# Heliconius Mimicry Gold Standard: Dorsal Butterfly Images with Bird and Butterfly Visual Acuity Transforms

## Facts

- Provider: Imageomics Institute; source images Hoyal Cuthill et al. (University of Cambridge)
- License: CC0-1.0 (https://huggingface.co/datasets/imageomics/Curated_GoldStandard_Hoyal_Cuthill)
- Size: 4 files
- Format: PNG (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/imageomics/Curated_GoldStandard_Hoyal_Cuthill
- Access: public, readable without an account
- Category: Life Sciences
- Source: https://github.com/Imageomics/Butterfly-mimicry
- Page: https://scigantic.com/archive/7d36a8dd-1d27-575a-bcb9-5f6137256a7e
- Keywords: Life Sciences, PNG, Hugging Face

## About

A curated subset of the Hoyal Cuthill et al. (2019) Heliconius butterfly photograph collection, prepared by the Imageomics Institute to study Mullerian mimicry between Heliconius erato and Heliconius melpomene. It contains 960 dorsal images of 320 specimens across 18 subspecies: for each specimen the original low-resolution RGB image (cropped and resized to 64 pixels high and padded to 140 wide, as in the source study), plus two versions transformed with the AcuityView R package to simulate what a bird predator and a butterfly would resolve, using acuity estimates from AcuityView 2.0 and Land (1997). The zip archive holds train/test folders per subspecies for the original images, Acuities/ folders (train_bird, test_bird, train_butterfly, test_butterfly), and dorsal_images_cuthill/ with processed dorsal images of all 1,234 specimens from the source dataset. Intended for subspecies classification under different observer acuities and for comparing machine and animal perception of mimicry. Dedicated to the public domain under CC0; the source images are on Dryad (doi:10.5061/dryad.2hp1978). Cite Hoyal Cuthill et al. (2019) and the Imageomics Butterfly-mimicry work.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="imageomics/Curated_GoldStandard_Hoyal_Cuthill", filename="Curated_GS_Cuthill.zip", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: PNG

Example file: `Curated_GS_Cuthill.zip`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/7d36a8dd-1d27-575a-bcb9-5f6137256a7e
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/7d36a8dd-1d27-575a-bcb9-5f6137256a7e
- Over MCP: `get_schema_card` with id `7d36a8dd-1d27-575a-bcb9-5f6137256a7e` at https://api.scigantic.com/mcp

## Related topics

- [PNG datasets](https://scigantic.com/topics/png)
- [Life Sciences datasets](https://scigantic.com/topics/life-sciences)
