Non-Destructive Identification of Internal Watercore in Apples Based on Online Vis/NIR Spectroscopy

Abstract

HighlightsA custom-designed online Vis/NIR spectroscopy system was used for real-time detection of watercore in apples.Watercore severity index (WSI) was applied for watercore severity assessment.Higher than 95.0% accuracy was obtained for total samples in classifying sound apples from watercore groups using kNN, BPNN, SVM, and 1D CNN at a detection speed of 3 apples s-1.Linear kernel SVM achieved the best classification accuracy of 96% for samples in the prediction set.Abstract. Watercore, an internal physiological disorder affecting apples, can be characterized by water-soaked, glassy regions near the fruit core. It is used as an indicator of full ripeness, storage suitability, and price of apples in many countries. Therefore, fast and non-destructive detection of watercore plays an important role in improving the commercial value of apples and reducing postharvest costs. In this study, an online visible/near-infrared (Vis/NIR) spectroscopy system was proposed for real-time detection of watercore in ‘Fuji’ apples (Malus pumila Mill.). A total of 318 samples harvested during harvest season in the same orchard were analyzed for both watercore severity index (WSI) and soluble solids content (SSC). According to the USDA watercore classification standard, all samples were classified into one of four classes (sound, slight, moderate, or severe) based on the affected area of watercore. Results showed that, although there was a positive correlation between spectral intensity and affected area of watercore, no significant relationship between affected area size and SSC could be obtained by Pearson test (correlation coefficient ~0.094). Generally, >95.0% accuracy was obtained for total samples at a detection speed of 3 apples s-1 in classifying sound from watercore groups using k-nearest neighbors (kNN) algorithm, back-propagation neural network (BPNN), support vector machine (SVM) classification, and one-dimensional convolutional neural network (1D-CNN). The best classification result was achieved by linear kernel SVM, with an accuracy of 96% for total samples. These classification algorithms showed preliminary feasibility for online screening of apples with watercore using Vis/NIR spectroscopy in industrial applications. Keywords: Apple watercore, Machine learning, Online detection, Vis/NIR spectroscopy, Watercore severity index.