Blood vessel enhancement via multi-dictionary and sparse coding: Application to retinal vessel enhancing - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Neurocomputing Année : 2016

Blood vessel enhancement via multi-dictionary and sparse coding: Application to retinal vessel enhancing

Résumé

Blood vessel images can provide considerable information of many diseases, which are widely used by ophthalmologists for disease diagnosis and surgical planning. In this paper, we propose a novel method for the blood Vessel Enhancement via Multi-dictionary and Sparse Coding (VE-MSC). In the proposed method, two dictionaries are utilized to gain the vascular structures and details, including the Representation Dictionary (RD) generated from the original vascular images and the Enhancement Dictionary (ED) extracted from the corresponding label images. The sparse coding technology is utilized to represent the original target vessel image with RD. After that, the enhanced target vessel image can be reconstructed using the obtained sparse coefficients and ED. The proposed method has been evaluated for the retinal vessel enhancement on the DRIVE and STARE databases. Experimental results indicate that the proposed method can not only effectively improve the image contrast but also enhance the retinal vascular structures and details.
Fichier principal
Vignette du fichier
Blood vessel enhancement via multi-dictionary.pdf (1.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01331415 , version 1 (13-06-2016)

Identifiants

Citer

Bin Chen, Yang Chen, Zhuhong Shao, Tong Tong, Limin Luo. Blood vessel enhancement via multi-dictionary and sparse coding: Application to retinal vessel enhancing. Neurocomputing, 2016, ⟨10.1016/j.neucom.2016.03.012⟩. ⟨hal-01331415⟩
176 Consultations
228 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More