Research Article
Burn Image Classification Using One-Class Support Vector Machine
@INPROCEEDINGS{10.1007/978-3-319-29236-6_23, author={Hai Tran and Triet Le and Thai Le and Thuy Nguyen}, title={Burn Image Classification Using One-Class Support Vector Machine}, proceedings={Context-Aware Systems and Applications. 4th International Conference, ICCASA 2015, Vung Tau, Vietnam, November 26-27, 2015, Revised Selected Papers}, proceedings_a={ICCASA}, year={2016}, month={4}, keywords={Burn image classification Support Vector Machine (SVM) Multi- color channels}, doi={10.1007/978-3-319-29236-6_23} }- Hai Tran
Triet Le
Thai Le
Thuy Nguyen
Year: 2016
Burn Image Classification Using One-Class Support Vector Machine
ICCASA
Springer
DOI: 10.1007/978-3-319-29236-6_23
Abstract
Burn image classification is critical and attempted problems in medical image processing. This paper proposes the image classification model applied for burn images. The proposal model use one-class Support Vector Machine with color features for burn image classification. The aim of this model is to identify automatically the degrees of burns in three levels: II, III, and IV. The skin burn color images are used as inputs to the model. Then, we apply the multi-color channels extraction and binary based on adaptive threshold for Support Vector Machine classifier. The proposal model uses One- class Support Vector Machine instead of kernel Support Vector Machine because of unbalance degrees of burns images database. The experiments are conducted with the real-life image provided by Cho Ray hospital with the precision 77.78 %. The validation process shows that our main results and the feasibility of our proposal model are stated (Fig. 1) .
