Multispectral ROI Detection Using Contrast-Selected Wavelengths

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current multispectral imaging methods for industrial processes are inefficient, costly, and inaccurate due to unsuitable wavelength selection, temperature-dependent LED emission, and limitations in filter elements, leading to poor detection of spectral features and increased complexity.

Innovation Solution

A method that selects wavelength ranges to minimize and maximize intensity differences between a target object and an area of interest, using a series of wavelength ranges to capture images with a broadband camera, and identify distinguishing features through image comparison.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If standard LEDs are used for illumination, then the lighting equipment is readily available and cost-effective, but the spectral resolution is insufficient (10 nm to 30 nm range cannot be resolved) and temperature-dependent emission reduces accuracy

Engineering Contradiction:
Improvespectral feature detection accuracyVSAvoidillumination system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The spectrum is segmented into multiple wavelength ranges, with each range captured by a dedicated image sensor or sensor array. This allows resolution of narrow spectral features (10-30 nm) that would be impossible with a single broadband sensor, while using relatively simple LED illumination sources.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from temporal spectral analysis (hyperspectral imaging over time) to spatial spectral analysis, where different wavelength ranges are captured simultaneously across different spatial locations or sensor elements. This eliminates the need for mechanical filter exchanges and achieves high spectral resolution without moving parts.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple filter elements are installed on recording devices for passive multispectral methods, then wavelength selection is achieved, but the number of filter elements cannot be increased indefinitely as it limits image resolution and filter replacement is very expensive

Engineering Contradiction:
Improvewavelength selection accuracyVSAvoidfilter system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the wavelength selection function from the recording device (camera) and places it in the illumination system. Instead of using multiple filters on the camera, different LED modules with distinct spectral emissions illuminate different wavelength ranges, eliminating the need for expensive filter elements and their mechanical exchange mechanisms.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The mechanical filter exchange system is replaced with an electronic/control-based system where different LED modules are activated sequentially or simultaneously. This substitution eliminates moving parts, reduces maintenance costs, and enables rapid wavelength switching without mechanical intervention.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If hyperspectral methods are used for object recognition, then spectral resolution is significantly higher than multispectral methods, but devices are expensive, difficult to operate, require extensive knowledge for evaluation, and need specialized image processing software

Engineering Contradiction:
Improvespectral resolutionVSAvoidsystem operation simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent applies partial spectral analysis by selecting only the specific wavelength ranges needed for the application, rather than capturing the entire spectrum as in hyperspectral imaging. This provides sufficient spectral discrimination for quality control while dramatically simplifying data processing and reducing computational requirements.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the operational parameters from full hyperspectral capture to targeted multispectral sampling at specific wavelength ranges. This parameter change optimizes the balance between spectral resolution and operational simplicity, making the system accessible to users without specialized knowledge while maintaining adequate detection capability.

Inventive Principle:
Principle #35Parameter changes

4Measurement precision

If sequential illumination with different wavelength ranges is used, then spectral features can be resolved accurately, but the response time is relatively slow due to mechanical exchange of filter elements

Engineering Contradiction:
Improvespectral feature resolutionVSAvoiddetection speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent uses periodic activation of different LED modules to illuminate the object at different wavelength ranges. Since LEDs can be switched on and off extremely rapidly (microsecond timescale), this periodic action achieves spectral multiplexing without the mechanical delays inherent in filter wheel systems, maintaining both high spectral resolution and fast detection speed.

Inventive Principle:
Principle #19Periodic action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables quick, efficient, and accurate detection of areas of interest with reduced costs and complexity, eliminating the need for time-consuming trial-and-error testing and hyperspectral image analysis.

Implementation Method 1

the intensity difference between the area of interest and the target object is minimized in the first wavelength range and the intensity difference between the area of interest and the target object is maximized in the second wavelength range

Methodology Applied
Scientific EffectReflection: Reflection

Data Source

PatentEP4653844A1Method for detecting a region of interest in multispectral images
Publication Date: 2025.11.26 SICK AG
  • EP4653844A1 patent drawingFigure 1
  • EP4653844A1 patent drawingFigure 2~3
  • EP4653844A1 patent drawingFigure 4~5B

AI summary

The invention relates to a method for detecting an area of ​​interest in multispectral images of a target object in an industrial process and to a device configured to perform the method. The method comprises the steps of: selecting a series of wavelength ranges, wherein the series of wavelength ranges includes at least a first wavelength range and a second wavelength range that differs from the first wavelength range, wherein the intensity difference between the area of ​​interest and the target object is minimized in the first wavelength range and the intensity difference between the area of ​​interest and the target object is maximized in the second wavelength range.wherein the intensity difference between the region of interest and the target object in a wavelength range is preferably defined by the difference in the spectrum of the region of interest and the target object within the wavelength range; acquiring a first image of the target object in the first wavelength range; acquiring a second image of the target object in the second wavelength range; comparing the first and second images of the target object to identify at least one distinguishing feature between the images of the target object; and recognizing the region of interest based on the identified at least one distinguishing feature.