AN APPROACH FOR IMAGE STEGANOGRAPHY AND STEGANALYSIS USING REGRESSIVE STUDENT PSYCHOLOGY OPTIMIZATION-ENABLED DEEP MAX-OUT NETWORK

The art of identifying steganographic traces from digital media images is termed steganalysis. The secret message embedded into the digital media files may be text, audio, video, or in the form of an image. The detection of secret hidden information from the images is carried out using Image steganalysis. The detection and extraction of existing hidden secret messages from the original image are difficult. Hence, an optimization-based deep learning model for detecting hidden information is designed here. In this research, the designed CAViaR Student Psychology-based Optimization-Deep Maxout Network (CSPBO-DMN) technique is used for recovery of the original image through steganography and steganalysis. The bit map image is generated from the cover image and the hidden secret message is XOR-ed with a key. Discrete wavelet transform (DWT)-based embedding, Least-significant bit (LSB)-based embedding and Discrete Cosine Transform (DCT)-based embedding techniques are the XOR-ed and bit map image output. Later, using the DMN classifier, the secret message is detected from the bit map image, which is trained using the CSPBO technique. The experimental outcomes proved that the CSPBO-DMN approach attained higher performance with a Peak-Signal-to-Noise Ratio (PSNR), Bit Error Ratio (BER), computational complexity and memory usage of 35.275 dB, 5.658, 1.225 and 0.017, respectively.