StomataSeg: Semi-Supervised Instance Segmentation for Sorghum Stomatal Components
Abstract
The primary distribution of this Sorghum Stomata Dataset(StomataSeg) is patch-based: the original patches are stored inside the original_patches/ directory, and the pseudo labels patches are stored inside the pseudo_labels_patches/ directory. For completeness and reproducibility, the original full-resolution microscope images and their original COCO annotation files are provided as supplementary material in original_images/. Each split (train/val/test) includes matching COCO-style JSON annotations with three instance classes (pore area, guard cell area, complex area).
Fields of Study & Subjects
Smart Agriculture and AI
Advanced Neural Network Applications
Cell Image Analysis Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 January 2026
- Document type
- Dataset