AgriEngineering · 2025 · 10 citations · 26 references
ComputingComputer ScienceFood ScienceComputer VisionMachine LearningMachine VisionDeep LearningFruit PathologyFruit QualityFruit Quality EvaluationFruit Quality ImprovementObject RecognitionCitrus FruitsDeep Learning-based Quality AssessmentDiagnostic ReportsFruit ClassificationFruit DetectionFruit Image AnalysisMobile Edge DevicesVision Transformers
This study introduces an interpretable deep learning pipeline for citrus fruit quality classification using the ViT-Base model vit_base_patch16_224 and Microsoft’s Phi-3-mini LLM. The ViT model, fine-tuned on resized 224 × 224 images with ImageNet weights, classifies fruits into good, damaged, and rotten categories, achieving 98.29% accuracy. For interpretability, Grad-CAM highlights damaged regions, while the Phi-3-mini generates human-readable diagnostic reports. The system runs efficiently on edge devices, enabling real-time, on-site quality assessment. This approach enhances transparency and decision-making, showing strong potential for deployment in the citrus industry.
26
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations