Retinal Biomarker discovery requires computer based image analysis with validate algorithms, validation requires ground truth in the form of significant volumes of images annotated by experts. Obtaining annotations sets is laborious. This study aims to generate realistic retinal fundus colour images (phantoms), similar in appearance to a given dataset, and associated with full ground-truth values. This work is mainly focused on the vasculature region and on its relationship with the background
Automatic Generation of Retinal Fundus Image Phantoms: Vascular Regions
De Biasi, Maddalena
2014/2015
Abstract
Retinal Biomarker discovery requires computer based image analysis with validate algorithms, validation requires ground truth in the form of significant volumes of images annotated by experts. Obtaining annotations sets is laborious. This study aims to generate realistic retinal fundus colour images (phantoms), similar in appearance to a given dataset, and associated with full ground-truth values. This work is mainly focused on the vasculature region and on its relationship with the backgroundFile in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
maddalena_de_biasi_tesi.pdf
accesso aperto
Dimensione
1.4 MB
Formato
Adobe PDF
|
1.4 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
Utilizza questo identificativo per citare o creare un link a questo documento:
https://hdl.handle.net/20.500.12608/18563