English
Español
DOI:
https://doi.org/10.32870/recibe.v14i3.449Keywords:
EnglishAbstract
Chronic wound diagnosis using machine learning is hindered by the lighting and shadows in the captured images. Therefore, this study evaluates the impact of different color spaces on wound segmentation using a U-Net. Results show that the YDbDr color space outperforms RGB.References
Cassidy, B., McBride, C., Kendrick, C., Reeves, N. D., Pappachan, J. M., Fernandez, C. J., ... & Yap, M. H. (2025). An enhanced harmonic densely connected hybrid transformer network architecture for chronic wound segmentation utilising multi-colour space tensor merging. Computers in Biology and Medicine, 192, 110172.
Gowda, S. N., & Yuan, C. (2018, December). ColorNet: Investigating the importance of color spaces for image classification. In Asian conference on computer vision (pp. 581-596). Cham: Springer International Publishing.
Iakubovskii, P. (2019). Segmentation Models [Computer software]. GitHub. https://github.com/qubvel/segmentation_models
Jocher, G., & Qiu, J. (2024). Ultralytics YOLO11 (Version 11.0.0) [Computer software]. GitHub. https://github.com/ultralytics/ultralytics
Kręcichwost, M., Czajkowska, J., Wijata, A., Juszczyk, J., Pyciński, B., Biesok, M., ... & Pietka, E. (2021). Chronic wounds multimodal image database. Computerized Medical Imaging and Graphics, 88, 101844.
Marijanović, D., & Filko, D. (2020). A systematic overview of recent methods for non-contact chronic wound analysis. Applied Sciences, 10(21), 7613.
