Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing
Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visua...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7960 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850077012579844096 |
|---|---|
| author | Vasutorn Chaowalittawin Woranidtha Krungseanmuang Posathip Sathaporn Boonchana Purahong |
| author_facet | Vasutorn Chaowalittawin Woranidtha Krungseanmuang Posathip Sathaporn Boonchana Purahong |
| author_sort | Vasutorn Chaowalittawin |
| collection | DOAJ |
| description | Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. |
| format | Article |
| id | doaj-art-8c5ff50493554a0fbc0916e874bf081a |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-8c5ff50493554a0fbc0916e874bf081a2025-08-20T02:45:53ZengMDPI AGApplied Sciences2076-34172025-07-011514796010.3390/app15147960Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image ProcessingVasutorn Chaowalittawin0Woranidtha Krungseanmuang1Posathip Sathaporn2Boonchana Purahong3Department of Robotics and Computational Intelligent Systems, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandDepartment of Robotics and Computational Intelligent Systems, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandDepartment of Robotics and Computational Intelligent Systems, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandDepartment of IoT and Information Engineering, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, ThailandDuck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods.https://www.mdpi.com/2076-3417/15/14/7960CNNpre-processing techniqueslight sourcescrack detectionduck egg |
| spellingShingle | Vasutorn Chaowalittawin Woranidtha Krungseanmuang Posathip Sathaporn Boonchana Purahong Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing Applied Sciences CNN pre-processing techniques light sources crack detection duck egg |
| title | Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing |
| title_full | Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing |
| title_fullStr | Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing |
| title_full_unstemmed | Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing |
| title_short | Duck Egg Crack Detection Using an Adaptive CNN Ensemble with Multi-Light Channels and Image Processing |
| title_sort | duck egg crack detection using an adaptive cnn ensemble with multi light channels and image processing |
| topic | CNN pre-processing techniques light sources crack detection duck egg |
| url | https://www.mdpi.com/2076-3417/15/14/7960 |
| work_keys_str_mv | AT vasutornchaowalittawin duckeggcrackdetectionusinganadaptivecnnensemblewithmultilightchannelsandimageprocessing AT woranidthakrungseanmuang duckeggcrackdetectionusinganadaptivecnnensemblewithmultilightchannelsandimageprocessing AT posathipsathaporn duckeggcrackdetectionusinganadaptivecnnensemblewithmultilightchannelsandimageprocessing AT boonchanapurahong duckeggcrackdetectionusinganadaptivecnnensemblewithmultilightchannelsandimageprocessing |