Discrete Shearlet Research Articles

Coinciding Diabetic Retinopathy and Diabetic Macular Edema Grading With Rat Swarm Optimization Algorithm for Enhanced Capsule Generation Adversarial Network.

In the worldwide working-age population, visual disability and blindness are common conditions caused by diabetic retinopathy (DR) and diabetic macular edema (DME). Nowadays, due to diabetes, many people are affected by eye-related issues. Among these, DR and DME are the two foremost eye diseases, the severity of which may lead to some eye-related problems and blindness. Early detection of DR and DME is essential to preventing vision loss. Therefore, an enhanced capsule generation adversarial network (ECGAN) optimized with the rat swarm optimization (RSO) approach is proposed in this article to coincide with DR and DME grading (DR-DME-ECGAN-RSO-ISBI 2018 IDRiD). The input images are obtained from the ISBI 2018 unbalanced DR grading data set. Then, the input fundus images are preprocessed using the Savitzky-Golay (SG) filter filtering technique, which reduces noise from the input image. The preprocessed image is fed to the discrete shearlet transform (DST) for feature extraction. The extracting features of DR-DME are given to the ECGAN-RSO algorithm to categorize the grading of DR and DME disorders. The proposed approach is implemented in Python and achieves better accuracy by 7.94%, 36.66%, and 4.88% compared to the existing models, such as the combined DR with DME grading for the cross-disease attention network (DR-DME-CANet-ISBI 2018 IDRiD), category attention block for unbalanced grading of DR (DR-DME-HDLCNN-MGMO-ISBI 2018 IDRiD), combined DR-DME classification with a deep learning-convolutional neural network-based modified gray-wolf optimizer with variable weights (DR-DME-ANN-ISBI 2018 IDRiD).

Color image watermarking using vector SNCM-HMT

An image watermarking scheme is typically evaluated using three main conflicting characteristics: imperceptibility, robustness, and capacity. Developing a good image watermarking method is challenging because it requires a trade-off between these three basic characteristics. In this paper, we proposed a statistical color image watermarking based on robust discrete nonseparable Shearlet transform (DNST)-fast quaternion generic polar complex exponential transform (FQGPCET) magnitude and vector skew-normal-Cauchy mixtures (SNCM)-hidden Markov tree (HMT). The proposed watermarking system consists of two main parts: watermark inserting and watermark extraction. In watermark inserting, we first perform DNST on R, G, and B components of color host image, respectively. We then compute block FQGPCET of DNST domain color components, and embed watermark signal in DNST-FQGPCET magnitudes using multiplicative approach. In watermark extraction, we first analyze the robustness and statistical characteristics of local DNST-FQGPCET magnitudes of color image. We then observe that, vector SNCM-HMT model can capture accurately the marginal distribution and multiple strong dependencies of local DNST-FQGPCET magnitudes. Meanwhile, vector SNCM-HMT parameters can be computed effectively using variational expectation–maximization (VEM) parameter estimation. Motivated by our modeling results, we finally develop a new statistical color image watermark decoder based on vector SNCM-HMT and maximum likelihood (ML) decision rule. Experimental results on extensive test images demonstrate that the proposed statistical color image watermarking provides a performance better than that of most of the state-of-the-art statistical methods and some deep learning approaches recently proposed in the literature.

Statistical learning based blind image watermarking approach

Image watermarking technology poses a significant challenge, requiring a delicate balance between robustness, imperceptibility, and capacity. To solve the balancing problem, a statistical learning based blind image watermarking technique is proposed in this paper. The idea of the proposed method to solve the balancing problem is to enhance imperceptibility and robustness while accommodating sufficient watermarks. Firstly, the local low-order pseudo-Zernike moments (PZM) magnitude in the discrete non-separable Shearlet transform (DNST) domain is constructed as the embedding domain. To ensure stability in embedding positions, we propose an edge embedding strategy. Secondly, by analyzing the statistical characteristics and multi-correlations of DNST-PZM magnitudes, a multi-correlation vector model based on the skew student's-t mixture (SSM) and hidden Markov tree (HMT) is designed. Finally, leveraging the vector SSM-HMT model and the maximum likelihood (ML) criterion, we derive the closed-form decoder expression. Comparative analysis with state-of-the-art methods demonstrates the superior imperceptibility and robustness of our proposed approach in accommodating the same capacity watermark.

Discrete linear canonical shearlet transform

In this paper, we introduce the continuous and discrete version of the linear canonical shearlet transform (LCST). The authors begin with the definition of the LCST and then establish a relationship between the linear canonical transform (LCT) and the LCST. Next, the paper derives several basic properties like Parseval’s Formula, inversion formula, and the characterization of the transform’s range. In addition to the continuous version of the transform, the authors also present a discrete version of the LCST. This discrete version allows for practical implementation and efficient computation of the transform in digital signal processing systems. Lastly, the paper establishes a frame condition for the discrete LCST, which thereby helps in establishing the reconstruction formula for the discrete LCST. The paper ends with a conclusion.

Analysis of space images of the fault system of the Altai-Sayan seismic active region based on Shearlet transform

The paper proposes a method for processing and analyzing satellite images of a territory with increased seismic activity to identify geological inhomogeneities (geological faults, blocks) on the Earth’s surface. The methodology is based on adapted algorithms for discrete Shearlet transform (Shearlet toolbox and FFST). The problems of noise filtering and contour extraction with contrasting and color coding for the studied visual observational data are solved.

Optimal multi-kernel SVM classifier with rotation, illumination and scale invariant hybrid DWT-Shearlet based GLCM feature descriptor and its application to face recognition

In computer vision, we must handle with the various structural aspects of image or video data. The texture is one of the most important aspects of this type of data, which is utilised to identify objects or regions of interest in an image. As imaging conditions change, textures inside actual images significantly change in brightness, contrast, size, and skew. To recognise textures in real-world images, a similarity measure that is invariant to these features must be used. Existing recognition techniques did not perform well due to issues such as illumination, scale, and subject rotation. To address this issue, invariant feature representation methods are being developed to generate features that are insensitive to such variations. In this paper, we proposed a robust hybrid feature descriptor and predicted the faces under illumination, scale, and pose variations using an optimum multi-kernel support vector machine. Additionally, the suggested robust hybrid feature descriptor is enhanced by combining a hybrid transform composed of discrete wavelet and discrete shearlet transforms with some image statistical textural data. The proposed face recognition system is implemented in MATLAB, and analysed using various parameters to show proposed methods improved performance as compared to the state of the art methods.

Brinjal leaf diseases detection based on discrete Shearlet transform and Deep Convolutional Neural Network.

Different diseases are observed in vegetables, fruits, cereals, and commercial crops by farmers and agricultural experts. Nonetheless, this evaluation process is time-consuming, and initial symptoms are primarily visible at microscopic levels, limiting the possibility of an accurate diagnosis. This paper proposes an innovative method for identifying and classifying infected brinjal leaves using Deep Convolutional Neural Networks (DCNN) and Radial Basis Feed Forward Neural Networks (RBFNN). We collected 1100 images of brinjal leaf disease that were caused by five different species (Pseudomonas solanacearum, Cercospora solani, Alternaria melongenea, Pythium aphanidermatum, and Tobacco Mosaic Virus) and 400 images of healthy leaves from India's agricultural form. First, the original plant leaf is preprocessed by a Gaussian filter to reduce the noise and improve the quality of the image through image enhancement. A segmentation method based on expectation and maximization (EM) is then utilized to segment the leaf's-diseased regions. Next, the discrete Shearlet transform is used to extract the main features of the images such as texture, color, and structure, which are then merged to produce vectors. Lastly, DCNN and RBFNN are used to classify brinjal leaves based on their disease types. The DCNN achieved a mean accuracy of 93.30% (with fusion) and 76.70% (without fusion) compared to the RBFNN (82%-without fusion, 87%-with fusion) in classifying leaf diseases.

Image watermarking using DNST-PHFMs magnitude domain vector AGGM-HMT

Invisibility, robustness and payload are three indispensable and contradictory properties for any image watermarking systems. Therefore, in this paper a novel statistical image watermark decoder based on robust discrete nonseparable Shearlet transform (DNST)-polar harmonic Fourier moments (PHFMs) magnitude and effective vector anisotropic generalized Gaussian mixtures (AGGM)-hidden Markov tree (HMT). We begin with a detailed study on the robustness and statistical characteristics of local DNST- PHFMs magnitudes of natural images. This study reveals the excellent robustness, highly non-Gaussian marginal statistics and strong dependencies of local DNST-PHFMs magnitudes. We also find that conditioned on their generalized neighborhoods, the local DNST-PHFMs magnitudes can be approximately modeled as anisotropic generalized Gaussian variables. Based on these findings, we model local DNST-PHFMs magnitudes using a vector AGGM-HMT that can capture all interscale, interdirection, and interlocation dependencies. Meanwhile, model parameters can be estimated effectively by using localization clues guided expectation–maximization (LCGEM) approach. Finally, we develop a new statistical image watermark decoder using the vector AGGM-HMT and maximum likelihood (ML) decision rule. Extensive experimental results show the superiority of the proposed watermark decoder over several state-of-the-art statistical watermarking methods and some approaches based on convolutional neural networks.

Blockchain based Securing Medical Records in Big Data Analytics

The patient privacy is danger while medical records and data are transmitted or share beyond secure big data. This is because violations push them to the margins and they begin to avoid fully revealing their stages. This kind of stages contains negative impact in scientific investigate. To overcome this issue, Secure Block Chain System for Managing and Sharing Electronic Medical Records in Big Data Field is proposed. In this manuscript, a Cryptographic Hash Generator (CHG) technique based Secured and Trusted Data storage and transmission using Block Chain (BC) in Hadoop Distributed File System (HDFS). Initially, the Big data collected from the health care center is partitioned into sensitive and insensitive data. Block chain system utilizes an asymmetric cryptography for validating transactions authentication. Here, the user key is created through secured bitwise cryptographic hash generator (CHG) while there is required to fetch the newly record for usage. In block chain system, when a user seeking data from a healthcare application have forward a request to CHG. The message is send back to the user with a secret key for confirmation. The key can be decrypted or even denied access if only a valid user allows the user to link to this cluster. Only sensitive data were selected to the process of encryption for the process of encryption, this CHG technique employs the Discrete Shearlet Transform (DST) for encrypting the data, and the data’s are warehoused in the block chain to upgrade the level of security. And the insensitive data are put directly on the Hadoop Distributed File System. During the verification process, CHG is utilized for creating the request forward through the user. The operator creates the purpose of remote key to create the block (request) and signing the request using transaction private key, then forward to request queuing. To validate a request, the request from the queue is supplied first and an Improved Grey wolf Optimization algorithm (IGWO) is utilized to determine the optimal request that is fetch through the consensus node for initiating the process of validation. After accepting the user’s request, access is given to the user associated with input or requested data, then the verified request is set to broadcast. The proposed method is executed in JAVA and Hadoop platform. Experimental results show that the proposed BC-CHG-DST-IGWOA shows better performances of higher Efficiency 20.14%, 31.25%, 24.33%, 14.69%, lower time 16.12%, 15.09%, 21.36%, 46.26% compared with the existing methods, such as medical records managing and securing blockchain based system supported by genetic algorithm with discrete wavelet transform (BC-SMR-BD-GA-DWT), DQN-based optimization framework to secure shared blockchain systems (BC-SMR-BD-DQNSB), Hyper ledger blockchain enabled secure medical record management along deep learning-based diagnosis model (BC-SMR-BD-HBESDM-DLD), Secure attribute-based signature scheme with multiple authorities for blockchain in electronic health records system (BC-SMR-BD-MA-ABS) respectively.

Multi-Sensor Image Fusion Method for Defect Detection in Powder Bed Fusion.

Multi-sensor defect detection technology is a research hotspot for monitoring the powder bed fusion (PBF) processes, of which the quality of the captured defect images and the detection capability is the vital issue. Thus, in this study, we utilize visible information as well as infrared imaging to detect the defects in PBF parts that conventional optical inspection technologies cannot easily detect. A multi-source image acquisition system was designed to simultaneously acquire brightness intensity and infrared intensity. Then, a multi-sensor image fusion method based on finite discrete shearlet transform (FDST), multi-scale sequential toggle operator (MSSTO), and an improved pulse-coupled neural networks (PCNN) framework were proposed to fuse information in the visible and infrared spectra to detect defects in challenging conditions. The image fusion performance of the proposed method was evaluated with different indices and compared with other fusion algorithms. The experimental results show that the proposed method achieves satisfactory performance in terms of the averaged information entropy, average gradient, spatial frequency, standard deviation, peak signal-to-noise ratio, and structural similarity, which are 7.979, 0.0405, 29.836, 76.454, 20.078 and 0.748, respectively. Furthermore, the comparison experiments indicate that the proposed method can effectively improve image contrast and richness, enhance the display of image edge contour and texture information, and also retain and fuse the main information in the source image. The research provides a potential solution for defect information fusion and characterization analysis in multi-sensor detection systems in the PBF process.

An Enhanced Approach of Image Steganographic Using Discrete Shearlet Transform and Secret Sharing

Recently, the internet has made the users able to transmit the digital media in the easiest manner. In spite of this facility of the internet, this may lead to several threats that are concerned with confidentiality of transferred media contents such as media authentication and integrity verification. For these reasons, data hiding methods and cryptography are used to protect the contents of digital media. In this paper, an enhanced method of image steganography combined with visual cryptography has been proposed. A secret logo (binary image) of size (128x128) is encrypted by applying (2 out 2 share) visual cryptography on it to generate two secret share. During the embedding process, a cover red, green, and blue (RGB) image of size (512x512) is divided into three layers (red, green and blue). The blue layer is transformed using Discrete Shearlet Transform (DST) to obtain its coefficients. The first secret share is embedded at the coefficients of transformed blue layer to obtain a stego image. At extraction process, the first secret share is extracted from the coefficients of blue layer of the stego image and XORed with the second secret share to generate the original secret logo. According to the experimental results, the proposed method is achieved better imperceptibility for the stego image with the payload capacity equal to (1 bpp). In addition, the secret logo becomes more secured using (2 out 2 share) visual cryptography and the second secret share as a private key.

Discrete Shearlets as a Sparsifying Transform in Low-Rank Plus Sparse Decomposition for Undersampled (k, t)-Space MR Data.

The discrete shearlet transformation accurately represents the discontinuities and edges occurring in magnetic resonance imaging, providing an excellent option of a sparsifying transform. In the present paper, we examine the use of discrete shearlets over other sparsifying transforms in a low-rank plus sparse decomposition problem, denoted by . The proposed algorithm is evaluated on simulated dynamic contrast enhanced (DCE) and small bowel data. For the small bowel, eight subjects were scanned; the sequence was run first on breath-holding and subsequently on free-breathing, without changing the anatomical position of the subject. The reconstruction performance of the proposed algorithm was evaluated against k-t FOCUSS. decomposition, using discrete shearlets as sparsifying transforms, successfully separated the low-rank (background and periodic motion) from the sparse component (enhancement or bowel motility) for both DCE and small bowel data. Motion estimated from low-rank of DCE data is closer to ground truth deformations than motion estimated from L and S. Motility metrics derived from the S component of free-breathing data were not significantly different from the ones from breath-holding data up to four-fold undersampling, indicating that bowel (rapid/random) motility is isolated in S. Our work strongly supports the use of discrete shearlets as a sparsifying transform in a decomposition for undersampled MR data.

Secured Medical Data Transfer Using Reverse Data Hiding System Through Steganography

Reversible Data Hiding (RDH) is the process of transferring secret data hidden inside cover media to the recipient so the recipient can securely retrieve both the secret data and cover media. The RDH approach is applied in this study in the field of telemedicine, and medical-secret data is conveyed privately via medical cover video. Morse code-based data encryption technique tends to encrypt the medical-secret data by compression using the Arithmetic coding technique. Discrete Shearlet transform (DST) compresses the selected frame from the medical cover video and the compressed secret data is embedded into the compressed frame using logical operations. On a receiver side, the reversal process is carried over and the original cover frame will be retrieved from the stego frame after secret medical data is retrieved. Password is included on the receiver side for authentication purposes. Parameters such as encryption time, compression ratio, Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR) are calculated and at the maximum iteration of the proposed algorithm, the highest PSNR value is achieved. In terms of Structural Similarity Index Measure (SSIM), a linear increase from 0.91 to 0.99 is evident for iterations. In comparison with other techniques, the proposed algorithm reaches a higher SSIM of 0.999 after the maximum number of iterations. Thus, the proposed method provides more security and authentication to the recipient.

A Robust NIfTI Image Authentication Framework Based on DST and Multi-Scale Otsu Thresholding

Telemedicine has been intensely promoted in the present pandemic situation of COVID-19 to maintain a strategic distance from the infected person. Several medical tests were used to detect the coronavirus, including antigen, RT-PCR, and a lung CT scan. Only a lung CT-Scan can detect the coronavirus and provide information about the lung infection. As a result, digital imaging plays a critical role in the current pandemic situation. Teleradiology allows for the communication of digital medical images of patients over the internet for diagnosis. A lung CT-Scan test is currently being performed on billions of people to detect COVID-19. These images were sent via the internet for diagnosis and research purposes. The NIfTI image file (.nii extension) was created by the CT-Scanner and contains multiple slices of the lungs. As a result, radiologists determine that the received image has not been tempered during transmission, posing a critical authenticity problem when transmitting these images over the internet. As a result, the researchers are more concerned about the integrity and authenticity of these images in teleradiology. This paper proposes a blind, robust watermarking scheme for lung CT-Scan NIfTI images to address this issue. We use Otsu’s image segmentation algorithm in the proposed scheme to identify the slice with the least amount of medical information for watermark embedding. The proposed scheme employs the Discrete Shearlet Transform (DST), Lifting Wavelet Transform (LWT), and Schur decomposition to embed the encrypted watermark. Watermarks are encrypted using the Affine Transform. The experimental results show that watermarked slice has been tainted by the addition of various sorts of noise, including salt-and-pepper noise, compression, Gaussian noise, speckle noise, and motion blur. After an attack, a watermark is retrieved, and the NC values of extracted watermarks are 0.99623 for Salt and pepper noise, 0.96964 for Gaussian noise, 0.99014 for Speckle noise. The proposed scheme was put to the test with a variety of attacks and produced significant results.

Comparative Study on MATLAB based JPEG Image Size Reduction Using Discrete Cosine Transform and Shearlet Transform for Mammogram Images with Potential Hospital Data Storage Applications

Aim: The aim of this study was to compare Discrete cosine transform and Shearlet transform for mammographic image compression and determine better transform among them. Materials and methods: Sample mammographic images were collected- DCT (30) and Shearlet (30) for compression. Compression ratio was calculated by comparing the original and compressed image size. The significance of the data were calculated using SPSS software. Result: There was a statistical significance between DCT and shearlet based compression ratio data (p=0.035) deviation independent sample t test). Conclusion: DCT based compression ratio was higher (2.41) than the shearlet transforms (0.73). Hence, proving to be a better compression transform than its counterpart (shearlet).

DSTnet: a new discrete shearlet transform-based CNN model for image denoising

Due to the superior performance and fast running speed, deep learning methods have been widely employed in image processing fields. However, most deep learning-based denoising methods require a specific noise level to train their models, and denoising models are built to remove specific levels of noise, which lacks the flexibility to deal with spatially variant noise. In this paper, we present a discrete shearlet transform (DST)-based denoising convolutional network (DSTnet). The proposed method first decomposes an image by DST and gets several subband images, then these subband images are used as input samples into the convolutional neural networks (CNNs) blocks. The proposed method has a good compromise between denoising performance and computation time. The DSTnet not only has a good efficiency in noise removing and detail preservation but also has the ability to handle a wide range of noise levels, which are suitable for real image denoising.

An efficient face recognition approach combining likelihood-based sufficient dimension reduction and LDA

In this paper, an efficient approach is proposed for face recognition (FR) under pose and illumination variations. It is based on combining likelihood-based sufficient dimension reduction (LSDR) and linear discriminant analysis (LDA) using different facial features. LDA is a well–established technique for dimensionality reduction, while LSDR is a relatively new supervised subspace learning method based on the key concept of sufficiency, and consists of estimating a central subspace for low-dimensional representation of facial images. We show, empirically, that this combination can obviously increase the separability between face classes. The facial features that were considered here are either engineered (hand-crafted) features (e.g., discrete shearlet transform coefficients) or learned features which are obtained by retraining a deep learning-based system called FaceNet. To assess the performance of the proposed approach, different classification methods were used during the evaluation phase, namely collaborative representation based classifier (CRC), KNN, linear SVM and three regression-based classifiers (LSRC, LRC and LDRC). The extensive experiments performed on four publicly available face databases – the extended Yale B, FERET, LFW and CMU Multi-PIE– have demonstrated that, on the one hand, LSDR is an effective and efficiency dimensionality reduction technique for face recognition. Particularly, it can be used to significantly increase the performance of a deep learning-based system such as FaceNet, mainly, when training samples are insufficient. On the other hand, its combination with LDA can outperform best individual face recognition algorithm based on LSDR or LDA. Furthermore, the proposed approach compares favorably to current state-of-the-art methods on face recognition, in terms of classification accuracy, under illumination and pose variations.

Fast Convergence of the Two Dimensional Discrete Shearlet Transform

The 2D discrete shearlet transform for a given function f in L2(R2) has been defined through dilation, shear and translation parameters in such a way that the continuity of f at (0, 0) can be studied by means of the convergence of the discrete shearlet transformas the dilation parameter converges to zero. Computer experiments illustrate this property by detecting edges in images that correspond to discontinuities.

Γ-convergence of a shearlet-based Ginzburg–Landau energy

We introduce two shearlet-based Ginzburg–Landau energies, based on the continuous and the discrete shearlet transform. The energies result from replacing the elastic energy term of a classical Ginzburg–Landau energy by the weighted L 2 -norm of a shearlet transform. The asymptotic behaviour of sequences of these energies is analysed within the framework of Γ-convergence and the limit energy is identified. We show that the limit energy of a characteristic function is an anisotropic surface integral over the interfaces of that function. We demonstrate that the anisotropy of the limit energy can be controlled by weighting the underlying shearlet transforms according to their directional parameter.

A Novel Hybrid Transform approach with integration of Fast Fourier, Discrete Wavelet and Discrete Shearlet Transforms for prediction of surface roughness on machined surfaces

Abstract Milled surfaces contain features of geometrically similar appearances under various magnifications in different orientations. Fourier transform is useful in obtaining accurate information from periodic data than wavelets, wavelets are effective in handling multi-resolution data than fourier transform, shearlets show much higher directional sensitivity than both fourier transform and wavelets but are computationally complex. Hence a novel hybrid transform approach with integration of Fast Fourier Transform (FFT), Discrete Wavelet Transform (DWT) and Discrete Shearlet Transform (DST) to characterize surface roughness on machined surfaces is presented. For the experimentation, Taguchi’s L9 orthogonal array was used on Computer Numerical Control (CNC) mill with High Speed Steel (HSS) end mill to machine aluminum 3025 alloy work samples. The Artificial Neural Network is trained with cutting parameters, vision parameters as input and the experimental surface roughness (Ra, Rq, Rz) as output. The validation results of proposed models show better performance with reasonable accuracy.