Related Experiment Video
Updated: Jun 14, 2025
11:34
Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
Published on: May 15, 2017
11.1K
A two-stage defect detection method for unevenly illuminated self-adhesive printed materials.
Guifeng Peng1, Tao Song2, Songxiao Cao1
1College of Metrology Measurement and Instrument, China Jiliang University, Hangzhou, 310018, China.
Scientific Reports
|September 4, 2024
Summary
This study introduces a new defect detection method for printed materials, improving accuracy by correcting brightness and using a two-stage approach. The enhanced technique effectively identifies printing defects while minimizing false positives and missed defects.
Area of Science:
- Image Processing
- Manufacturing Quality Control
Background:
- Printing defect detection faces challenges with uneven illumination and complex textures, leading to inaccurate extraction and localization.
- Existing image difference methods often generate numerous small-scale pseudo-defects, complicating accurate analysis.
Purpose of the Study:
- To develop a comprehensive defect detection approach for self-adhesive printed materials.
- To address inaccuracies in defect extraction, localization, and reduce false positives in printed material inspection.
Main Methods:
- Implemented a joint bilateral filter with brightness correction to handle uneven illumination and smooth complex textures.
- Developed a two-stage defect detection strategy: initial localization using a bright-dark difference template group, followed by pseudo-defect filtering via feature similarity.
Main Results:
- The improved difference method achieved 99.1% average precision in defect localization across five diverse printing patterns.
- The two-stage strategy significantly reduced the false detection rate to below 0.5%, while maintaining a low missed defect rate.
Conclusions:
- The proposed integrated approach effectively overcomes limitations of traditional defect detection methods for printed materials.
- This method offers a robust solution for high-precision printing defect inspection, enhancing quality control in manufacturing.
