Date of Award

5-2015

Document Type

Thesis

Degree Name

Master of Science (MS)

Legacy Department

Electrical Engineering

Committee Member

Dr. John Gowdy

Committee Member

Dr. Robert Schalkoff

Committee Member

Dr. Carl Baum

Abstract

Lip reading is the recognition of spoken words from the visual information of lips. It has been of considerable interest in the Computer Vision and Speech Recognition communities to automate this process using computer algorithms. In this thesis, we have developed a novel method involving describing visual features using fixed length descriptors called Histogram of Oriented Displacements to which we apply Support Vector Machines for recognition of spoken words. Using this method on the CUAVE database we have achieved a recognition rate of 81%.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.