bloodcelldiff_flipped_data Computer Vision Project
Updated a month ago
In this blood cell detection project, I initially sampled 600 unlabelled images representing key blood cell types: Red Blood Cells (RBC), Platelets (PLT), Neutrophils (NEUT), Lymphocytes (LYMPH), Monocytes (MONO), Eosinophils (EOS), and Basophils (BASO). Each image was manually labelled to create the first fully labelled dataset.
To increase the dataset's robustness and improve model training, I applied several augmentations: horizontal flips, vertical flips, and a combination of horizontal and vertical flips. This data augmentation process expanded the dataset from the original 600 images to 2400 labelled images (600 images × 4 variations).
The original dataset, created by Acevedo et al. (2020), is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). I have made modifications, including manual labeling and augmentation, to adapt the dataset to the specific needs of this project.
Reference: Andrea Acevedo, Anna Merino, Santiago Alférez, Ángel Molina, Laura Boldú, José Rodellar, A dataset of microscopic peripheral blood cell images for development of automatic recognition systems, Data in Brief, Volume 30, 2020, 105474, ISSN 2352-3409, https://doi.org/10.1016/j.dib.2020.105474.
License: CC BY 4.0.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
bloodcelldiff_flipped_data_dataset,
title = { bloodcelldiff_flipped_data Dataset },
type = { Open Source Dataset },
author = { RubenF },
howpublished = { \url{ https://universe.roboflow.com/rubenf/bloodcelldiff_flipped_data } },
url = { https://universe.roboflow.com/rubenf/bloodcelldiff_flipped_data },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2024 },
month = { sep },
note = { visited on 2024-11-05 },
}