Non-Destructive Prediction of Fruit Ripeness and Firmness Using Hyperspectral Imaging and Lightweight Machine Learning Models
Under review at Computers and Electronics in Agriculture, 2025
Abstract
Hyperspectral imaging enables non-destructive assessment of fruit ripeness and firmness. We benchmark 19 traditional machine learning algorithms on dual-task prediction using the DeepHS Fruit dataset across five fruit species. Preprocessing strategy consistently matters more than algorithm choice. ExtraTrees with stratified resplit achieves 75.00% overall accuracy, surpassing Fruit-HSNet’s 70.73% while training in 0.31 seconds on consumer hardware.