Home // CONTENT 2017, The Ninth International Conference on Creative Content Technologies // View article

Video Fingerprinting by Common Features in a Scene

Authors:
Jongweon Kim
Sungjun Han
Yongbae Kim
Jungjae Lee

Keywords: video identification; common feature; scene; scale invariant feature transform

Abstract:
Video fingerprinting is an important aspect in the copyright protection field as digital environment enables the copyright infringement to get easier and easier. There are many video contents on the Internet. Copyright owners want to identify contents on the net and to block infringed contents. The video content is invaluable because the owners invested huge amount of money when they made the movie. In this paper, we propose an efficient algorithm to identify video contents even if we only have a video frame. The algorithm divides a video content into scenes and then extracts common feat from a scene. The feature database contains only a set of features per scene. That means the proposed algorithm optimizes the feature database and the time it takes to compare the features. Also, this algorithm can identify a video using only a frame of the video.

Pages: 14 to 17

Copyright: Copyright (c) IARIA, 2017

Publication date: February 19, 2017

Published in: conference

ISSN: 2308-4162

ISBN: 978-1-61208-533-3

Location: Athens, Greece

Dates: from February 19, 2017 to February 23, 2017