Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications
Abstract
This work presents a new public dataset for cell detection in bright-field microscopy images annotated with Oriented Bounding Boxes (OBBs) named Oriented Cell Dataset (OCD). Our dataset also contains a subset of images with five independent expert annotations which allows inter-annotation analysis to determine a suitable IoU acceptance threshold for evaluating cell detectors. We show that OBBs and a derived representation Oriented Ellipses (OEs) provide a more accurate shape representation than standard Horizontal Bounding Boxes (HBBs) with a slight overhead of one extra click in the annotation process. We benchmarked OCD using 14 state-of-the-art oriented object detectors and explored two main problems in cancer biology: cell confluence and polarity determination. Our code and dataset are available at https://github.com/LucasKirsten/Deep-Cell-Tracking-EBB.
Cite
Text
Kirsten et al. "Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications." Winter Conference on Applications of Computer Vision, 2025.Markdown
[Kirsten et al. "Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications." Winter Conference on Applications of Computer Vision, 2025.](https://mlanthology.org/wacv/2025/kirsten2025wacv-oriented/)BibTeX
@inproceedings{kirsten2025wacv-oriented,
title = {{Oriented Cell Dataset: A Dataset and Benchmark for Oriented Cell Detection and Applications}},
author = {Kirsten, Lucas and Angonezi, Angelo and Marques, Jose and Oliveira, Fernanda and Faccioni, Juliano and Cassel, Camila and de Sousa, Débora and Vedovatto, Samlai and Lenz, Guido and Jung, Claudio},
booktitle = {Winter Conference on Applications of Computer Vision},
year = {2025},
pages = {3996-4005},
url = {https://mlanthology.org/wacv/2025/kirsten2025wacv-oriented/}
}