Quality Detection of Stored Potatoes via Transfer Learning: A CNN and Vision Transformer Approach

2026-01-02

arXiv.org

AI Summary

This study addresses the challenge of monitoring potato quality during storage, where sprouting, weight loss, and dynamic shelf-life changes complicate accurate assessment. To this end, the authors propose a novel deep learning approach that integrates convolutional neural networks (CNNs) with Vision Transformers (ViT), marking the first application of such hybrid architectures to potato storage quality evaluation. Leveraging transfer learning, pretrained models—including ResNet, VGG, DenseNet, and ViT—are employed to extract visual features for two tasks: a binary classification model to detect sprouting and a coarse-grained multi-class model to predict both weight loss severity and remaining shelf life. Experimental results demonstrate that DenseNet achieves 98.03% accuracy in sprouting detection, while the coarse-grained shelf-life classification (with 2–5 classes) exceeds 89.83% accuracy, significantly outperforming fine-grained alternatives and confirming the robustness and effectiveness of the proposed strategy.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Image-based deep learning provides a non-invasive, scalable solution for monitoring potato quality during storage, addressing key challenges such as sprout detection, weight loss estimation, and shelf-life prediction. In this study, images and corresponding weight data were collected over a 200-day period under controlled temperature and humidity conditions. Leveraging powerful pre-trained architectures of ResNet, VGG, DenseNet, and Vision Transformer (ViT), we designed two specialized models: (1) a high-precision binary classifier for sprout detection, and (2) an advanced multi-class predictor to estimate weight loss and forecast remaining shelf-life with remarkable accuracy. DenseNet achieved exceptional performance, with 98.03% accuracy in sprout detection. Shelf-life prediction models performed best with coarse class divisions (2-5 classes), achieving over 89.83% accuracy, while accuracy declined for finer divisions (6-8 classes) due to subtle visual differences and limited data per class. These findings demonstrate the feasibility of integrating image-based models into automated sorting and inventory systems, enabling early identification of sprouted potatoes and dynamic categorization based on storage stage. Practical implications include improved inventory management, differential pricing strategies, and reduced food waste across supply chains. While predicting exact shelf-life intervals remains challenging, focusing on broader class divisions ensures robust performance. Future research should aim to develop generalized models trained on diverse potato varieties and storage conditions to enhance adaptability and scalability. Overall, this approach offers a cost-effective, non-destructive method for quality assessment, supporting efficiency and sustainability in potato storage and distribution.

Problem

• potato quality
• sprout detection
• weight loss estimation
• shelf-life prediction
• storage monitoring

Innovation

• Transfer Learning
• Vision Transformer
• Potato Quality Detection
• Shelf-life Prediction
• DenseNet