Nystagmus is a periodic, involuntary movement of eyes examined for diagnosis of various vestibular diseases such as benign paroxysmal positional vertigo, the most frequent vestibular disorder. In recent years, videonystagmography has been widely used in the examination of nystagmus due to its non-invasive feature. However, identifying and classifying nystagmus still requires professional knowledge and training. To this end, a pupil tracking algorithm was proposed in this paper using convolutional neural networks. U-Net was selected for pupil segmentation, and we constructed the ground truth of a new dataset for the training procedure. An additional tracking algorithm was designed to prevent false outputs of the U-Net model. Results show that the proposed pupil tracking algorithm scored higher performance than conventional methods.
|