AI-driven maturity stage identification of Amazonian fruits

This paper presents a Machine Learning approach for the classification of Amazonian fruits (Moriche, Asai and Seje). Vegetative indices were used as features to drive the corresponding classification by processing RGB/VIS imagery. In this regard, we used four Machine Learning models to identify the stage of maturity for the fruits: Multi-variable regressions, Naives Bayes, Support Vector Machines and Artificial Neural Networks. These models were trained and tested with the features of each variety. Experimental results were validated by calculating ROC data, in which neural networks achieved an accuracy of 99% in the stage of maturity identification for the three amazonian varieties. These results allow us to conclude that the used vegetative indices accurately correlate with the physiological characteristics of the fruits, being relevant for the stage of maturity of the three varieties.