Back to search
Clemson University
Visual Speech Recognition using Histogram of Oriented Displacements
Abstract
dc:description.abstractLip 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%.
Degree
thesis:*- Name thesis:degree_name
- Master of Science (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kumaravel, Sujeeth Selvam
- Contributors dc:contributor
-
- Dr. John Gowdy
- Dr. Robert Schalkoff
- Dr. Carl Baum
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://open.clemson.edu/all_theses/2112