Deep learning benchmark for hazelnut quality assessment using X-ray images

Researchers have developed a deep learning benchmark for classifying hazelnut quality using X-ray images. The study, which involved 799 segmented X-ray images, evaluated various single-model configurations and ensembles. An ensemble combining a convolutional neural network trained with binary cross-entropy and a frozen Swin Transformer achieved the highest balanced accuracy of 86.3%. The findings underscore the potential of deep learning for automated agricultural quality assessment and highlight the necessity of rigorous evaluation and data curation for small, imbalanced datasets. AI

IMPACT Establishes a new benchmark for agricultural imaging analysis, potentially improving quality control in food production.

RANK_REASON The cluster contains an academic paper detailing a new benchmark and methodology for image classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• Binary Cross-Entropy
• convolutional neural network
• Giancarlo Sportelli
• Hugging Face
• Swin Transformer
• X-ray

• paper
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →