# Salmonella Serovar Hyperspectral Microscopy: 500 Hypercube Images of Five Serovars for AI Classification

## Facts

- Provider: Papa, Bhattacharya, Park and Yi (Food AI Nexus)
- License: CC-BY-4.0 (https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral)
- Size: 504 files
- Format: PNG, Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral
- Access: public, readable without an account
- DOI: https://doi.org/10.3390/foods14152737
- Category: Health & Biomedical
- Source: https://huggingface.co/datasets/food-ai-nexus/salmonella-serovar-hyperspectral
- Page: https://scigantic.com/archive/8abf6e36-996d-537b-ab84-541d175ee308
- Keywords: Health & Biomedical, spectroscopy, PNG, Parquet, Hugging Face

## About

Hyperspectral microscopy images of five Salmonella enterica serovars relevant to poultry and foodborne illness (Enteritidis, Infantis, Kentucky, Johannesburg and the monophasic variant 4,[5],12:i:-), released with Papa, Bhattacharya, Park and Yi (2025), Foods 14(15):2737, doi:10.3390/foods14152737. Cultures at 10^5 CFU/mL were imaged with an Olympus BX43 upright microscope, a 100x oil-immersion objective and a HinaLea 4250 hyperspectral camera; 500 hypercubes (100 per serovar) were acquired. images/ holds RGB composites rendered from each hypercube at 620, 550 and 450 nm, one full 1936 x 1216 field of view per PNG, split 70/30 into 350 train and 150 test images balanced by serovar; spectra/ holds single-cell spectral features in Parquet (the same table is published separately as salmonella-serovar-hyperspectral-spectra, 25,972 cells). Supports rapid pathogen identification, hyperspectral image classification and image-spectra fusion. About 0.7 GB; load with datasets.load_dataset. Licensed CC BY 4.0 by the authors; cite the Foods paper.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("food-ai-nexus/salmonella-serovar-hyperspectral")
print(ds)
```

## Data structure

File types in sampled files: PNG, Parquet

Example file: `spectra/test.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/8abf6e36-996d-537b-ab84-541d175ee308
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/8abf6e36-996d-537b-ab84-541d175ee308
- Over MCP: `get_schema_card` with id `8abf6e36-996d-537b-ab84-541d175ee308` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Health & Biomedical datasets](https://scigantic.com/topics/health-and-biomedical)
- [Spectroscopy datasets](https://scigantic.com/topics/spectroscopy)
- [PNG datasets](https://scigantic.com/topics/png)
