Share Email Print

Proceedings Paper

Implementing the projected spatial rich features on a GPU
Author(s): Andrew D. Ker
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The Projected Spatial Rich Model (PSRM) generates powerful steganalysis features, but requires the calculation of tens of thousands of convolutions with image noise residuals. This makes it very slow: the reference implementation takes an impractical 20{30 minutes per 1 megapixel (Mpix) image. We present a case study which first tweaks the definition of the PSRM features, to make them more efficient, and then optimizes an implementation on GPU hardware which exploits their parallelism (whilst avoiding the worst of their sequentiality). Some nonstandard CUDA techniques are used. Even with only a single GPU, the time for feature calculation is reduced by three orders of magnitude, and the detection power is reduced only marginally.

Paper Details

Date Published: 19 February 2014
PDF: 10 pages
Proc. SPIE 9028, Media Watermarking, Security, and Forensics 2014, 90280K (19 February 2014); doi: 10.1117/12.2042473
Show Author Affiliations
Andrew D. Ker, Univ. of Oxford (United Kingdom)

Published in SPIE Proceedings Vol. 9028:
Media Watermarking, Security, and Forensics 2014
Adnan M. Alattar; Nasir D. Memon; Chad D. Heitzenrater, Editor(s)

© SPIE. Terms of Use
Back to Top