Abstract
Many steganalysis methods have been introduced in the literature. These methods were developed to combat specific steganography techniques and to detect specific image formats. However, no single steganalysis method or tool can detect all types of steganography and support all available image formats. This paper proposes a detection system based on the colour gradient co-occurrence matrix (CGCM). Varieties of statistical features were extracted from the CGCM. The system was developed to detect RGB stego images with 24-bit depth. An image-data base was created to test and train the system. The stego images included in the data-base were created using commonly-used steganography method, which is Least Significant Bit (LSB). The size of hidden files plays an important role in terms of detection. Therefore, to improve the proposed system's detection capacity, different sizes of hidden files have been considered. The proposed detection system was trained and tested to distinguish stego images from clean ones using the discriminant analysis (DA) and multilayer neural network (MLP) classification methods. The paper presents the ability of the proposed system which achieved effective performance in terms of detecting stego images.