A video based eye detection system for bipolar disorder diagnosis

In this study, a video-based pupil detection system and neuropsychological tests for the system are developed for diagnosis of neuropsychiatric disorders. An Active Contour Snake model is proposed to extract the position (x,y) and radius (r) information of pupils in video sequences. The test in this research is applied to two different groups, namely; bipolar disorder group and control (nonbipolar) group. In order to conduct the test application, a number of selected words are shown to the people on a computer screen. While they are reading these words, the pupil detection system is used to determine the coordinates of the screen where the eye looking at and how long it takes to look at these words simultaneously. This information acquired from these tests is used as a feature vector in Support Vector Machines (SVM) for classifying the bipolar disorder and control groups.