Abstract Although image steganography advances considerably in recent years, it continues to face numerous challenges. Image steganography is the practice of preserving privacy by embedding hidden information text, video, or images within a cover image to protect from human eye. This research presents a streamlined Convolutional Neural Networks (CNN) based model designed to embed a concealed image inside a cover image and retrieve the hidden image from the input. The proposed approach helps in embedding and retrieving hidden information leveraging the Encoder-Decoder technique using CNN. It spreads and compresses the information of the hidden image throughout all available bits, in contrast to conventional steganographic techniques which employ the least significant bits of the container image to conceal the majority of the message. Furthermore, the proposed approach is assessed with various metrics such as structured similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) where empirical results show that the proposed method reported better PSNR (44.37) and SSIM (0.9956) than existing deep learning based steganographic methods and provides enhanced imperceptibility, security, robustness, and hiding capacity.

Stochastic gradient descent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic SGD is to change by equal-sized steps for all parameters, irrespective of the gradient behavior. Hence, an efficient way of deep network optimization is to have adaptive step sizes for each parameter. Recently, several attempts have been made to improve gradient descent methods such as AdaGrad, AdaDelta, RMSProp, and adaptive moment estimation (Adam). These methods rely on the square roots of exponential moving averages of squared past gradients. Thus, these methods do not take advantage of local change in gradients. In this article, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i.e., diffGrad). In the proposed diffGrad optimization technique, the step size is adjusted for each parameter in such a way that it should have a larger step size for faster gradient changing parameters and a lower step size for lower gradient changing parameters. The convergence analysis is done using the regret bound approach of the online learning framework. In this article, thorough analysis is made over three synthetic complex nonconvex functions. The image categorization experiments are also conducted over the CIFAR10 and CIFAR100 data sets to observe the performance of diffGrad with respect to the state-of-the-art optimizers such as SGDM, AdaGrad, AdaDelta, RMSProp, AMSGrad, and Adam. The residual unit (ResNet)-based convolutional neural network (CNN) architecture is used in the experiments. The experiments show that diffGrad outperforms other optimizers. Also, we show that diffGrad performs uniformly well for training CNN using different activation functions. The source code is made publicly available at https://github.com/shivram1987/diffGrad.

Local descriptors used in face recognition are robust in a sense that these descriptors perform well in varying pose, illumination, and lighting conditions. The accuracy of these descriptors depends on the precision of mapping the relationship that exists in the local neighborhood of a facial image into microstructures. In this paper, a local gradient hexa pattern is proposed that identifies the relationship among the reference pixel and its neighboring pixels at different distances across different derivative directions. Discriminative information exists in the local neighborhood as well as in different derivative directions. The proposed descriptor effectively transforms these relationships into binary micropatterns discriminating inter-class facial images with optimal precision. The recognition and retrieval performance of the proposed descriptor has been compared with state-of-the-art descriptors, namely, local derivative pattern, local tetra pattern, multiblock local binary pattern, and local vector pattern over the most challenging and benchmark facial image databases, i.e., Cropped Extended Yale B, CMU-PIE, color-FERET, LFW, and Ghallager database. The proposed descriptor has better recognition as well as retrieval rates compared with state-of-the-art descriptors.