Low feature dimension in image steganographic recognition

Steganalysis <span>aids in the detection of steganographic data without need to know embedding algorithm or "cover" image. The researcher's major goal was develop a technique that might improve recognition accuracy while utilizing minimal feature vector dimension. A number techniques have been developed detect steganography images. However, steganalysis technique's performance is still limited due their large dimension, which takes long time compute. variations texture and properties an embedded image are clearly seen. Therefore, this paper, we proposed based on one features, such as gray level co-occurrence matrix (GLCM). As classifier, Ada-Boost Gaussian discriminant analysis (GDA) used. In order evaluate method, use public database our applied it using IStego100K datasets. results experiment show can greatly. It also indicates terms accuracy, classifier surpassed GDA. comparative findings method outperforms other current especially size accuracy</span>.