BASN—Learning Steganography with a Binary Attention Mechanism

Image steganography is the method of concealing information, which can be text, image, or video, under a cover image in a way that it is invisible to the human eyes. Payload capacity, security and robustness are the features of steganography. A high-quality image steganography ensures a large payload capacity, superior security, and robustness against adversarial attacks. Image steganography is considered to be reversible if the concealed information's original state can be restored with little or no loss in the pixel values and textures. The main goal of this paper is to look at some of the typical techniques and models that are used to build image steganography systems by adopting the Preview, Question, Read, Summarize (PQRS) method to explain how the payload capacity, security, and robustness of these models may be quantified for future research and recommend GAN-based deep learning methods for improving existing reversible image steganography models. Keywords: Image steganography, GAN-based models, Payload capacity, PSNR, Reversibility, SSIM

This paper presents the transform domain image steganography schemes using three popular matrix factorization techniques and contourlet transform. It is known that security of image steganography is mainly evaluated using undetectability of stego image when steganalyzer examines it in order to detect the presence of hidden secret information. Good imperceptibility only suggests eavesdropper’s inability to suspect about the hidden information; however stego image may be analyzed by applying certain statistical checks when it is being transmit- ted through the channel. This work focusses on improving undetectability by employing ma- trix decomposition techniques along with transform domain image steganography. Singular value decomposition (SVD), QR factorization, Nonnegative matrix factorization (NMF) are employed to decompose contourlet coefficients of cover image and secret is embedded into its matrix factorized coefficients. The variety of investigations include the effect of matrix decomposition techniques on major attributes of image steganography like imperceptibility, robustness to a variety of image processing operations, and universal steganalysis perfor- mance. Better imperceptibility, large capacity, and poor detection accuracy compared to existing work validate the efficacy of the proposed image steganography algorithm. Compa- rative analysis amongst three matrix factorization methods is also presented and analyzed.

The Effectiveness of Internet and Mobile Applications in English Language Learning for Health Sciences’ Students in a University in the United Arab Emirates

In human action recognition, the way of collecting action data through video or photos is easily affected by factors such as perspective and light, and it is not easy to describe and extract features. To solve this problem, we researched human skeletal joint data and the use of the convolutional neural network (CNN). The joint data was converted into a PNG image by image coding. In addition, we proposed 3 descriptions of data arrangement order for grayscale image coding. Combined with 4 coding methods and RGB image coding, the coding scheme was expanded to 16 kinds, and used a CNN model with 9 layers structure to conduct comparative experiments on 16 kinds of coding schemes. Then, the influence of data arrangement order and coding methods was discussed based on action recognition results. The experimental results show that the “Zhi” font coding method under the data arrangement order Case 2 is easier to classify actions, and the accuracy of the test set is 96 %.

.Significance: Automatic and accurate classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images is essential for assisting ophthalmologist in the diagnosis and grading of macular diseases. Therefore, more effective OCT volume classification for automatic recognition of macular diseases is needed.Aim: For OCT volumes in which only OCT volume-level labels are known, OCT volume classifiers based on its global feature and deep learning are designed, validated, and compared with other methods.Approach: We present a general framework to classify OCT volume for automatic recognizing macular diseases. The architecture of the framework consists of three modules: B-scan feature extractor, two-dimensional (2-D) feature map generation, and volume-level classifier. Our architecture could address OCT volume classification using two 2-D image machine learning classification algorithms. Specifically, a convolutional neural network (CNN) model is trained and used as a B-scan feature extractor to construct a 2-D feature map of an OCT volume and volume-level classifiers such as support vector machine and CNN with/without attention mechanism for 2-D feature maps are described.Results: Our proposed methods are validated on the publicly available Duke dataset, which consists of 269 intermediate age-related macular degeneration (AMD) volumes and 115 normal volumes. Fivefold cross-validation was done, and average accuracy, sensitivity, and specificity of 98.17%, 99.26%, and 95.65%, respectively, are achieved. The experiments show that our methods outperform the state-of-the-art methods. Our methods are also validated on our private clinical OCT volume dataset, consisting of 448 AMD volumes and 462 diabetic macular edema volumes.Conclusions: We present a general framework of OCT volume classification based on its 2-D feature map and CNN with attention mechanism and describe its implementation schemes. Our proposed methods could classify OCT volumes automatically and effectively with high accuracy, and they are a potential practical tool for screening of ophthalmic diseases from OCT volume.

In recent electroencephalograph (EEG)-based emotion recognition, the differential entropy (DE) features extracted from multiple electrodes are organized as a 2D feature map for convolutional neural network (CNN) in order to utilize the information hidden in the electrodes. In this study, we attempt to investigate the influence of different feature maps on the recognition performance. Six different 2D feature maps (M1-M4: baseline feature maps without sparsity and location relationship, M5-M6: pre-defined feature maps with sparsity and location relationship) are used to organize the DE features for the traditional CNN model. Evaluation study on the DEAP dataset finds that the 2D feature map configuration exhibits statistically significant effect on the classification performance of the traditional CNN model in classifying the high/low arousal and high/low valence, respectively. However, the differences are rather limited, e.g., only 1% improvement can be resulted from selecting the optimal 2D feature map among 6 feature maps. This implies that the feature map may not be a critical issue when applying the DE features to classifying the emotion states in a CNN.

In information security, image steganography is one of the information securing process. Image steganography is mostly used in medical fields for hiding medical prescription data behind the medical images. Designing steganographic algorithms for empirical cover sources, such as digital images, is very perplexing due to the lack of accurate models. The most successful approach today avoids estimating the cover source distribution because this task is infeasible for complex and non-stationary sources. Instead, the steganography problem is formulated as source coding with fidelity constraint the sender entrenches the message with minimizing the distortion. Practical algorithms that entrench near the theoretical payload–distortion bound are available for a very general class of distortion functions. With the current framework, the only task left to the sender is essential for the design of the distortion function. Here information is which wants to be confidential that information's are stored behind the image pixels. However, due to increasing crypt analysis attacks and binary image de stenographic process image steganography has very less security. So improving the security in image steganography process, the current system provide the asymmetric encryption standard for improving more security in steganography.

Image Steganography is a way to hide the secret information using a cover image. The information in the secret image will be hided in cover image, so that the secret information is no more accessible. In this paper, an image steganography technique has been proposed which is based on block division method and LSB embedding. In block division, the image is divided into blocks of fixed size followed by embedding process. The proposed work ensures the higher quality of the image and promising security. This paper also compares proposed work with existing work on bases of various parameters like PSNR and MSE.

The visually meaningful image encryption (VMIE) technique is used to offer additional security to the noise-like encrypted image by implanting the secret image in the cover image. Generally, VMIE techniques follow two steps: pre-encryption and embedding. In this paper, an advanced V-Net architecture based VMIE technique is presented. V-Net architecture is based on a Convolution Neural Network (CNN) and offered medical image segmentation, that is utilized in the image into image steganography in the proposed work. In the proposed VMIE technique, the secret image is encrypted by utilizing the 5D chaotic map to provide high security, and the encrypted secret image is implanted into the cover image using a V-Net based embedding method. CNN-based image embedding methods offer high payload capacity and imperceptibility. In these methods, the encoder hides the secret image into the cover and the decoder reconstruct the secret image. Furthermore, a CNN-based efficient decoder is designed in the proposed method. Moreover, to validate the proposed method, standard evaluation parameters are analyzed.

Handwritten digit recognition is a well-researched area in the field of pattern recognition that is used for distinguishing the pre-segmented handwritten digits. Deep learning is a recent research trend in this field and architectures like convolutional neural network (CNN) are being used. CNN is a computationally expensive architecture that is normally used to provide high accuracy in complex classification problems which require tuning of millions of parameters. On the contrary, less complex classification problems can be solved using considerably less number of parameters—hence using CNN on them leads to unnecessary wastage of resources. In the present work, we have proposed to reduce the feature maps that are used to train the CNN to reduce storage space and computation time. Experimental results show that the time required to train the CNN decreases with reducing the number of feature maps without notably affecting the accuracy.

Land-use scene classification (LUSC) is a key technique in the field of remote sensing imagery (RSI) interpretation. A convolutional neural network (CNN) is widely used for its ability to autonomously and efficiently extract deep semantic feature maps (DSFMs) from large-scale RSI data. However, CNNs cannot accurately extract the rich spatial structure information of RSI, and the key information of RSI is easily lost due to many pooling layers, so it is difficult to ensure the information integrity of the spatial structure feature maps (SSFMs) and DSFMs of RSI with CNNs only for LUSC, which can easily affect the classification performance. To fully utilize the SSFMs and make up for the insufficiency of CNN in capturing the relationship information between the land-use objects of RSI, while reducing the loss of important information, we propose an effective dual-branch hybrid framework, HFCC-Net, for the LUSC task. The CNN in the upper branch extracts multi-scale DSFMs of the same scene using transfer learning techniques; the graph routing-based CapsNet in the lower branch is used to obtain SSFMs from DSFMs in different scales, and element-by-element summation achieves enhanced representations of SSFMs; a newly designed function is used to fuse the top-level DSFMs with SSFMs to generate discriminant feature maps (DFMs); and, finally, the DFMs are fed into classifier. We conducted sufficient experiments using HFCC-Net on four public datasets. The results show that our method has better classification performance compared to some existing CNN-based state-of-the-art methods.

Due to the inclement weather at sea, the pictures collected by USV will always be affected by fog, degrading in quality. In order to improve the quality of images collected by USV, convolutional neural networks (CNN) are widely used in image defogging. In this article, we proposed a CNN-based end-to-end defogging neural network, using dense connection blocks and the attention mechanism to obtain image information. Since convolutional neural networks have the advantages of local perception and parameter sharing, we have changed the traditional apriori method for atmospheric scattering models. We use multi-scale learning to capture image information and use the attention mechanism to suppress some irrelevant details. Experiments have shown that our method has a good effect on USV image dehazing problem.

In existing convolutional neural networks (CNNs), both convolution and pooling are locally performed for image regions separately, no contextual dependencies between different image regions have been taken into consideration. Such dependencies represent useful spatial structure information in images. Whereas recurrent neural networks (RNNs) are designed for learning contextual dependencies among sequential data by using the recurrent (feedback) connections. In this work, we propose the convolutional recurrent neural network (C-RNN), which learns the spatial dependencies between image regions to enhance the discriminative power of image representation. The C-RNN is trained in an end-to-end manner from raw pixel images. CNN layers are firstly processed to generate middle level features. RNN layer is then learned to encode spatial dependencies. The C-RNN can learn better image representation, especially for images with obvious spatial contextual dependencies. Our method achieves competitive performance on ILSVRC 2012, SUN 397, and MIT indoor.

Convolutional neural network (CNN) has developed such a large network size in last few years, so reducing the storage requirement without hurting its accuracy becomes necessary. In this paper, in order to reduce the number of high dimensional feature maps in shallow layers, we propose a feature map selection method, which cuts the feature map number by correlation coefficient between kernels and finishes detection by HOG+SVM method. Firstly, we extract feature maps of shallow layers from trained CNN. Then, we merge strongly relevant feature maps and choose all maps among weakly relevant feature maps by analyzing correlation coefficient of kernels. Finally, we extract HOG features of the chosen feature maps and use SVM to complete the training and classification. The experimental results show that the proposed method can effectively prune high dimensional feature maps and stabilize or even advance the performance in pedestrian detection.

Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the local and sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this letter, we propose an efficient E2E SE model, termed WaveCRN. Compared with models based on convolutional neural networks (CNN) or long short-term memory (LSTM), WaveCRN uses a CNN module to capture the speech locality features and a stacked simple recurrent units (SRU) module to model the sequential property of the locality features. Different from conventional recurrent neural networks and LSTM, SRU can be efficiently parallelized in calculation, with even fewer model parameters. In order to more effectively suppress noise components in the noisy speech, we derive a novel restricted feature masking approach, which performs enhancement on the feature maps in the hidden layers; this is different from the approaches that apply the estimated ratio mask to the noisy spectral features, which is commonly used in speech separation methods. Experimental results on speech denoising and compressed speech restoration tasks confirm that with the SRU and the restricted feature map, WaveCRN performs comparably to other state-of-the-art approaches with notably reduced model complexity and inference time.