Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images

Lahmiri, Salim et Boukadoum, Mounir (2013). « Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images ». Journal of Medical Engineering, 2013, pp. 1-13.

Fichier(s) associé(s) à ce document :

Prévisualisation	PDF Télécharger (3MB)

Résumé

A new methodology for automatic feature extraction from biomedical images and subsequent classification is presented. The approach exploits the spatial orientation of high-frequency textural features of the processed image as determined by a two-step process. First, the two-dimensional discrete wavelet transform(DWT) is applied to obtain the HH high-frequency subband image. Then, a Gabor filter bank is applied to the latter at different frequencies and spatial orientations to obtain new Gabor-filtered image whose entropy and uniformity are computed. Finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier. The approach was validated on mammograms, retina, and brain magnetic resonance (MR) images.The obtained classification accuracies show better performance in comparison to common approaches that use only the DWT or Gabor filter banks for feature extraction.

Type:	Article de revue scientifique
Mots-clés ou Sujets:	biomedical image, classification, Gabor-filtered image, brain magnetic resonance
Unité d'appartenance:	Faculté des sciences > Département d'informatique
Déposé par:	A. Mounir Boukadoum
Date de dépôt:	10 mai 2016 13:09
Dernière modification:	30 mai 2016 14:47
Adresse URL :	http://archipel.uqam.ca/id/eprint/8436

Modifier les métadonnées (propriétaire du document)

Statistiques