Advantages of Using Feature Selection Techniques on Steganalysis Schemes - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

Advantages of Using Feature Selection Techniques on Steganalysis Schemes

(1) , (2) , (3) , (1) , (1)
1
2
3

Abstract

Steganalysis consists in classifying documents as steganogra- phied or genuine. This paper presents a methodology for steganalysis based on a set of 193 features with two main goals: determine a suffi- cient number of images for effective training of a classifier in the obtained high-dimensional space, and use feature selection to select most relevant features for the desired classification. Dimensionality reduction is per- formed using a forward selection and reduces the original 193 features set by a factor of 13, with overall same performance.
Fichier principal
Vignette du fichier
Publication87.pdf (282.98 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00166695 , version 1 (08-08-2007)

Identifiers

  • HAL Id : hal-00166695 , version 1

Cite

Yoan Miche, Patrick Bas, Christian Jutten, Amaury Lendasse, Olli Simula. Advantages of Using Feature Selection Techniques on Steganalysis Schemes. IWANN 2007 - 9th International Work-Conference on Artificial Neural Networks, Jun 2007, San Sebastian, Spain. pp.electronic version. ⟨hal-00166695⟩
125 View
1294 Download

Share

Gmail Facebook Twitter LinkedIn More