Adem Haj Boubaker
Research Subjects
Research Interests
Adem Haj Boubaker has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Hichem Snoussi
University of Technology of Troyes
1 shared publication - Kais Loukil
CES Laboratory ENIS National Engineering School University of Sfax, B.P. 3038 Sfax, Tunisia, Tunisia
1 shared publication - Mohamed Abid
CES Laboratory, ENIS National Engineering School, University of Sfax, Sfax B.P. 3038, Tunisia
1 shared publication - Slim Hamdi
CES Laboratory, ENIS National Engineering School, University of Sfax, Sfax B.P. 3038, Tunisia
1 shared publication
Latest Publications
- Open Access
- 3 December 2025
- Published by MDPI AG in Journal of Imaging
- Vol. 11 (12) , 431
Hybrid AI Pipeline for Laboratory Detection of Internal Potato Defects Using 2D RGB Imaging
The internal quality assessment of potato tubers is a crucial task in agro-laboratory processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in laboratory. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 95% and precision near 97.2% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.
- 3 December 2025
- Published by MDPI AG in Journal of Imaging
- Vol. 11 (12) , 431
Open AccessHybrid AI Pipeline for Laboratory Detection of Internal Potato Defects Using 2D RGB Imaging
The internal quality assessment of potato tubers is a crucial task in agro-laboratory processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in laboratory. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 95% and precision near 97.2% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.