Abstract:Post-harvest fruit quality assessment is essential for reducing food waste, yet reliable non-destructive methods typically depend on expensive hyperspectral cameras and computationally intensive deep learning models. These systems typically require GPU resources, large-scale training data, and domain expertise, limiting their feasibility for many real-world agricultural settings. This study systematically evaluates 20 classical machine learning algorithms on hyperspectral imaging data for simultaneous ripeness classification and firmness prediction across five fruit species, using cross-validated experimental design with Bayesian hyperparameter optimization. Data preprocessing strategy, particularly class balancing and spectral transformations, contributes as much to prediction accuracy as algorithm choice. Our results show that tree-based machine learning models can outperform state-of-the-art deep earning models reported in Fruit-HSNet. Moreover, the findings indicate that only three visible-range wavelengths are needed to recover over 94% of full-spectrum accuracy, demonstrating that low-cost multispectral sensors combined with lightweight machine learning models can serve as practical alternatives to expensive hyperspectral cameras and complex deep learning approaches for practical fruit quality sorting.
| Subjects: | Image and Video Processing (eess.IV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.22788 [eess.IV] |
| (or arXiv:2604.22788v1 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2604.22788 arXiv-issued DOI via DataCite |
From: Phongsakon Mark Konrad [view email]
[v1]
Sun, 5 Apr 2026 07:57:27 UTC (563 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。