Discriminative Subtree Selection for NBI Endoscopic Image Labeling

Abstract : In this paper, we propose a novel method for image labeling of colorectal Narrow Band Imaging (NBI) endoscopic images based on a tree of shapes. Labeling results could be obtained by simply classifying histogram features of all nodes in a tree of shapes, however, satisfactory results are difficult to obtain because histogram features of small nodes are not enough discriminative. To obtain discriminative subtrees, we propose a method that optimally selects discriminative subtrees. We model an objective function that includes the parameters of a classifier and a threshold to select subtrees. Then labeling is done by mapping the classification results of nodes of the subtrees to those corresponding image regions. Experimental results on a dataset of 63 NBI endoscopic images show that the proposed method performs qualitatively and quantitatively much better than existing methods.
Type de document :
Communication dans un congrès
ACCV2016 workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis, Nov 2016, Taipei, Taiwan. ACCV2016 workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis, 26, pp.610 - 624, 2017, 〈10.1007/978-3-319-54427-4_44〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01572264
Contributeur : Tsubasa Hirakawa <>
Soumis le : dimanche 6 août 2017 - 08:13:25
Dernière modification le : mardi 8 août 2017 - 08:45:51

Fichier

W18_07.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Tsubasa Hirakawa, Toru Tamaki, Takio Kurita, Bisser Raytchev, Kazufumi Kaneda, et al.. Discriminative Subtree Selection for NBI Endoscopic Image Labeling. ACCV2016 workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis, Nov 2016, Taipei, Taiwan. ACCV2016 workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis, 26, pp.610 - 624, 2017, 〈10.1007/978-3-319-54427-4_44〉. 〈hal-01572264〉

Partager

Métriques

Consultations de la notice

75

Téléchargements de fichiers

24