Translator Disclaimer
Paper
12 May 2004 Classification of burn wounds using support vector machines
Author Affiliations +
Abstract
The purpose of this work is to improve a previous method developed by the authors for the classification of burn wounds into their depths. The inputs of the system are color and texture information, as these are the characteristics observed by physicians in order to give a diagnosis. Our previous work consisted in segmenting the burn wound from the rest of the image and classifying the burn into its depth. In this paper we focus on the classification problem only. We already proposed to use a Fuzzy-ARTMAP neural network (NN). However, we may take advantage of new powerful classification tools such as Support Vector Machines (SVM). We apply the five-folded cross validation scheme to divide the database into training and validating sets. Then, we apply a feature selection method for each classifier, which will give us the set of features that yields the smallest classification error for each classifier. Features used to classify are first-order statistical parameters extracted from the L*, u* and v* color components of the image. The feature selection algorithms used are the Sequential Forward Selection (SFS) and the Sequential Backward Selection (SBS) methods. As data of the problem faced here are not linearly separable, the SVM was trained using some different kernels. The validating process shows that the SVM method, when using a Gaussian kernel of variance 1, outperforms classification results obtained with the rest of the classifiers, yielding an error classification rate of 0.7% whereas the Fuzzy-ARTMAP NN attained 1.6 %.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Begona Acha, Carmen Serrano, Sergio Palencia, and Juan Jose Murillo "Classification of burn wounds using support vector machines", Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); https://doi.org/10.1117/12.535491
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
Back to Top