This report discusses the accuracy of blink detection in eye tracking, using machine learningalgorithms. Blink detection is used in a wide variety of medicinal and psychological applica-tions such as a controller for motor impaired individuals. Image classification has recentlybeen used in eye tracking and blink detection applications. The blink detection is appliedon data captured from the Pupil Invisible head-mounted eye tracker. The aim is that givenan image, the classifier can accurately determine the state of which the eye is in, blink oropen.These tests will be conducted on two SVM (support vector machine) models using differenttraining data, one trained on data from controlled environments, the other model also trainedon uncontrolled environments. For this project, data was captured in infrared disturbedenvironments to see how it affects the models performance. These models are evaluatedaccording to their accuracy using multiple different metrics. This rapport will discuss theresults of both classifiers in both tests, in addition to describing training methodology withan aim to find if blink detection is viable in infrared disturbed environments.