ATUMUNMOON/Egg-Instance-Segmentation

---
license: cc-by-nc-4.0
---

# Egg Instance Segmentation
This is a dataset with images of eggs that can be used for egg segmentation purposes. The dataset is divided into two classes: white-egg and brown-egg. This is YOLO format dataset.
The training and validation images are in the train and val folders respectively.
The polygon annotations specifying the exact boundaries of eggs are in the related labels folders.

## Goal
This dataset is collected to train a YOLO model to segment different types of eggs (right now the white and brown eggs data are available).
A model is trained on this dataset to segments eggs in images.
This model can also be used for estimating the sizes of the eggs for quality assessment or sorting purposes in factories.

## Sample Images
As an example, the following image is from the dataset. The image is annotated with polygons around the eggs.
<p align="center">
<img width="800" height="800" src="./data/images/train/sample22.jpg" alt="Egg sample">
</p>

## How to Use
In order to use the dataset for training purposes, one can download the dataset at first and then change the `path`
in the `data.yaml` file to the absolute path where the data is stored. The `data.yaml` file is in the `data` folder.

## License
This dataset is licensed under the Attribution–NonCommercial 4.0 International License (CC BY-NC 4.0).