Phenotypic image dataset of naturally grown shiitake mushrooms across multiple varieties and growth stages

This dataset contains phenotypic images of naturally grown shiitake mushrooms collected under real cultivation conditions. The dataset covers multiple shiitake mushroom varieties and growth stages and supports classification, grading, and object detection tasks. The dataset includes RGB images acquired in natural cultivation environments with varying illumination conditions, occlusions, overlaps, and complex backgrounds. Corresponding object detection annotations are provided as plain-text label files compatible with mainstream deep learning detection frameworks. The dataset was developed to support research in agricultural computer vision, intelligent mushroom cultivation, phenotypic analysis, and deep learning-based detection methods. The repository contains image data, annotation files, metadata, and related scripts for dataset organization and experimental reproduction used in the accompanying manuscript.