Jump to : Download | Abstract | Contact | BibTex reference | EndNote reference |

dvmmPub179

Shih-Fu Chang. Compressed-Domain Content-Based Image and Video Retrieval. In Symposium on Multimedia Communications and Video Coding, Polytechnic University, New York, NY, October 1995.

Download [help]

Download paper: Adobe portable document (pdf)

Copyright notice:This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

In this paper, we focus on automated image retrieval using various types of visual features (including image templates). Specifically, we explore a unique approach which emphasizes the compressed-domain solutions. Given most images and videos stored in the compressed form, it is highly desirable to perform content-based visual retrieval directly in the compressed domain. In other words, extraction of visual features, matching of images and videos, or even manipulations of search results can be implemented using the compressed visual data without decompressing (or sometimes with minimal decoding). The advantage of performing these tasks in the compressed domain is obvious. The computational cost can be greatly reduced compared to the alternative which fully decodes the compressed material and executes the above tasks in the uncompressed domain. Not only that the decoding process is avoided, the amount of data in the compressed domain is also lower than in the uncompressed domain. We have applied the compressed-domain approach to image/video manipulation and compositing [2,11], texture/color-based image query [9], image matching [10], video indexing and editing [6, 25]

Contact

Shih-Fu Chang

BibTex Reference

@InProceedings{dvmmPub179,
   Author = {Chang, Shih-Fu},
   Title = {Compressed-Domain Content-Based Image and Video Retrieval},
   BookTitle = {Symposium on Multimedia Communications and Video Coding},
   Address = {Polytechnic University, New York, NY},
   Month = {October},
   Year = {1995}
}

EndNote Reference [help]

Get EndNote Reference (.ref)

 
bar

For problems or questions regarding this web site contact The Web Master.

This document was translated automatically from BibTEX by bib2html (Copyright 2003 © Eric Marchand, INRIA, Vista Project).