Integrating machine learning and features extraction for practical reliable color images steganalysis classification.

Steganalysis is a known practice to detect hidden secrecy within covered e-media. Researches claimed obscured detection attainability via features extraction, as for perceiving concealed data within images. This paper verifies practicality of the claim by testing investigation of a steganalysis system that depicts the existence of hidden data focused on statistical features of color images using artificial neural network techniques. The proposed system is built to work for blind image steganalysis representing common security as looked for the most. The work experimentations adopted common steganography techniques to create the stego images for our intended steganalysis challenging practicality evaluation. The study involved machine learning radial basis function and naïve bayes classifiers to sort the remarks improving discovery accuracy. From the investigational results, the proposed system exemplified reliability and enhancements in the recognition rate for most steganographic methods showing attractive annotations. Further, the correlation features displayed increased correctness showing reliable convalescing practicality overcoming many previous steganalysis defects. [ABSTRACT FROM AUTHOR]