Meaningful Image Research Articles

Adversarial Embedding Using Steganography Technique

Abstract: Conventional visual secret sharing (VSS) schemes hide secret images in shares that are moreover published on clarity or are decoded and stored in a digital form. The shares can appear as noise-suchlike pixels or as meaningful images, but it'll arouse dubitation and increase interception threat during transmission of the shares. Hence, VSS schemes suffer from a transmission threat problem for the secret itself and for the actors who are involved in the VSS scheme. To address this problem, we proposed a new fashion for the palette-grounded steganography using a texture with LSB and also a natural-image-grounded VSS scheme (NVSS scheme) that shares secret images via colorful carrier media to cover the secret and the actors during the transmission phase. We contrive the texture conflation process into steganography to hide secret dispatches. In comparison to using a being cover image to hide dispatches, our algorithm hides the source texture image and embeds secret dispatches through the process of print. The natural shares can be prints or hand-painted filmland in digital form or published form. We also propose possible ways to hide the secret to reduce the transmission threat problem for the share. Experimental results indicate that the proposed approach is an excellent result for working the transmission threat problem for the VSS schemes. Keywords: visual secret sharing (VSS), steganography, natural-image-based VSS scheme (NVSS scheme), OR Code, Palette Based Steganography.

Threshold Meaningful Secret Image Sharing Scheme Based on QR Code

In the traditional secret image sharing scheme (SIS), the noise-like cover image is vulnerable and thus suspicion is easily aroused by malicious users. Therefore, the meaningful secret image sharing scheme deserves investigation. In this paper, we introduce a new k , n threshold meaningful secret image sharing scheme based on QR code (MSIS-QR). In the proposed MSIS-QR, the secret image is shared with n QR codes, where each share of the scheme is a valid QR code and can be decoded by a QR code scanner. When k or more shares are collected, the secret image can be losslessly recovered by the Chinese remainder theorem. Experimental results indicate the advantages of our scheme in terms of recovered image quality and decoding time.

Novel Visual Secret Sharing Scheme for the QR Code with Meaningful Shares

Visual secret sharing (VSS) scheme can share the secret image with several shares. Shares are performed by the decoding operation to restore the secret image. VSS scheme is mainly used for the secure transmission of images. Quick response (QR) code is often used by people on the Internet. It can be encrypted by the VSS scheme to enhance the security of its transmission. The share is meaningless that will arouse the suspicion of the attacker. The security of the VSS scheme is decreased. This paper proposes a novel VSS scheme for the QR code with meaningful images to solve this problem. Two continue tone images are converted to halftone images. The halftone image is modified to generate the share. Every share is meaningful, not meaningless. Two shares are performed the decoding operation to restore the secret QR code. The restored QR code can be correctly decoded by the general decoder. Experimental results prove that the proposed scheme is feasible.

A Novel Enhanced Nonnegative Matrix Factorization Method for Face Recognition

Nonnegative matrix factorization (NMF), distinguished from the approaches for holistic feature representation, is able to acquire meaningful basis images for parts-based representation. However, NMF does not utilize the data-label information and usually achieves undesirable performance in classification. To address the above-mentioned problem of NMF, this paper proposes a new enhanced NMF (ENMF) method for facial image representation and recognition. We seek to learn powerfully discriminative feature by a label-based regularizer which describes the relationship between the data. It is desired that minimizing the regularizer makes the data from the same class have high similarity and the data from different classes have low similarity. This good property will contribute to improving the performance of NMF. Therefore, we propose an objective function of ENMF by incorporating the label-based regularizer into the loss function. Subsequently, we find the stationary point of the constructed auxiliary function by means of Cardano’s formula and derive the update rules of our ENMF algorithm. The convergence of the proposed ENMF is both theoretically sound and empirically validated. Finally, the proposed ENMF method is successfully applied to face recognition. Four publicly available face datasets, namely AR, Caltech 101, Yale, and CMU PIE, are chosen for evaluations. Compared with the state-of-the-art NMF-based algorithms, the experimental results illustrate that the proposed ENMF algorithm achieves superior performance.

Optimized visually meaningful image embedding strategy based on compressive sensing and 2D DWT-SVD

Optimized visually meaningful image embedding strategy based on compressive sensing and 2D DWT-SVD

Perceptually Optimal Color Representation of Fully Polarimetric SAR Imagery.

The four bands of fully polarimetric SAR data convey scattering characteristics of the Earth’s background, but perceptually are not very easy for an observer to use. In this work, the four different channels of fully polarimetric SAR images, namely HH, HV, VH, and VV, are combined so that a color image of the Earth’s background is derived that is perceptually excellent for the human eye and at the same time provides accurate information regarding the scattering mechanisms in each pixel. Most of the elementary scattering mechanisms are related to specific color and land cover types. The innovative nature of the proposed approach is due to the two different consecutive coloring procedures. The first one is a fusion procedure that moves all the information contained in the four polarimetric channels into three derived RGB bands. This is achieved by means of Cholesky decomposition and brings to the RGB output the correlation properties of a natural color image. The second procedure moves the color information of the RGB image to the CIELab color space, which is perceptually uniform. The color information is then evenly distributed by means of color equalization in the CIELab color space. After that, the inverse procedure to obtain the final RGB image is performed. These two procedures bring the PolSAR information regarding the scattering mechanisms on the Earth’s surface onto a meaningful color image, the appearance of which is close to Google Earth maps. Simultaneously, they give better color correspondence to various land cover types compared with existing SAR color representation methods.

Meaningful secret image sharing resist to typical image processing of shadows

Meaningful secret image sharing resist to typical image processing of shadows

Meaningful Secret Image Sharing with Saliency Detection.

Secret image sharing (SIS), as one of the applications of information theory in information security protection, has been widely used in many areas, such as blockchain, identity authentication and distributed cloud storage. In traditional secret image sharing schemes, noise-like shadows introduce difficulties into shadow management and increase the risk of attacks. Meaningful secret image sharing is thus proposed to solve these problems. Previous meaningful SIS schemes have employed steganography to hide shares into cover images, and their covers are always binary images. These schemes usually include pixel expansion and low visual quality shadows. To improve the shadow quality, we design a meaningful secret image sharing scheme with saliency detection. Saliency detection is used to determine the salient regions of cover images. In our proposed scheme, we improve the quality of salient regions that are sensitive to the human vision system. In this way, we obtain meaningful shadows with better visual quality. Experiment results and comparisons demonstrate the effectiveness of our proposed scheme.

ClassHyPer: ClassMix-Based Hybrid Perturbations for Deep Semi-Supervised Semantic Segmentation of Remote Sensing Imagery

Inspired by the tremendous success of deep learning (DL) and the increased availability of remote sensing data, DL-based image semantic segmentation has attracted growing interest in the remote sensing community. The ideal scenario of DL application requires a vast number of annotation data with the same feature distribution as the area of interest. However, obtaining such enormous training sets that suit the data distribution of the target area is highly time-consuming and costly. Consistency-regularization-based semi-supervised learning (SSL) methods have gained growing popularity thanks to their ease of implementation and remarkable performance. However, there have been limited applications of SSL in remote sensing. This study comprehensively analyzed several advanced SSL methods based on consistency regularization from the perspective of data- and model-level perturbation. Then, an end-to-end SSL approach based on a hybrid perturbation paradigm was introduced to improve the DL model’s performance with a limited number of labels. The proposed method integrates the semantic boundary information to generate more meaningful mixing images when performing data-level perturbation. Additionally, by using implicit pseudo-supervision based on model-level perturbation, it eliminates the need to set extra threshold parameters in training. Furthermore, it can be flexibly paired with the DL model in an end-to-end manner, as opposed to the separated training stages used in the traditional pseudo-labeling. Experimental results for five remote sensing benchmark datasets in the application of segmentation of roads, buildings, and land cover demonstrated the effectiveness and robustness of the proposed approach. It is particularly encouraging that the ratio of accuracy obtained using the proposed method with 5% labels to that using the purely supervised method with 100% labels was more than 89% on all benchmark datasets.

Removing the impulse noise from images based on fuzzy cellular automata by using a two-phase innovative method

In this paper, a novel method is proposed to restore digital images corrupted by impulse noise. The proposed method in this paper consists of two phases for detecting impulse noise and image restoration. Corrupted pixels in the first phase of the proposed method are identified in two steps. In the first step, the corrupted pixels are identified by minimum values and the average Moore neighborhood pixels of the central pixel. In the second step of this phase, the pixels identified in the previous step as an uncorrupted pixel, are examined whether they are uncorrupted or corrupted once again for further accuracy by a new algorithm. The new algorithm uses cellular automata to identify corrupted pixels by measuring the harmonic and arithmetic means values of four different states of the position of five pixels in the neighborhood of the central pixel. In the second phase of the proposed method, the corrupted pixels are restored using the cosine similarity of the maximization of four different positions of the five pixels neighborhood to the central pixel using fuzzy cellular. The proposed algorithm is evaluated using image enhancement factor (IEF), Structural Similarity Index (SSIM), and Peak Signal to Noise Ratio (PSNR). The proposed method has been tested on 580 images at 15–90% noise density and the qualitative and quantitative results show that the proposed filter is robust enough at different noise levels and meaningful image details such as edges compared to other methods are well maintained.

A k,n-Threshold Secret Image Sharing Scheme Based on a Non-Full Rank Linear Model

Secret image sharing is a hot issue in the research field of data hiding schemes for digital images. This paper proposes a general k,n threshold secret image sharing scheme, which distributes secret data into n meaningful image shadows based on a non-full rank linear model. The image shadows are indistinguishable from their corresponding distinct cover images. Any k combination of the n shares can perfectly restore the secret data. In the proposed scheme, the integer parameters k,n, with k≤n, can be set arbitrarily to meet the application requirement. The experimental results demonstrate the applicability of the proposed general scheme. The embedding capacity, the visual quality of image shadows, and the security level are satisfactory.

Acoustic detection of unmanned aerial vehicles using biologically inspired vision processing.

Robust detection of acoustically quiet, slow-moving, small unmanned aerial vehicles is challenging. A biologically inspired vision approach applied to the acoustic detection of unmanned aerial vehicles is proposed and demonstrated. The early vision system of insects significantly enhances signal-to-noise ratios in complex, cluttered, and low-light (noisy) scenes. Traditional time-frequency analysis allows acoustic signals to be visualized as images using spectrograms and correlograms. The signals of interest in these representations of acoustic signals, such as linearly related harmonics or broadband correlation peaks, essentially offer equivalence to meaningful image patterns immersed in noise. By applying a model of the photoreceptor stage of the hoverfly vision system, it is shown that the acoustic patterns can be enhanced and noise greatly suppressed. Compared with traditional narrowband and broadband techniques, the bio-inspired processing can extend the maximum detectable distance of the small and medium-sized unmanned aerial vehicles by between 30% and 50%, while simultaneously increasing the accuracy of flight parameter and trajectory estimations.

A stable meaningful image encryption scheme using the newly-designed 2D discrete fractional-order chaotic map and Bayesian compressive sensing

In order to safely and covertly protect the digital image information during public channel transmission and localized storage, a stable image visually secure encryption algorithm by using 2D discrete fractional-order chaotic map (FOCM), Bayesian compressive sensing (BCS), and discrete V transform (DVT) is presented in this paper. First, the key-controlled measurement matrix constructed by the infinite collapse-Chebyshev-coupling chaotic map is employed to measure the scrambled wavelet packet coefficients of plain image in parallel. Then, the fractional-order chaotic map designed through piece-wise constant arguments method is employed to generate the secret code streams with assistance of the counter mode, and under its control, the compressed image is re-encrypted into the intermediate secret image. Next, the DVT-based embedding technology is proposed to stochastically embed the secret data into the non-secret-involved host image. Eventually, experimental results show that under the premise of ensuring security, the proposed algorithm improves the visual security around 1∼9 dB, and stabilizes its compression performance within 1 dB, compared with other existing related encryption algorithms.

Simplifying the hardware requirements for fast neural EIT of peripheral nerves

Objective. The main objective of this study was to assess the feasibility of lowering the hardware requirements for fast neural electrical impedance tomography (EIT) in order to support the distribution of this technique. Specifically, the feasibility of replacing the commercial modules present in the existing high-end setup with compact and cheap customized circuitry was assessed. Approach. Nerve EIT imaging was performed on rat sciatic nerves with both our standard ScouseTom setup and a customized version in which commercial benchtop current sources were replaced by custom circuitry. Electrophysiological data and images collected in the same experimental conditions with the two setups were compared. Data from the customized setup was subject to a down-sampling analysis to simulate the use of a recording module with lower specifications. Main results. Compound action potentials (573 ± 287 μV and 487 ± 279 μV, p=0.28) and impedance changes (36 ± 14 μV and 31 ± 16 μV, p=0.49) did not differ significantly when measured using commercial high-end current sources or our custom circuitry, respectively. Images reconstructed from both setups showed neglibile (<1voxel, i.e. 40 μm) difference in peak location and a high degree of correlation (R 2 = 0.97). When down-sampling from 24 to 16 bits ADC resolution and from 100 to 50 KHz sampling frequency, signal-to-noise ratio showed acceptable decrease (<−20%), and no meaningful image quality loss was detected (peak location difference <1voxel, pixel-by-pixel correlation R 2 = 0.99). Significance: The technology developed for this study greatly reduces the cost and size of a fast neural EIT setup without impacting quality and thus promotes the adoption of this technique by the neuroscience research community.

Optical cryptosystem for visually meaningful encrypted images based on gyrator transform and Hénon map

Optical cryptosystem for visually meaningful encrypted images based on gyrator transform and Hénon map

РОЛЬ КУЛЬТУРНОГО ЛАНДШАФТА В ФОРМИРОВАНИИ РЕГИОНАЛЬНОГО САМОСОЗНАНИЯ СТАРИЦКОГО ВЕРХНЕВОЛЖЬЯ НА РУБЕЖЕ ХIХ-ХХ ВВ.

According to the information-axiological approach of Yu.A. Vedenin and M.E. Kuleshova, spiritual and intellectual values transmitted in the form of information from generation to generation play a significant role in the formation of the cultural landscape. The comprehensive study and actualization of cultural heritage as part of the cultural landscape reveals the role of traditional culture values in the modern socio-cultural situation. There is a close connection between the cultural landscape and local self-awareness through recognizable and meaningful images, concepts and symbols. Associative meanings and meanings of the cultural landscape of the territory affect the socio-cultural potential of the local society, the identification of its place in the external environment. At the turn of the 19–20th centuries the inhabitants of the Staritsky region were actively engaged in research in the field of local history, archiving, sought to preserve the local cultural heritage in collective practices, collecting, in publications in historical periodicals. Historical and cultural landscape served as inspiration for research of I.P. Krylov, A.N. Vershinsky, S.I. Pokrovsky, A.D. Ushakov. The clergy played a huge role in preserving regional culture. The clergy of the Staritsky Upper Volga region were members of the Tver Scientific Archival Commission, subscribers of historical journals, collectors of local folklore and archivists. The old manors, being at a distance from the provincial center, and possessing a powerful cultural and historical potential, had a great influence on the culture of the county as a whole, their artistic values served as the core of the collection of the county museum.

Meaningful secret image sharing for JPEG images with arbitrary quality factors.

JPEG is the most common format for storing and transmitting photographic images on social network platforms. JPEG image is widely used in people's life because of their low storage space and high visual quality. Secret image sharing (SIS) technology is important to protect image data. Traditional SIS schemes generally focus on spatial images, however there is little research on frequency domain images. In addition, the current tiny research on SIS for JPEG images only focuses on JPEG images with a compression quality factor (QF) of 100. To overcome the limitation of JPEG images in SIS, we propose a meaningful SIS for JPEG images to operate the quantized DCT coefficients of JPEG images. The random elements utilization model is applied to achieve meaningful shadow images. Our proposed scheme has a better quality of the shadow images and the recovered secret image. Experiment results and comparisons indicate the effectiveness of the scheme. The scheme can be used for JPEG images with any compression QF. Besides, the scheme has good characteristics, such as (k,n) threshold, extended shadow images.

Applying GMEI-GAN to Generate Meaningful Encrypted Images in Reversible Data Hiding Techniques

With the rapid development of information technology, the transmission of information has become convenient. In order to prevent the leakage of information, information security should be valued. Therefore, the data hiding technique has become a popular solution. The reversible data hiding technique (RDH) in particular uses symmetric encoding and decoding algorithms to embed the data into the cover carrier. Not only can the secret data be transmitted without being detected and retrieved completely, but the cover carrier also can be recovered without distortion. Moreover, the encryption technique can protect the carrier and the hidden data. However, the encrypted carrier is a form of ciphertext, which has a strong probability to attract the attention of potential attackers. Thus, this paper uses the generative adversarial networks (GAN) to generate meaningful encrypted images for RDH. A four-stage network architecture is designed for the experiment, including the hiding network, the encryption/decryption network, the extractor, and the recovery network. In the hiding network, the secret data are embedded into the cover image through residual learning. In the encryption/decryption network, the cover image is encrypted into a meaningful image, called the marked image, through GMEI-GAN, and then the marked image is restored to the decrypted image via the same architecture. In the extractor, 100% of the secret data are extracted through the residual learning framework, same as the hiding network. Lastly, in the recovery network, the cover image is reconstructed with the decrypted image and the retrieved secret data through the convolutional neural network. The experimental results show that using the PSNR/SSIM as the criteria, the stego image reaches 45.09 dB/0.9936 and the marked image achieves 38.57 dB/0.9654. The proposed method not only increases the embedding capacity but also maintains high image quality in the stego images and marked images.

Generative high-capacity image hiding based on residual CNN in wavelet domain

Image hiding is the process of hiding a secret image in another meaningful image or other carriers so that the secret image remains imperceptible and can be recovered securely at the receiving end. The output image of an image hiding algorithm hides the secret image and visually appears to be the same as the carrier image, thus reducing the possibility of being attacked. The current hiding algorithms have relatively low hiding capacity and weak security. In this paper, we propose a generative image hiding algorithm based on a residual convolutional neural network (ResCNN) in wavelet domain to overcome the above-mentioned shortcomings. First, the secret image was subjected to wavelet transform. The low-frequency band of wavelet coefficients were discarded, and only the high-frequency bands were retained as features. These features were then effectively embedded into the carrier image by a generative ResCNN. The recovery network was trained simultaneously with the hiding network so as to extract the hidden features from the container and reconstruct the secret image. Pixel shuffle was used to recover a high-resolution secret image. The experimental results show that the proposed image hiding algorithm is capable of obtaining state-of-the-art results in terms of high hiding capacity and strong security measures.

Bi-dimensional representation of EEGs for BCI classification using CNN architectures.

An important challenge when designing Brain Computer Interfaces (BCI) is to create a pipeline (signal conditioning, feature extraction and classification) requiring minimal parameter adjustments for each subject and each run. On the other hand, Convolutional Neural Networks (CNN) have shown outstanding to automatically extract features from images, which may help when distribution of input data is unknown and irregular. To obtain full benefits of a CNN, we propose two meaningful image representations built from multichannel EEG signals. Images are built from spectrograms and scalograms. We evaluated two kinds of classifiers: one based on a CNN-2D and the other built using a CNN-2D combined with a LSTM. Our experiments showed that this pipeline allows to use the same channels and architectures for all subjects, getting competitive accuracy using different datasets: 71.3 ± 11.9% for BCI IV-2a (four classes); 80.7 ± 11.8 % for BCI IV-2a (two classes); 73.8 ± 12.1% for BCI IV-2b; 83.6 ± 1.0% for BCI II-III and 82.10% ± 6.9% for a private database based on mental calculation.