MPEG-7 visual descriptors selection for burn characterization by multidimensional scaling match

This is the authors' abstract. We don't add key points for this paper.

This paper presents a new approach towards the selection of color image features to be used in the classification of burn wounds. The features are selected such that they generate similarity matrices and multidimensional scaling (MDS) plots that match the similarity matrix and the MDS-plot resulting from a subjective visual burn area similarity test performed by trained surgeons. We show that standard MPEG-7 visual descriptors that combine color and texture are good candidates for the task of burn wound grading.