 |
 |
Communication dans un congrès
Classification of SD-OCT Volumes with LBP: Application to DME Detection
Abstract : This paper addresses the problem of automatic classification of Spectral Domain OCT (SD-OCT) data for automatic identification of patients with Diabetic Macular Edema (DME) versus normal subjects. Our method is based on Local Binary Patterns (LBP) features to describe the texture of Optical Coherence Tomography (OCT) images and we compare different LBP features extraction approaches to compute a single signature for the whole OCT volume. Experimental results with two datasets of respectively 32 and 30 OCT volumes show that regardless of using low or high level representations, features derived from LBP texture have highly discriminative power. Moreover, the experiments show that the proposed method achieves better classification performances than other recent published works.
Littérature citée [19 références]
https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01235888
Contributeur : Guillaume Lemaitre <>
Soumis le : lundi 30 novembre 2015 - 20:48:52
Dernière modification le : lundi 30 mars 2020 - 08:41:44
Document(s) archivé(s) le : samedi 29 avril 2017 - 00:28:02
Contributeur : Guillaume Lemaitre <>
Soumis le : lundi 30 novembre 2015 - 20:48:52
Dernière modification le : lundi 30 mars 2020 - 08:41:44
Document(s) archivé(s) le : samedi 29 avril 2017 - 00:28:02
Fichier
master(2).pdf
Fichiers produits par l'(les) auteur(s)
