VIC01

The dataset utilized in this study consists of images of Macauba (Acrocomia aculeata) fruits collected from Fazenda Limeira in Lavras, Minas Gerais, Brazil. The fruits were sourced from palm trees naturally growing in a grazing area, ensuring a diverse and representative sample. A total of randomly selected immature fruits were meticulously cleaned and stored in a shaded environment for 48 hours to preserve their natural state before imaging. High-resolution photographs were then taken to capture detailed biometric features essential for accurate detection and classification. The dataset was carefully curated to include variability in fruit size, shape, and color, enhancing the model’s ability to generalize and perform robustly in real-world conditions. This comprehensive dataset supports the optimization of agro-industrial processes by facilitating automated sorting, improving quality control, and reducing waste. Overall, the dataset plays a crucial role in demonstrating the potential of artificial intelligence in precision agriculture.