TIRDH: A Novel Three-Shadow-Image Reversible Data Hiding Algorithm Using Weight and Modulo

Abstract

Reversible data hiding (RDH) in image media is crucial for securely embedding confidential information while ensuring complete recovery of both the cover image and the hidden data. Traditional RDH techniques often struggle to balance embedding capacity and image fidelity, limiting their practical effectiveness. This paper introduces TIRDH, a novel three-shadow-image RDH scheme that employs weight and modulo operations to achieve high-capacity embedding while preserving image quality. The method embeds an M-ary secret message within a shadow pixel cluster using a 3-tuple weight vector, modulo operations, and a variation table to guide pixel modifications. This guarantees data integrity without pixel underflow or overflow, thereby avoiding the falling-off boundary problem (FOBP) and ensuring reversibility. Additionally, the scheme offers flexible embedding rates, adjustable through a single parameter and weight vector, making it highly adaptable to various user requirements, image types, and application scenarios. Experimental results from three standard image databases demonstrate its effectiveness, achieving embedding rates ranging from 0.04 to 1.6814 bits per pixel while maintaining high image quality, with an average PSNR ranging from 47.65 to 62.65 dB. Furthermore, its prediction mechanism attains 98.2% accuracy, enabling precise performance estimation before actual message embedding. This predictive capability enhances efficiency by allowing users to anticipate the impact on image quality beforehand. Security assessments confirm strong resilience against RS steganalysis and pixel difference histogram attacks, providing enhanced protection for confidential data. Comparisons with 12 state-of-the-art methods show that the proposed approach outperforms competitors when embedding fewer than 50,000 secret bits and surpasses another set of 12 schemes when the embedding rate exceeds 1.0 bits per pixel. For 1,000 test images with an embedding rate of 1.4 bits per pixel, it consistently outperforms six leading RDH techniques, demonstrating robustness across diverse datasets. These findings establish our proposed TIRDH method as a comprehensive and reliable solution for RDH applications, offering superior embedding performance, high image quality, strong security, and practical adaptability across various real-world scenarios.