Communications of the ACM
Smarter Video Searching and Indexing
A new framework under development would allow Internet users to use images to search for videos.
Credit: Techinasia.com
A new framework that would enable Internet users to search for videos using images rather than text could lead to smarter searching and indexing.
University of Lincoln researchers are working to create the framework, which relies on finding similarities between videos using tiny frames instead of using full-size video frames. The tiny frames are extracted from compressed video in real time and are able to fully represent video content, without wasting more time in decompressing the video to perform complex computer algorithms.
"I want to discover the semantic similarity between videos using the content only," says Lincoln Ph.D. student Saddam Bekhet. "I adapted some new techniques and found that tiny representative frames could be used to discover similarities."
The research builds on work to provide a framework for automated video analysis and annotation by the university's Digital Contents Analysis, Production and Interaction Group.
"The next stage is to build an effective framework," Bekhet says.
From University of Lincoln
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found