CornHub: Instance-Segmentation Dataset

🌽 CornHub: Instance-Segmentation Dataset of Corn Cobs

Version: 1.0.0  Date: 2025-05-18  License: CC BY 4.0Author: Sebastian Borukało  

📦 Description

CornHub is an instance-segmentation dataset of corn cobs in real field conditions. It contains 304 high-resolution RGB images in three variants:

- FULL (2432×2432 px)  - LITE (1024×1024 px)  - ULTRALITE (512×512 px)  

Captured at varying distances (close-up and wide-angle), lighting conditions (sunny, overcast), and viewpoints, each corn cob is annotated as its own grayscale mask (single channel):

- 0 = background  - 1, 2, 3… = individual corn cob instances  

Images and masks are provided in PNG format.

Use CornHub to train and evaluate instance-segmentation models in agriculture, field robotics, and computer vision research.

DataSet view:

Version
Filename
Resolution

Full
CornHub_FULL_2432.zip
2432×2432 px

Lite
CornHub_LITE_1024.zip
1024×1024 px

Ultra-Lite
CornHub_ULTRALITE_512.zip
512×512 px

📂 Download Options

Available on:

- Kaggle:                    https://www.kaggle.com/datasets/ciapserr/cornhub-instance-segmentation-dataset - Zenodo:                   https://doi.org/10.5281/zenodo.15453713- PapersWithCode:    https://paperswithcode.com/dataset/cornhub 

🤝 Credits

This dataset is free to use and you can use it in any project or paper, however I would be glad if you would cite me and give credit - as it is stated in the license.

CornHub: Instance-Segmentation Dataset of Corn Cobs Author: Sebastian Borukało 

DOI: https://doi.org/10.5281/zenodo.15453713DOI: 10.5281/zenodo.15453713