Award Date

1-1-2007

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Evangelos A. Yfantis

Number of Pages

71

Abstract

Automatic video analysis tools have dramatically increased in importance as the Internet video revolution has blossomed. This thesis presents an approach for automatic comparison of videos based on the inherent content. Also, an approach for creating groups (or clusters) of similar videos from a large video database is given; First, methods simplifying and summarizing the content of videos will be presented. Such methods include shot boundary detection and key frame feature extraction; Next, a comparison of different distance measures between videos will be given. These distance measures will be used to construct video clusters, and results will be compared.

Keywords

Based; Classification; Comparison; Content; Video

Controlled Subject

Computer science

File Format

pdf

File Size

1484.8 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

https://doi.org/10.25669/cxoa-lev1


Share

COinS