Strawberry Water Content Estimation and Ripeness Classification Using Hyperspectral Sensing

We propose data-driven approaches to water content estimation and ripeness classification of the strawberry fruit. A narrowband hyperspectral spectroradiometer was used collect reflectance signatures from 43 fruits at different levels. Then, ground truth obtained using oven-dry method. To estimate content, 674 698 nm bands were selected create a normalized difference index. The index as an input logarithmic model for estimating fruit content. gave correlation coefficient 0.82 Root Mean Squared Error (RMSE) 0.0092 g/g. For classification, Support Vector Machine (SVM) full spectrum achieved over 98% accuracy. Our analysis further show that, in absence data, our proposed input, which uses values only two frequency bands, 71% accuracy, might be adequate certain applications with limited sensing resources.