PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

DCT-SVM based multi-classification of mouse skin precancerous stages from autofluorescence and diffuse reflectance data
Faiza Abdat, M. Amouronx, Yann Guermeur and Walter Blondel
In: ECBO 2011(2011).


This paper deals with multi-classification of skin precancerous stages based on bimodal AutoFluorescence (AF) spectroscopy and Diffuse Reflectance (DR) spectroscopy. The proposed data processing method is based on Discrete Cosine Transform (DCT) to extract discriminant spectral features and on Support Vector Machine to classify. Results show that DCT gives better results for AF spectra than for DR spectra. This study shows that bimodality and spectral resolution allow an increase in diagnostic accuracy. This accuracy can get as high as 79% when combining the 3 distances for bimodality.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Multimodal Integration
ID Code:7996
Deposited By:Yann Guermeur
Deposited On:17 March 2011