Related Experiment Video
Updated: Apr 12, 2026
11:34
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
Published on: May 15, 2017
11.6K
Unsupervised defect detection in textiles based on Fourier analysis and wavelet shrinkage
Applied Optics
|May 14, 2015
Summary
This study introduces an unsupervised textile defect inspection method using Fourier analysis and wavelet shrinkage. The technique effectively identifies defects without reference images, offering a novel approach to quality control.
Area of Science:
- Materials Science
- Image Processing
- Textile Engineering
Background:
- Textile defect detection is crucial for quality control.
- Existing methods often require reference images or complex algorithms.
- Automated, unsupervised defect detection remains a challenge.
Purpose of the Study:
- To propose an unsupervised method for textile defect inspection.
- To eliminate the need for reference images in defect detection.
- To develop a robust method for identifying diverse textile defects.
Main Methods:
- Applying Fourier analysis to eliminate periodic background patterns.
- Utilizing wavelet shrinkage for denoising residual images.
- Employing thresholding on reconstructed images for defect segmentation.
Main Results:
- Successfully eliminated periodic background patterns.
- Denoised images revealed defect-specific information.
- Achieved effective segmentation of defects using thresholding.
- Demonstrated superior performance compared to other methods.
Conclusions:
- The proposed unsupervised method is effective for textile defect inspection.
- Fourier analysis and wavelet shrinkage offer a powerful combination for defect detection.
- The method shows promise for automated quality control in the textile industry.
