Textile Visual Quality Control Using Image Sub-areas

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing quality control processes for warning protection clothing are time-consuming, subjective, and lack objective precision, particularly in assessing the luminosity and reflection capacity of textiles after washing and wear, which can lead to non-compliance with functional standards.

Innovation Solution

A procedure and device for visual quality control that involves selecting specific sub-areas of the textile for analysis based on image processing techniques, including edge recognition, morphological processing, and color-based exemptions, using multiple images to evaluate pixel brightness and reflection, and comparing these evaluations against threshold values for objective assessment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual visual inspection by trained personnel is used, then quality control can be performed with simple equipment, but the process is subjective and lacks precision

Engineering Contradiction:
Improvequality control precisionVSAvoidequipment complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual visual inspection by trained personnel with an automated image processing system. The system captures images of the textile, processes them through algorithms to detect defects, and provides objective quality assessment. This substitution eliminates subjectivity while maintaining operational simplicity through software-based analysis rather than complex hardware.

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

2Reliability

If automated camera systems are used for quality control, then objectivity and precision are improved, but the inspection process becomes time-consuming

Engineering Contradiction:
Improvequality control reliabilityVSAvoidinspection time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the quality control process into distinct image processing steps: capturing multiple images at different exposure settings, selectively processing relevant areas, and analyzing specific quality parameters. This segmentation allows parallel processing of different image sets and focuses computational resources on critical defect detection areas, significantly reducing total inspection time while maintaining comprehensive quality assessment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by capturing multiple images at different exposure settings simultaneously before the actual quality analysis begins. This pre-capture of various exposure conditions allows the subsequent processing to work with pre-prepared data, eliminating the need for sequential shooting and reducing overall inspection time while ensuring all necessary quality parameters are captured.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If multiple images with different exposure settings are captured, then measurement precision is improved, but the complexity of image processing increases

Engineering Contradiction:
Improvepixel evaluation precisionVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by processing different areas of the textile image with different exposure settings according to their specific requirements. Bright areas use underexposed images to prevent overexposure artifacts, while dark areas use overexposed images to ensure sufficient brightness for defect detection. This localized processing approach improves measurement precision for each specific area while reducing overall processing complexity by avoiding uniform processing of the entire image.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3327627B1Method, apparatus and computer program for visual quality control of textiles
Publication Date: 2022.08.17 MEWA TEXTIL SERVICE AG & CO MANAGEMENT OHG
  • EP3327627B1 patent drawingFigure 1~2
  • EP3327627B1 patent drawingFigure 3~5
  • EP3327627B1 patent drawingFigure 6~9

AI summary

The present invention relates to a device, a computer program, and a method for the visual quality control of textiles, comprising the steps of: - capturing at least one image (100, 102) of a textile object (10), - selecting at least one sub-area (112, 116, 120) of the captured textile object in the image (100, 102) based on at least one predetermined selection criterion, - evaluating at least some image points in the selected sub-area (112, 116, 120) and determining an evaluation value for the image points based on at least one predetermined evaluation criterion, - comparing the evaluation value with a predetermined threshold value, or - calculating an averaged evaluation value for all evaluated image points and comparing the averaged evaluation value with the predetermined threshold value.