LAUSR

Visual inspection is an important process conducted as an initial diagnostic step in medical examinations. It is assumed that the gaze movements of an orthodontist (expert) differ from those of a layperson. In this study, to examine whether the degree of proficiency in conducting a visual examination can be estimated from gaze movement, we conducted a gaze measurement experiment in which facial images (frontal and lateral images of three patients) were viewed by ten experts and ten laypersons. The performance in discriminating whether a subject was an expert or layperson exhibited a certain improvement when applying an aggregation method for the gaze data, that is, the grid gaze frequency and AOI gaze frequency. We examined whether proficiency levels could be determined using machine learning techniques. The results demonstrated that our method distinguished experts and laypersons relatively effectively using gaze frequency based on the grid and area of interest set by an expert for each face part.