AI-driven maturity stage identification of Amazonian fruits
Keywords:image processing, Machine Learning, vegetative index, amazonian fruits, moriche, seje
This paper presents a Machine Learning approach for the classification of Amazonian fruits (Moriche, Asaí y Seje). Vegetative indices were used as features to drive the corresponding classification by processing RGB/VIS imagery. In turn, we implemented 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 only with Moriche features, and then tested for Asaí and Seje. 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 implemented vegetative indices accurately correlate with the physiological characteristics of the fruits, being relevant for the stage of maturity of the three varieties.