Share Email Print
cover

Journal of Electronic Imaging

Texture descriptors based on adaptive neighborhoods for classification of pigmented skin lesions
Author(s): Victor González-Castro; Johan Debayle; Yanal Wazaefi; Mehdi Rahim; Caroline Gaudy-Marqueste; Jean-Jacques Grob; Bernard Fertil
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Different texture descriptors are proposed for the automatic classification of skin lesions from dermoscopic images. They are based on color texture analysis obtained from (1) color mathematical morphology (MM) and Kohonen self-organizing maps (SOMs) or (2) local binary patterns (LBPs), computed with the use of local adaptive neighborhoods of the image. Neither of these two approaches needs a previous segmentation process. In the first proposed descriptor, the adaptive neighborhoods are used as structuring elements to carry out adaptive MM operations which are further combined by using Kohonen SOM; this has been compared with a nonadaptive version. In the second one, the adaptive neighborhoods enable geometrical feature maps to be defined, from which LBP histograms are computed. This has also been compared with a classical LBP approach. A receiver operating characteristics analysis of the experimental results shows that the adaptive neighborhood-based LBP approach yields the best results. It outperforms the nonadaptive versions of the proposed descriptors and the dermatologists’ visual predictions.

Paper Details

Date Published: 21 September 2015
PDF: 8 pages
J. Electron. Imaging. 24(6) 061104 doi: 10.1117/1.JEI.24.6.061104
Published in: Journal of Electronic Imaging Volume 24, Issue 6
Show Author Affiliations
Victor González-Castro, The Univ. of Edinburgh Medical School (United Kingdom)
Johan Debayle, Ecole Nationale Supérieure des Mines de Saint-Étienne (France)
Yanal Wazaefi, Lab. des Sciences de l'Information et des Systèmes (France)
Mehdi Rahim, Lab. des Sciences de l'Information et des Systèmes (France)
Caroline Gaudy-Marqueste, Hôpital de la Timone (France)
Jean-Jacques Grob, Hôpital de la Timone (France)
Bernard Fertil, Lab. des Sciences de l'Information et des Systèmes (France)


© SPIE. Terms of Use
Back to Top