# LSID-Beans: Leaf on Stem Image Dataset of 6,981 Common Bean Leaf Images with Segmentation Masks, Fiducial Markers and Measured Leaf Area (UFJF, AgML Mirror)

## Facts

- Provider: Karla Florentino, Paulo Rozatto, Kaio Sousa, Lucas Hudson, Artur Meyer and Alemilson Silva (Universidade Federal de Juiz de Fora); Hugging Face mirror by Project-AgML
- License: CC-BY-4.0 (https://data.mendeley.com/public-api/datasets/f42hwwrpgn?version=3)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Project-AgML/LSID_bean_segmentation
- Access: public, readable without an account
- DOI: https://doi.org/10.17632/f42hwwrpgn.3
- Category: Agriculture & Environment
- Source: https://huggingface.co/datasets/Project-AgML/LSID_bean_segmentation
- Page: https://scigantic.com/archive/5d962605-de5b-5902-8c56-eadf2c7c10c4
- Keywords: Agriculture & Environment, image segmentation, Parquet, Hugging Face

## About

LSID-Beans holds 6,981 images (512 x 512) of 612 common bean (Phaseolus vulgaris) leaves still on the stem, each photographed next to a fiducial marker. Annotations give the measured leaf dimensions (area, perimeter, length and width), leaf segmentation masks, the real area of the marker, marker pose, capture conditions and camera calibration. Built for deep learning of non-destructive leaf area and leaf dimension measurement from photos. Useful for leaf segmentation, plant phenotyping, and leaf area estimation in plant physiology. Stored as Parquet shards with the image bytes and annotations in columns; load with datasets.load_dataset("Project-AgML/LSID_bean_segmentation") 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 Karla Florentino, Paulo Rozatto, Kaio Sousa, Lucas Hudson, Artur Meyer and Alemilson Silva et al. and the DOI 10.17632/f42hwwrpgn.3.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Project-AgML/LSID_bean_segmentation")
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/5d962605-de5b-5902-8c56-eadf2c7c10c4
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/5d962605-de5b-5902-8c56-eadf2c7c10c4
- Over MCP: `get_schema_card` with id `5d962605-de5b-5902-8c56-eadf2c7c10c4` 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)
