This dataset consists of 14,710 labeled photographs of Hass avocados (Persea Americana Mill. cv Hass), resized to 800 x 800 pixels and saved in the .jpg format, designed to facilitate the development of deep learning models for predicting ripening stages and estimating shelf-life.
A total of 478 Hass avocados were acquired three days post-harvest and categorized into three storage groups: T10 at 10 ºC with 85% relative humidity (RH); T20 at 20 ºC with 85% RH; and Tamb under ambient conditions.
The ripening process of these avocados was documented through daily photographs (2 of each sample of opposite sides), each linked to a detailed Ripening Index with five stages:
1 - Underripe;
2 - Breaking;
3 - Ripe (First Stage);
4 - Ripe (Second Stage);
5 - Overripe.
The fourth stage marked the end of the avocados' shelf-life, with any sample classified as stage 5 considered beyond its prime. Time stamps on each photograph enable the tracking of the duration from any photograph, to the point each avocado reached the end of its shelf-life.
Additionally, an Excel spreadsheet accompanies the dataset, listing all photograph filenames, their corresponding sample number, storage group, classification according to the 5-stage Ripening Index, the day the photograph was taken relative to the start of the experiment, and the side of the fruit photographed (a or b).
Please cite the original contributors if you use it for your own work, by referring to this dataset.