimage of a respective sparkle point with a pigment and/or pigment class, and determining, based on an output of the neural network, at least one of the one or more preliminary matching formulas as the formula(s) best matching the target coating.

First claim

The invention claimed is:

1. A computer-implemented method comprising at least the following steps:
obtaining, using at least one measuring device, color values, texture values and digital images of a target coating,
retrieving from a database which comprises formulas for coating compositions and interrelated color values, interrelated texture values, and interrelated digital images, one or more preliminary matching formulas based on the color values and/or the texture values obtained for the target coating,
performing, using a computer processor in operative conjunction with at least one filtering technique, for each of the obtained images of the target coating and the images interrelated with the one or more preliminary matching formulas, an image analysis to determine at least one sparkle point within the respective images,
creating subimages of each sparkle point from the respective obtained images and from the respective images interrelated with the one or more preliminary matching formulas,
providing the created subimages to a convolutional neural network, the convolutional neural network being trained to correlate a respective subimage of a respective sparkle point with a pigment and/or pigment class and to identify the pigment and/or pigment class based on the respective subimage of the respective sparkle point,
determining and outputting, for the target coating and for each preliminary matching formula, a statistic of the identified pigments and/or pigment classes, respectively, wherein the statistic determined for the target coating and the statistics determined for the one or more preliminary matching formulas can each be presented as a respective histogram and/or as a respective vector,
comparing, using a computer processor, the statistic determined for the target coating with the statistics determined for the one or more preliminary matching formulas, and
determining at least one of the one or more preliminary matching formulas as the formula(s) best matching with the target coating.

2. The method according to claim 1 , further comprising deriving from each subimage a correlation for at least one pigment, wherein the correlation indicates a contribution of the at least one pigment to a distribution of the sparkle points within the respective image from which the subimage had been cut out.

3. The method according to claim 1 , wherein the image analysis for each image comprises creating a mask, identifying contours and overlaying a frame on the respective image, thus creating the subimages of each sparkle point from the respective image.

4. The method according to claim 1 , wherein a correlation of each subimage for each measurement geometry with at least one pigment is derived by means of the convolutional neuronal network which is configured to classify each subimage of a respective sparkle point for each measurement geometry with a pre-given probability to a specific pigment and/or pigment class.

5. The method according to claim 4 , wherein each derived correlation for each measurement geometry, at which the respective subimage is taken, is used to adapt a contribution of the at least one pigment and/or pigment class when determining the best matching formula.

6. The method according to claim 1 , wherein determining the best matching formula comprises providing a list of pigments with respective quantities and/or concentrations.

7. The method according to claim 1 , wherein each subimage is created with an image area based on a maximum size of the at least one sparkle point in a black background.

8. A device comprising:
a database, which comprises formulas for coating compositions and interrelated color values, interrelated texture values, and interrelated digital images,
at least one processor, which is in communicative connection with at least one measuring device, the database, at least one filtering technique, and a convolutional neural network, and programmed to execute at least the following steps:
receiving, from the measuring device, color values, texture values and digital images of a target coating,
retrieving from the database one or more preliminary matching formulas based on the color values and/or the texture values obtained for the target coating,
performing, by using the filtering technique, for each of the obtained images of the target coating and the images interrelated with the one or more preliminary matching formulas, an image analysis to determine at least one sparkle point within the respective images,
creating subimages of each sparkle point from the received images and from the images interrelated with the one or more preliminary matching formulas,
providing the created subimages to the convolutional neural network, the convolutional neural network being trained to correlate a respective subimage of a respective sparkle point with a pigment and/or a pigment class, and to identify the pigment and/or the pigment class based on the respective subimage of the respective sparkle point,
determining and outputting, for the target coating and for each preliminary matching formula, a statistic of the identified pigments and/or pigment classes, respectively, wherein the statistic determined for the target coating and the statistics determined for the one or more preliminary matching formulas can each be presented as a respective histogram and/or as a respective vector,
comparing the statistic determined for the target coating with the statistics determined for the one or more preliminary matching formulas, and
determining at least one of the one or more preliminary matching formulas as the formula(s) best matching with the target coating.

9. The device according to claim 8 , further comprising the at least one measuring device, the filtering technique and/or the convolutional neural network.

10. The device according to claim 8 , wherein the processor is further configured to execute the step of deriving from each subimage a correlation for at least one pigment, wherein the correlation indicates a contribution of the at least one pigment to a distribution of the sparkle points within the respective image from which the subimage had been cut out.

11. The device according to claim 8 , wherein the processor is further configured to derive a correlation of each subimage for each measurement geometry with at least one pigment by means of the convolutional neuronal network which is configured to classify each subimage of a respective sparkle point for each measurement geometry with a pre-given probability to a specific pigment and/or pigment class.

12. The device according to claim 11 , wherein the processor is further configured to use each derived correlation for each measurement geometry, at which the respective subimage is taken, to adapt a contribution of the at least one pigment and/or pigment class when determining the best matching formula.

13. The device according to claim 8 , which further comprises an output unit configured to output the determined best matching formula.

14. A device configured to execute the method according to claim 1 .

15. A non-transitory computer readable medium with a computer program with program codes that are configured, when the computer program is loaded and executed by at least one processor, which is in a communicative connection with at least one measuring device, a database, a filtering technique and a convolutional neural network, to execute at least the following steps:
receiving, from the measuring device, color values, texture values and digital images of a target coating,
retrieving from the database which comprises formulas for coating co

Assignees

• Basf Coatings Gmbh

Inventors

• Bischoff Guido
• Baughman Donald R
• Leopold Matthew
• Scott Stuart K

Classifications

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10024

  Color image · CPC title

• G01N2021/4711

  Multiangle measurement · CPC title

• G01N21/4738

  Diffuse reflection (precedence is given to G01N21/55 - G01N21/57 if specular component is taken into consideration), e.g. also for testing fluids, fibrous materials · CPC title