Efficient and effective JPEG compressed domain image retrieval

DOI

10.2991/icmt-13.2013.4How to use a DOI?

Keywords

content-based image retrieval, image databases, compressed domain retrieval, JPEG, discrete cosine transform

Abstract

Content-based image retrieval(CBIR) has been an active research area for more than two decades. However, while almost all images are stored in compressed form, the vast majority of CBIR algorithms operate in the (uncompressed) pixel do-main. This not only leads to a computational overhead for feature calculation, it can also be demonstrated that image compression has a negative effect on retrieval accu-racy, especially at extreme compression rates. In this paper,we present efficient and effective CBIR techniques that operate directly in the compressed domain, hence not requiring full decompression for feature extraction. In particular, we focus on the JPEG domain since most images are compressed using JPEG. We show how CBIR features can be extracted from DCT coefficients, from differentially coded DC data, and from tuned information contained in the JPEG headers.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Schaefer Gerald
PY  - 2013/11
DA  - 2013/11
TI  - Efficient and effective JPEG compressed domain image retrieval
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 27
EP  - 31
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.4
DO  - 10.2991/icmt-13.2013.4
ID  - Gerald2013/11
ER  -