# RoCoLe: Robusta Coffee Leaf Images for Coffee Leaf Rust and Red Spider Mite Detection, 1,560 Leaves with Severity Labels and Masks (AgML Mirror)

## Facts

- Provider: Jorge Parraga-Alava, Kevin Cusme, Angélica Loor and Esneider Santander; Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/c5yvn32dzg?version=2)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/RoCoLe_disease_detection
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/c5yvn32dzg.2
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/RoCoLe_disease_detection
- Page: https://scigantic.com/archive/ad382e4a-cb57-56b1-b08c-1d8f21b7597f
- Keywords: Agriculture & Environment, image segmentation, Parquet, Hugging Face

## About

RoCoLe holds 1,560 images of robusta coffee (Coffea canephora) leaves: healthy leaves, and leaves with visible red spider mites or with the spots of coffee leaf rust (Hemileia vastatrix). Annotations give the state (healthy or unhealthy), the disease severity measured as the leaf area covered by spots, a bounding box and a segmentation mask per leaf, across six categories. Useful for coffee leaf rust detection, disease severity estimation, and leaf segmentation in coffee plantations. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/RoCoLe_disease_detection") or through the AgML Python library (Project-AgML, UC Davis), which reformatted the original release. License: CC BY 4.0, as stated by the original publisher; cite Jorge Parraga-Alava, Kevin Cusme, Angélica Loor and Esneider Santander et al. and the DOI 10.17632/c5yvn32dzg.2.

## Load the data

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

## Data structure

File types in sampled files: Parquet

Example file: `data/train-00000-of-00002.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ad382e4a-cb57-56b1-b08c-1d8f21b7597f
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ad382e4a-cb57-56b1-b08c-1d8f21b7597f
- Over MCP: `get_schema_card` with id `ad382e4a-cb57-56b1-b08c-1d8f21b7597f` 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)
