Deep Neural Network-based Reversible Image Steganography Technique using Circle-U-Net

Data communication is made at the ease with the advent of the latest communications medium and tools. The concern over data breaches has increased. The digital media communicated across the network are susceptible to unapproved access. Though numerous image steganography approaches were existing for concealing the secret image into the cover image there are still limitations such as inadequate restoration of image quality and less embedding capacity. To overwhelm such shortcomings recently many image steganography approaches based on deep learning are proposed. In this work, a Circle-U-Net-based reversible image steganography technique is proposed. The model includes a contracting process, which includes residual bottleneck as well as circle connect layers which obtain context; an expanding process, which includes sampling layers as well as merging layers for pixel-wise localization. The reversible image steganography (RIS) is carried out with neural network models such as CNN, U-Net scheme, and Circle-U-Net structure on TinyImageNet-200 and Alzheimer’s MRI dataset. The proposed technique is experimented along with RIS using CNN and RIS using U-Net. The experimental results depict that the RIS using the Circle-U-Net structure performs better among the three models.