A High-Capacity Reversible Data Hiding on Grayscale Images Using Threshold-Based Clustering

In the digital age, safeguarding confidential information from unauthorized access is critical. Data transmission occurs in various formats, including text, images, and videos, and while advancements have enhanced the efficiency and convenience of these processes, vulnerabilities in communication channels remain a concern. The proposed scheme secures communication by hiding secret data within a carrier image, visually making it undetectable to potential attackers. Steganography is challenging when transmitting huge quantities of secret data because there is a negotiation between data capacity and imperceptibility. The mastered framework uses grayscale images as a medium for the conveyance of high-capacity secret data. First, the threshold value is computed from the histogram and the statistical mode value. The threshold calculated in the initial step will be a crucial data embedding parameter in the proposed scheme. Then the carrier image is interpolated to increase its size to double. The expanded image is then segmented into 2X2 blocks, the block undergoes a segmentation function to decide whether the block value is above the threshold or below the threshold. Finally, the secret data is embedded into the pixel block based on the threshold value of the block. The secret data and the input image are extracted separately on the receiving end. Standard metrics, Peak Signal to Noise Ratio (PSNR), and Structure Similarity Index Metric (SSIM) are used to evaluate the efficiency of the proposed scheme. The values above 42 and 36 obtained for PSNR for low payload and high payload show the effectiveness of the mastered scheme. Statistical measures, such as mean, standard deviation, and entropy, are used to validate the efficiency of the scheme in ensuring data integrity and security during transmission.