Unimore logo AImageLab

Using the Topological Tree for skin lesion structure description

Abstract: In this work we describe the Topological Tree (TT) as a knowledge representation method that relates some important visual and spatial features of image regions, namely the color similarity, the inclusion and the spatial adjacency. Starting from color-based region segmentation of an image into disjoint regions, their spatial relationships can be devised and described with graph-based methods. We are interested in the region’s propriety “to be included into” (in the sense of “surrounded by”) another region. This property could be very useful in biomedical imaging and in particular in the diagnosis of skin melanoma. The TT can be constructed after segmentation, by computing the spatial relationships of regions or can be generated directly during the segmentation: to this aim we present a novel recursive fuzzy c-means (FCM) clustering algorithm based on the PCA of the color space. In the paper, in addition to the TT definition and the construction algorithm description, some results are presented and discussed.


Cucchiara, Rita; Grana, Costantino "Using the Topological Tree for skin lesion structure description" Knowledge-based Intelligent Information Engineering Systems & Allied Technologies, Podere d'Ombriano, Crema, Italy, pp. 166 -170 , Sep 16-18, 2002

 not available

Paper download:

  • Author version: