Date of Completion

Spring 5-1-2019

Thesis Advisor(s)

Patrick D. Kumavor

Honors Major

Biomedical Engineering


Artificial Intelligence and Robotics | Bioelectrical and Neuroengineering | Bioimaging and Biomedical Optics | Biological and Chemical Physics | Biomedical Devices and Instrumentation | Diagnosis | Disease Modeling | Equipment and Supplies | Eye Diseases | Graphics and Human Computer Interfaces | International Public Health | Investigative Techniques | Medical Biomathematics and Biometrics | Medical Neurobiology | Musculoskeletal, Neural, and Ocular Physiology | Nervous System | Nervous System Diseases | Neurology | OS and Networks | Other Analytical, Diagnostic and Therapeutic Techniques and Equipment | Other Biomedical Engineering and Bioengineering | Programming Languages and Compilers | Systems and Integrative Engineering | Vision Science


Abnormal ocular motility is a common manifestation of many underlying pathologies particularly those that are neurological. Dynamics of saccades, when the eye rapidly changes its point of fixation, have been characterized for many neurological disorders including concussions, traumatic brain injuries (TBI), and Parkinson’s disease. However, widespread saccade analysis for diagnostic and research purposes requires the recognition of certain eye movement parameters. Key information such as velocity and duration must be determined from data based on a wide set of patients’ characteristics that may range in eye shapes and iris, hair and skin pigmentation [36]. Previous work on saccade analysis has primarily been based on presetting patient information such as location of markers (e.g. pupil, iris, caruncle) before and after a saccade. In this paper, a machine learning approach is applied to determine a saccade’s dynamics by eye structure identification of static images before and after a saccade. Several machine learning and alternative methods are considered for the identification of the pupil and a static component of the eye such as the caruncle. These include circle detection via the Hough Transform. The incorporation of these approaches aims to reduce computational load, increase broader patient detection, and improve compatibility with various device interfaces. In this report, these tools are explored by applying them to smartphone-captured images of the eye after a saccade is induced simultaneously using the smartphone device.