# Barley Foliar Disease Segmentation: Brown Rust and Ramularia Leaf Spot on Field-Grown Flag Leaves of 62 Genotypes, 4,764 Image Patches (TU Munich, AgML Mirror)

## Facts

- Provider: Sofia Martello, Nikita Genze and Dominik Grimm (Technical University of Munich); Hugging Face mirror by Project-AgML
- License: MIT (https://data.mendeley.com/public-api/datasets/4ny92p2r8f?version=1)
- Size: 12 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/barley_disease_segmentation
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/4ny92p2r8f.1
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/barley_disease_segmentation
- Page: https://scigantic.com/archive/6d7958e4-0715-5492-8810-9032bb3112a3
- Keywords: Agriculture & Environment, image segmentation, Parquet, Hugging Face

## About

High-resolution images of barley flag leaves naturally infected with two visually similar foliar pathogens, brown rust (Puccinia hordei) and ramularia leaf spot (Ramularia collo-cygni), with pixel masks for multiclass disease segmentation. Leaves came from 62 barley genotypes in field trials in Estrées-Saint-Denis (France) and Irlbach and Paitzkofen (Germany) at Zadoks stages 50 to 69, and were imaged on a fixed laboratory platform. The original 336 annotated leaves were cut into patches; the set reflects mixed infections, varied symptoms, senescence discoloration and strong class imbalance. This mirror holds 4,764 images with masks. Useful for disease severity phenotyping in resistance breeding. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/barley_disease_segmentation") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: MIT, as stated by the original publisher; cite Sofia Martello, Nikita Genze and Dominik Grimm et al. and the DOI 10.17632/4ny92p2r8f.1.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/barley_disease_segmentation")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00010.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/6d7958e4-0715-5492-8810-9032bb3112a3
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/6d7958e4-0715-5492-8810-9032bb3112a3
- Over MCP: `get_schema_card` with id `6d7958e4-0715-5492-8810-9032bb3112a3` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [Agriculture & Environment datasets](https://scigantic.com/topics/agriculture-and-environment)
