Saffron-DB: An image dataset for saffron quality control, classification, and automated assessment based on image analysis and deep learning.

The dataset contains JPG images of saffron stigmas organized by sample in a dedicated folder structure. For each sample, both original and augmented images are available. Data augmentation was performed using geometric and photometric transformations, including horizontal and vertical flipping, translation, scaling, rotation, brightness and contrast adjustment, and Gaussian blur. This step enriches the dataset and improves the robustness of deep learning models.