Skip to Main content Skip to Navigation
New interface
Conference papers

Advantages of Using Feature Selection Techniques on Steganalysis Schemes

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.
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Patrick Bas Connect in order to contact the contributor
Submitted on : Wednesday, August 8, 2007 - 2:50:46 PM
Last modification on : Tuesday, October 19, 2021 - 11:22:39 PM
Long-term archiving on: : Friday, April 9, 2010 - 12:30:33 AM


Files produced by the author(s)


  • HAL Id : hal-00166695, version 1


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⟩



Record views


Files downloads