[PDF]

Medical image processing - bruises


Benjamin Watson

06/09/2024

Supervised by Paul L Rosin; Moderated by Yipeng Qin

This project will use a set of images of bruises that have been marked with circles to roughly outline their position. The project aim is to develop automatic detection of bruises using a combination of image processing and machine learning techniques.

Here are a few relevant technical papers relating to image-based bruise analysis:

Li, Cheng-Ru, et al. "Quantifying the color changes in bruised skin using a color-calibrated imaging system." 2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA). IEEE, 2020. Tirado, Jhonatan, and David Mauricio. "Bruise dating using deep learning." Journal of forensic sciences 66.1 (2021): 336-346. Majumdar, Puspita, et al. "On detecting domestic abuse via faces." Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018


Final Report (06/09/2024) [Zip Archive]

Publication Form