Title :
Steganalysis of LSB based image steganography using spatial and frequency domain features
Author :
Malekmohamadi, Hossein ; Ghaemmaghami, Shahrokh
Author_Institution :
Sharif Univ. of Technol., Tehran, Iran
fDate :
June 28 2009-July 3 2009
Abstract :
In this paper, we propose a method for steganalysis of grayscale images using both spatial and Gabor features. The basis of our work is to use Gabor filter coefficients and statistics of the graylevel co-occurrence matrix of images to train a support vector machine. We show that this feature set works well in steganalysis of grayscale images steganographied by LSB matching and S-tools.
Keywords :
Gabor filters; feature extraction; image coding; image matching; learning (artificial intelligence); matrix algebra; statistical analysis; steganography; support vector machines; Gabor feature extraction; Gabor filter coefficient; LSB image matching; LSB-based image steganography; S-tools; frequency-domain feature extraction; graylevel co-occurrence matrix statistics; grayscale image steganalysis; spatial-domain feature extraction; support vector machine training; Discrete Fourier transforms; Discrete cosine transforms; Discrete wavelet transforms; Feature extraction; Frequency domain analysis; Gabor filters; Gray-scale; Higher order statistics; Steganography; Support vector machines; Gabor filters; Gray-level co-occurrence matrix; LSB matching; S-tools; Steganalysis; Support vector machine;
Conference_Titel :
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location :
New York, NY
Print_ISBN :
978-1-4244-4290-4
Electronic_ISBN :
1945-7871
DOI :
10.1109/ICME.2009.5202858
