Title :
How robust is the SVM wound segmentation?
Author :
Marina Kolesnik;Ales Fexa
Author_Institution :
Fraunhofer Institute for Applied Information Technology, Schloss Birlinghoven, 53604 Sankt Augustin, GERMANY. Tel. +49-2241 14 3421, Fax: +49-2241 14 1506, E-mail: marina.kolesnik@fit.fraunhofer.de
fDate :
6/1/2006 12:00:00 AM
Abstract :
This paper investigates the robustness of automatic wound segmentation. The work builds upon an automatic segmentation procedure by the support vector machine (SVM)-classifier presented in [M. Kolesnik et al. (2004), (2005)]. Here we extend the procedure by incorporating textural features and the deformable snake adjustment to refine SVM-generated wound boundary. The robustness of SVM-based segmentation is tested against different feature spaces using a long sample of training images featuring a broad variety of wounds´ appearance. Recommendations drawn from these experiments provide a useful guideline for the development of a software support system for the visual monitoring of chronic wounds in wound care units
Keywords :
"Robustness","Support vector machines","Wounds","Image segmentation","Image edge detection","Support vector machine classification","Image sampling","Histograms","Color","Skin"
Conference_Titel :
Signal Processing Symposium, 2006. NORSIG 2006. Proceedings of the 7th Nordic
Print_ISBN :
1-4244-0412-6
DOI :
10.1109/NORSIG.2006.275274
