The tear film lipid layer is heterogeneous among the population. Itsclassification depends on its thickness and can be done using the interference pattern categories proposed by Guillon. The interference phenomena can be characterised as a colour texture pattern, which can be automatically classified into one of these categories. From a photography ofthe eye, a region of interest is detected and its low-level features are extracted, generating a feature vector that describes it, to be finally classifiedin one of the target categories. This paper presents an exhaustive studyabout the problem at hand using different texture analysis methods inthree colour spaces and different machine learning algorithms. All thesemethods and classifiers have been tested on a dataset composed of 105images from healthy subjects and the results have been statistically analysed. As a result, the manual process done by experts can be automatedwith the benefits of being faster and unaffected by subjective factors, withmaximum accuracy over 95%.
展开▼
