This thesis deals with the automatic segmentation of corneal endothelium images. The aim is to develop algorithms for an automatic analysis of corneal images and the estimation of some clinical parameters. On a set of 30 images of endothelium, acquired through a specular microscopy, three particular features have been highlighted using spatial filtering. The filtered images have been analyzed using the ROC curve to evaluate the filters' goodness and to establish the best images of the set

Estrazione di caratteristiche topologiche in immagini di endotelio corneale

Cibin, Federica
2013/2014

Abstract

This thesis deals with the automatic segmentation of corneal endothelium images. The aim is to develop algorithms for an automatic analysis of corneal images and the estimation of some clinical parameters. On a set of 30 images of endothelium, acquired through a specular microscopy, three particular features have been highlighted using spatial filtering. The filtered images have been analyzed using the ROC curve to evaluate the filters' goodness and to establish the best images of the set
2013-07-25
endotelio, cornea
File in questo prodotto:
File Dimensione Formato  
testo_tesi.pdf

accesso aperto

Dimensione 2.56 MB
Formato Adobe PDF
2.56 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/20.500.12608/17160