Improvement of Message Processing-based Steganographic Algorithm using Convolutional Neural Networks
20 Oct 2021-pp 68-74
TL;DR: In this article, the authors proposed an application that uses a Message Processing-based Steganographic Algorithm and an Artificial Intelligence algorithm to colorize the recovered message using Convolutional Neural Networks.
Abstract: Steganography is the art and science of hiding secret messages without being discovered by a potential attacker. In this paper we propose an application that uses a Message Processing-based Steganographic Algorithm and an Artificial Intelligence algorithm to colorize the recovered message using Convolutional Neural Networks. This solution gives the opportunity to hide a higher quantity of message data in the cover image. The structure of the application and an analysis of test results are presented in this paper.
References
More filters
01 Aug 2017
TL;DR: All the elements and important issues related to CNN, and how these elements work, are explained and defined and the parameters that effect CNN efficiency are state.
Abstract: The term Deep Learning or Deep Neural Network refers to Artificial Neural Networks (ANN) with multi layers. Over the last few decades, it has been considered to be one of the most powerful tools, and has become very popular in the literature as it is able to handle a huge amount of data. The interest in having deeper hidden layers has recently begun to surpass classical methods performance in different fields; especially in pattern recognition. One of the most popular deep neural networks is the Convolutional Neural Network (CNN). It take this name from mathematical linear operation between matrixes called convolution. CNN have multiple layers; including convolutional layer, non-linearity layer, pooling layer and fully-connected layer. The convolutional and fully-connected layers have parameters but pooling and non-linearity layers don't have parameters. The CNN has an excellent performance in machine learning problems. Specially the applications that deal with image data, such as largest image classification data set (Image Net), computer vision, and in natural language processing (NLP) and the results achieved were very amazing. In this paper we will explain and define all the elements and important issues related to CNN, and how these elements work. In addition, we will also state the parameters that effect CNN efficiency. This paper assumes that the readers have adequate knowledge about both machine learning and artificial neural network.
2,338 citations
08 Oct 2016
TL;DR: This paper proposes a fully automatic approach to colorization that produces vibrant and realistic colorizations and shows that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder.
Abstract: Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We evaluate our algorithm using a “colorization Turing test,” asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32 % of the trials, significantly higher than previous methods. Moreover, we show that colorization can be a powerful pretext task for self-supervised feature learning, acting as a cross-channel encoder. This approach results in state-of-the-art performance on several feature learning benchmarks.
2,326 citations
11 Jul 2016
TL;DR: A novel technique to automatically colorize grayscale images that combines both global priors and local image features and can process images of any resolution, unlike most existing approaches based on CNN.
Abstract: We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features. Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image. The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion. Furthermore, our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors. We validate our approach with a user study and compare against the state of the art, where we show significant improvements. Furthermore, we demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.
758 citations
08 Oct 2016
TL;DR: In this paper, a fully automatic image colorization system was developed, which leverages recent advances in deep networks, exploiting both low-level and semantic representations, and trained a model to predict per-pixel color histograms.
Abstract: We develop a fully automatic image colorization system. Our approach leverages recent advances in deep networks, exploiting both low-level and semantic representations. As many scene elements naturally appear according to multimodal color distributions, we train our model to predict per-pixel color histograms. This intermediate output can be used to automatically generate a color image, or further manipulated prior to image formation. On both fully and partially automatic colorization tasks, we outperform existing methods. We also explore colorization as a vehicle for self-supervised visual representation learning.
647 citations
TL;DR: Two novel ways of applying the histogram characteristic function (HCF), introduced by Harmsen for the detection of steganography in color images but ineffective on grayscale images, are introduced: calibrating the output using a downsampled image and computing the adjacency histogram instead of the usual histogram.
Abstract: We consider the problem of detecting spatial domain least significant bit (LSB) matching steganography in grayscale images, which has proved much harder than for its counterpart, LSB replacement. We use the histogram characteristic function (HCF), introduced by Harmsen for the detection of steganography in color images but ineffective on grayscale images. Two novel ways of applying the HCF are introduced: calibrating the output using a downsampled image and computing the adjacency histogram instead of the usual histogram. Extensive experimental results show that the new detectors are reliable, vastly more so than those previously known.
544 citations