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.
|Commitee:||Ary, James, Haggerty, Kevin|
|School:||California State University, Long Beach|
|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|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be