A Systematic Evaluation of Photometric Data Augmentation Combinations in Medical Object Detection
Karadeniz Fen Bilimleri Dergisi · 26.03.2026 · 16 (2) · 572-591
DOI: 10.31466/kfbd.1870662 ↗Kurz gefasst
Fachartikel in der Zeitschrift Karadeniz Fen Bilimleri Dergisi, online erschienen am 26.03.2026. Verfasst von Onur Erdem Korkmaz. Die Arbeit nennt 31 Literaturangaben. Gefördert von: No.
Abstract (Originalsprache)
This study examines how different data augmentation strategies influence medical object detection performance on the Kvasir-SEG dataset by using Faster R-CNN X101-FPN and YOLOv7 as benchmark models. Augmentation is widely used to improve robustness in image classification. However, systematic analyses in object detection are still limited because bounding-box integrity must be preserved during every geometric transformation step. In this work, eight photometric augmentation techniques (Hue, Noise, Saturation, Grayscale, Blur, Brightness, Contrast, and Cutout) were applied independently and in multi-level combinations. Each augmentation was tested in single, double, triple, and full pipelines. Model performance was evaluated through mean Average Precision (mAP) using the COCO evaluation standard. The results show that color-based augmentations improve detection accuracy more than distortion-based augmentations in polyp detection tasks. The results also show that excessive augmentation depth slows model convergence and prevents accuracy gains. This study provides a structured analysis of augmentation depth and diversity on a medical object detection dataset and offers clear guidance for designing effective augmentation pipelines for medical object detection.
Förderung
- No
Zitieren
APA
Korkmaz, O. E. (2026). A Systematic Evaluation of Photometric Data Augmentation Combinations in Medical Object Detection. Karadeniz Fen Bilimleri Dergisi, 16(2), 572-591. https://doi.org/10.31466/kfbd.1870662
Vancouver
Korkmaz OE. A Systematic Evaluation of Photometric Data Augmentation Combinations in Medical Object Detection. Karadeniz Fen Bilimleri Dergisi. 2026;16(2):572-591. doi:10.31466/kfbd.1870662
BibTeX
@article{Korkmaz2026,
author = {Korkmaz, Onur Erdem},
title = {A Systematic Evaluation of Photometric Data Augmentation Combinations in Medical Object Detection},
journal = {Karadeniz Fen Bilimleri Dergisi},
year = {2026},
volume = {16},
number = {2},
pages = {572--591},
doi = {10.31466/kfbd.1870662}
}
EUVIMED