A system for the computerized analysis of images obtained from ELM has been
developed to enhance the early recognition of malignant melanoma, As an in
itial step, the binary mask of the skin lesion is determined by several bas
ic segmentation algorithms together with a fusion strategy, A set of featur
es containing shape and radiometric features as well as local and global pa
rameters is calculated to describe the malignancy of a lesion, Significant
features are then selected from this set by application of statistical feat
ure subset selection methods. The final kNN classification delivers a sensi
tivity of 87% with a specificity of 92%.