Effect Pigment Identification in Target Coatings via Sparkle Points

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for identifying and matching effect pigments in coatings are inefficient, time-consuming, and often require substantial user intervention, leading to inconsistent results, especially when dealing with complex mixtures or new coatings.

Innovation Solution

A computer-implemented method using a convolutional neural network to analyze digital images of target coatings, identify sparkle points, and correlate them with specific pigments through a trained neural network, combined with a database of coating formulas, to determine the best matching formula.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional camera/spectrometer methods with case-by-case analysis are used, then measurement precision can be maintained, but productivity is very low and time consuming

Engineering Contradiction:
Improveidentification accuracyVSAvoidanalysis speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the coating analysis into distinct processing stages: raw image acquisition, sparkle point detection through filtering, subimage extraction, neural network classification, and statistic generation. This segmentation enables parallel processing of multiple images simultaneously, dramatically improving productivity while maintaining precision through specialized processing at each stage

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements preliminary action by pre-processing images to detect and extract sparkle points before full analysis, and by using a pre-trained neural network model. The filtering techniques and sparkle point identification are performed in advance on all images, allowing rapid comparison and analysis without repeating full processing for each case

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If detailed image analysis and filtering techniques are applied, then identification accuracy improves, but device complexity increases

Engineering Contradiction:
Improvepigment identification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary neural network model that acts as a mediator between raw image data and pigment identification. The CNN model processes complex image features and transformations, converting detailed visual information into standardized probability distributions that can be efficiently compared against reference data, thereby maintaining high accuracy while managing system complexity through abstraction

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If convolutional neural network with multiple processing steps is used, then identification accuracy and reliability improve, but loss of time increases due to complex processing

Engineering Contradiction:
Improvematching reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent ensures continuity of useful action by implementing a streamlined processing pipeline where images are processed sequentially through optimized stages without interruption. The neural network model continuously processes extracted features, and results are immediately compared against the database, eliminating idle time and ensuring that each processing step directly contributes to the final identification, thereby maintaining high reliability with efficient time utilization

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP4058986B1Method and device for identification of effect pigments in a target coating
Publication Date: 2025.10.01 BASF COATINGS GMBH
  • EP4058986B1 patent drawingFigure 1
  • EP4058986B1 patent drawingFigure 2
  • EP4058986B1 patent drawingFigure 3a~3c

AI summary

The present invention refers to a computer-implemented method, the 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, - 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, - 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 with the target coating. The present invention further provides a respective device and a non- transitory computer readable medium.