Polarized Surface Inspection Imaging for Moving Objects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional imaging systems struggle to acquire images of objects with appropriate levels of detail due to poor lighting conditions, especially in factory settings, leading to incomplete representation of surface features, and multiple image acquisitions can be challenging for moving objects.

Innovation Solution

A single image acquisition method using different types of light projected from various directions, such as linearly, elliptically, or circularly polarized light, to generate a detailed image by analyzing sub-images with distinct polarization orientations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple image acquisitions are performed to improve surface feature detail, then image quality improves, but device complexity and processing time increase

Engineering Contradiction:
Improvesurface feature detailVSAvoidcomplexity of combining multiple images
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the imaging process by using a single image acquisition that captures multiple polarization orientations simultaneously through different regions of the sensor array. Each region is associated with a specific polarization filter orientation, allowing the system to obtain multiple polarization images in one shot rather than requiring multiple sequential acquisitions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent adds a spatial dimension to the polarization measurement by distributing different polarization filters across different regions of the sensor array. This spatial multiplexing allows simultaneous capture of multiple polarization states without temporal sequencing, effectively transforming a time-based problem into a space-based solution.

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

2Loss of information

If multiple image acquisitions are performed to capture complete surface features, then image completeness improves, but productivity decreases for moving objects

Engineering Contradiction:
Improvecompleteness of surface featuresVSAvoidspeed of imaging moving objects
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The sensor array is segmented into multiple regions, each equipped with polarization filters at different orientations. This segmentation enables simultaneous capture of multiple polarization images across different spatial zones, ensuring complete surface feature information is obtained in a single acquisition without requiring sequential imaging that would fail for moving objects.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system maintains continuous imaging capability by capturing all necessary polarization information simultaneously in a single exposure. This eliminates gaps between sequential acquisitions, ensuring that moving objects are imaged continuously without interruption, thereby maintaining both information completeness and high productivity.

Inventive Principle:
Principle #20Continuity of useful action

3Measurement precision

If conventional lighting is used to illuminate the surface, then setup simplicity is maintained, but image contrast and detail are insufficient

Engineering Contradiction:
Improveimage contrast and detailVSAvoidlighting configuration
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by assigning different polarization filter orientations to different regions of the sensor array. Each region is optimized to detect light polarized at a specific angle, allowing the system to extract detailed surface information from various lighting conditions simultaneously. This regional specialization enables high contrast imaging without requiring complex external lighting modifications.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The imaging system performs self-service by using the reflected light itself to carry polarization information that reveals surface features. Rather than requiring complex external lighting setups, the system leverages the natural polarization properties of reflected light and uses internal polarization filters to extract surface detail, thereby maintaining setup simplicity while achieving high image quality.

Inventive Principle:
Principle #25Self-service

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

This approach allows for high-detail imaging of surface features with reduced computational complexity and equipment costs, suitable for both stationary and moving targets, by combining sub-images to enhance contrast and resolution.

Implementation Method 1

A single image acquisition is executed, including acquiring at least three sub-images, each of the at least three sub-images being acquired using a different one of the at least three types of light and at least partly excluding the at least two other types of light

Methodology Applied
Scientific EffectPolarization: Polarisation

Data Source

PatentEP3855170B1Method for vision inspection with multiple types of light
Publication Date: 2025.12.31 COGNEX CORP
  • EP3855170B1 patent drawingFigure 1
  • EP3855170B1 patent drawingFigure 2
  • EP3855170B1 patent drawingFigure 3A~3B

AI summary

Systems and methods are provided for acquiring images of objects. Light (110a, 110b, 110c, 110d) of different types (e.g., different polarization orientations) can be directed onto an object (112) from different respective directions (e.g., from different sides of the object). A single image acquisition can be executed in order to acquire different sub-image data (120a, 120b, 120c) corresponding to the different light types. An image (122) of a surface of the object, including representation of surface features of the surface, can be generated based on the sub-image data (120a, 120, 120c).