Related Experiment Video
Updated: Jan 17, 2026
04:23
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
Published on: April 21, 2023
2.3K
An acoustic signal-to-image conversion integrated convolutional neural network model for egg crack detection.
Z Balcı1, I Yabanova2, A Mert3
1Çaldıran Vocational School/Electronics and Automation Department, Van Yüzüncü Yıl University, Van, TÜRKİYE.
British Poultry Science
|September 15, 2025
Summary
This study introduces a novel acoustic crack detection system for eggshells using a convolutional neural network (CNN). The system accurately identifies even microscopic cracks, enhancing food safety and preventing spoilage.
Area of Science:
- Food Safety
- Biotechnology
- Machine Learning
Background:
- Eggshell integrity is crucial for food safety, as cracks allow pathogen entry, increasing food poisoning risks.
- Deformations compromise shell integrity, leading to accelerated egg deterioration and susceptibility to environmental damage.
Purpose of the Study:
- To develop a non-destructive crack detection system for eggshells.
- To mitigate food safety risks associated with fractured eggshells.
- To utilize acoustic signal analysis and machine learning for accurate crack identification.
Main Methods:
- A system was designed using mechanical and electronic sub-systems for non-destructive acoustic excitation of eggshells.
- High-sensitivity microphones captured acoustic signals, which were processed using variational mode decomposition (VMD).
- Intrinsic mode functions (IMFs) were converted to greyscale images and classified using a lightweight convolutional neural network (CNN).
Main Results:
- The developed system achieved 100% accuracy in distinguishing between intact and cracked eggs.
- The model successfully identified invisible micro-cracks, demonstrating high sensitivity.
- The acoustic signal-to-image conversion integrated with CNN proved effective for crack detection.
Conclusions:
- The proposed acoustic signal-to-image conversion and CNN model offer a highly effective solution for detecting eggshell cracks.
- This technology significantly enhances food safety by identifying compromised eggs, including those with micro-cracks.
- The non-destructive method provides a reliable approach to quality control in egg production and handling.
