Please use this identifier to cite or link to this item:
Title: Feature selection applied to human tear film classification
Authors: Villaverde,DG
Beatriz Remeseiro López
Issue Date: 2014
Abstract: Dry eye is a common disease which affects a large portion of the population and harms their routine activities. Its diagnosis and monitoring require a battery of tests, each designed for different aspects. One of these clinical tests measures the quality of the tear film and is based on its appearance, which can be observed using the Doane interferometer. The manual process done by experts consists of classifying the interferometry images into one of the five categories considered. The variability existing in these images makes necessary the use of an automatic system for supporting dry eye diagnosis. In this research, a methodology to perform this classification automatically is presented. This methodology includes a color and texture analysis of the images, and also the use of feature selection methods to reduce image processing time. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors lower than 9%. Additionally, it saves time for experts and can work in real-time for clinical purposes.
metadata.dc.type: conferenceObject
Appears in Collections:Non INESC TEC publications - Indexed Articles in Conferences

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.25 MBAdobe PDFThumbnail
View/Open Request a copy

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.