Dissertation/Thesis Abstract

Quantitative Analysis of Strabismus Using Image Processing
by Suriyal, Shorav Singh, M.S., California State University, Long Beach, 2018, 86; 10841398
Abstract (Summary)

A technique to calculate the deviation of an iris along the horizontal and vertical axis is implemented on the images of people’s faces, downloaded from google images, as well as performed on five healthy subjects. Strabismus analysis is a quantitative analysis of finding the deviation of an iris in people with strabismus or crossed eyes.

There are three primary techniques involved in developing this method, each of which will be used in this project: Hough transform, Histogram of oriented gradients, and Haar features. These techniques are widely used and implemented in Matlab 2016b software. The final value of deviation is calculated in pixels and then compared to both eyes to get an estimate of deviation and error calculation in the final result.

This experiment must be performed under a set of conditions which limit the capability of the developed algorithm. This thesis makes three contributions. Firstly, we propose two graphical user interfaces; these interfaces have a live as well as local image processing capability. Secondly, we recommended a bounding box approach to make the face of person align to minimize the error in calculating the vertical deviation. Thirdly, we propose a bottom-up method to find the horizontal and vertical variation in pixels as its measuring unit. Since, in case of a normal eye, this variation will be close to zero, gives us the probability of a person being non-strabismic while a higher value of difference makes a person probable to strabismus.

Indexing (document details)
Advisor: Druzgalski, Christopher
Commitee: Ary, James, Haggerty, Kevin
School: California State University, Long Beach
Department: Electrical Engineering
School Location: United States -- California
Source: MAI 58/02M(E), Masters Abstracts International
Subjects: Engineering, Electrical engineering
Keywords: Computer vision, Crossed eyes, Face and eye detection, Image processing, Machine learning, Strabismus
Publication Number: 10841398
ISBN: 978-0-438-53886-3
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy