Learning Fruit Class from Short Wave Near Infrared Spectral Features, an AI Approach Towards Determining Fruit Type

This paper analyzes the potential of using short-wave NIRS (near-infrared spectroscopy) for fruit classification problems. The research focuses on O-H and C-H overtone features of fruit and its correlation with NIRS and therefore opens a new dimension of fruit classification problems using NIRS. Eleven fruits, which include apple, cherry, hass, kiwi, grapes, mango, melon, orange, loquat, plum, and apricot, were used in this study to cover physical characteristics such as peel thinness, pulp, seed thickness, and size. NIR spectral data is collected using the industry-standard F-750 fruit quality meter (wavelength range 300-1100nm) for all fruit mentioned above. Different shallow machine learning architectures were trained to classify fruits using spectral feature vectors. At first, using 83 features vectors within the range of 725-975nm (3nm-resolution) and then using only four features of wavelength 770nm, 840nm, 910nm, and 960nm (corresponding to O-H and C-H overtone features). For the 83 spectral features range as an input, the QDA classifier achieved a cross-validation accuracy of 100% and a test data accuracy of 93.02%. For the four features vector as an input, the QDA classifier achieved a cross-validation accuracy of 97.1% and test data accuracy of 90.38%. The results demonstrate that fruit classification is mainly a function of absorptivity of short wave NIR radiation primarily with respect to O-H and C-H overtones features. An LED-based device mainly having 770nm, 840nm, 910nm, and 960nm range LEDs can be used in applications where automation in fruit classification is required.