F
Fernando Vilariño
Researcher at Autonomous University of Barcelona
Publications - 51
Citations - 2177
Fernando Vilariño is an academic researcher from Autonomous University of Barcelona. The author has contributed to research in topics: Segmentation & Object detection. The author has an hindex of 18, co-authored 51 publications receiving 1515 citations. Previous affiliations of Fernando Vilariño include Given Imaging Ltd. & Trinity College, Dublin.
Papers
More filters
Journal ArticleDOI
WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians
Jorge Bernal,F. Javier Sánchez,Gloria Fernández-Esparrach,Debora Gil,Cristina Rodríguez,Fernando Vilariño +5 more
TL;DR: This paper introduces a novel polyp localization method for colonoscopy videos based on a model of appearance for polyps which defines polyp boundaries in terms of valley information and proves that this method outperforms state-of-the-art computational saliency results.
Journal ArticleDOI
Towards automatic polyp detection with a polyp appearance model
TL;DR: The method consists of three stages: region segmentation, region description and region classification, which guarantees that if a polyp is present in the image, it will be exclusively and totally contained in a single region.
Book ChapterDOI
Texture-Based Polyp Detection in Colonoscopy
TL;DR: This paper applies four methods of texture feature extraction based on Grey-Level-Co-occurence and Local-Binary-Patterns to classify polyps in colonoscopy images obtained with an area under the ROC-curve of up to 0.96.
Proceedings ArticleDOI
Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy
TL;DR: A method for the rejection of the parts of the video resulting not valid for analysis by means of automatic detection of intestinal juices is proposed, which achieves a significant reduction in visualization time, with no relevant loss of valid frames.
Journal ArticleDOI
Predictive (un)distortion model and 3-D reconstruction by biplane snakes
TL;DR: The proposed methods decrease up to 88% the reconstruction error obtained when geometrical distortion effects are ignored, and improve the biplane snake behavior when dealing with wavy vessels, by means of using generalized gradient vector flow.