Low Frequency Wavelet Coefficients Research Articles

A Novel Motor Fault Diagnosis Method Based on Generative Adversarial Learning with Distribution Fusion of Discrete Working Conditions

Many kinds of electrical equipment are used in civil and building engineering. The motor is one of the main power components of this electrical equipment, which can provide stable power output. During the long-term use of motors, various motor faults may occur, which affects the normal use of electrical equipment and even causes accidents. It is significant to apply fault diagnosis for the motors at the construction site. Aiming at the problem that signal data of faulty motor lack diversity, this research designs a multi-layer perceptron Wasserstein generative adversarial network, which is used to enhance training data through distribution fusion. A discrete wavelet decomposition algorithm is employed to extract the low-frequency wavelet coefficients from the original motor current signals. These are used to train the multi-layer perceptron Wasserstein generative adversarial model. Then, the trained model is applied to generate fake current wavelet coefficients with the fused distribution. A motor fault classification model consisting of a feature extractor and pattern recognizer is built based on perceptron. The data augmentation experiment shows that the fake dataset has a larger distribution than the real dataset. The classification model trained on a real dataset, fake dataset and combined dataset achieves 21.5%, 87.2%, and 90.1% prediction accuracy on the unseen real data, respectively. The results indicate that the proposed data augmentation method can effectively generate fake data with the fused distribution. The motor fault classification model trained on a fake dataset has better generalization performance than that trained on a real dataset.

MLWAN: Multi-Scale Learning Wavelet Attention Module Network for Image Super Resolution

Image super resolution (SR) is an important image processing technique in computer vision to improve the resolution of images and videos. In recent years, deep convolutional neural network (CNN) has made significant progress in the field of image SR; however, the existing CNN-based SR methods cannot fully search for background information in the measurement of feature extraction. In addition, in most cases, different scale factors of image SR are assumed to be different assignments and completed by training different models, which does not meet the actual application requirements. To solve these problems, we propose a multi-scale learning wavelet attention network (MLWAN) model for image SR. Specifically, the proposed model consists of three parts. In the first part, low-level features are extracted from the input image through two convolutional layers, and then a new channel-spatial attention mechanism (CSAM) block is concatenated. In the second part, CNN is used to predict the highest-level low-frequency wavelet coefficients, and the third part uses recursive neural networks (RNN) with different scales to predict the wavelet coefficients of the remaining subbands. In order to further achieve lightweight, an effective channel attention recurrent module (ECARM) is proposed to reduce network parameters. Finally, the inverse discrete wavelet transform (IDWT) is used to reconstruct HR image. Experimental results on public large-scale datasets demonstrate the superiority of the proposed model in terms of quantitative indicators and visual effects.

Robust Watermarking Method for Secure Transmission of Medical Images in EHR Systems

Confidentiality of Electronic Health Record (EHR) and privacy are two important security requirements for healthcare systems. Many devices on the EHR network utilize little or no encryption, which makes data in transit vulnerable to exploitative attacks, such as Man-in-the-Middle and other filtration methods. Recently, watermarking algorithms as an efficient response to these requirements is in the underline. In this paper, we present a robust watermarking method conceived as part of an Electronic Health Record platform. In this method a chaotic encryption and blind medical image watermarking technique was incorporated into the system as an authorization mechanism to ensure confidentiality and integrity of electronic health information. We present a hybrid watermarking method based on a combination of discrete wavelet transform (DWT), hessenberg Decomposition (HD), Singular value decomposition (SVD) and an original chaos crypto system based on the Arnold Transform (AT) of Singular Value Decomposition. In order to spread the robustness of our algorithm and provide additional security, an improved SVD-AT embedding and extraction procedure has been used to scramble the EHR data in the preprocessing step of the proposed method. In the process of watermark embedding, an R-level discrete wavelet transform was applied to the host image. The low frequency wavelet coefficients are selected to carry this scrambled-watermark. In extraction process, the stored used plain image is obtained from the trusted authority server to complete the verification process. The receiver should compare the unsigned watermark with the extracted watermark again. The verification can be done before clinical procedures and diagnosis. The proposed watermarking method endures entirety attacks and rightly extracts the hidden watermark without significant degradation in the image quality, thus, when the Peak Signal to Noise Ratio (PSNR) and Normalized Correlation (NC) performance of the proposed algorithm is performed.

Analysis of the Correlation Properties of the Wavelet Transform Coefficients of Typical Images

The increasing flow of photo and video information transmitted through the channels of infocommunication systems and complexes stimulates the search for effective compression algorithms that can significantly reduce the volume of transmitted traffic, while maintaining its quality. In the general case, the compression algorithms are based on the operations of converting the correlated brightness values of the pixels of the image matrix into their uncorrelated parameters, followed by encoding the obtained conversion coefficients. Since the main known decorrelating transformations are quasi-optimal, the task of finding transformations that take into account changes in the statistical characteristics of compressed video data is still relevant. These circumstances determined the direction of the study, related to the analysis of the decorrelating properties of the generated wavelet coefficients obtained as a result of multi-scale image transformation. The main result of the study was to establish the fact that the wavelet coefficients of the multi-scale transformation have the structure of nested matrices defined as submatrices. Therefore, it is advisable to carry out the correlation analysis of the wavelet transformation coefficients separately for the elements of each submatrix at each level of decomposition (decomposition). The main theoretical result is the proof that the core of each subsequent level of the multi-scale transformation is a matrix consisting of the wavelet coefficients of the previous level of decomposition. It is this fact that makes it possible to draw a conclusion about the dependence of the corresponding elements of neighboring levels. In addition, it has been found that there is a linear relationship between the wavelet coefficients within the local area of ​​the image with a size of 8×8 pixels. In this case, the maximum correlation of submatrix elements is directly determined by the form of their representation, and is observed between neighboring elements located, respectively, in a row, column or diagonally, which is confirmed by the nature of the scattering. The obtained results were confirmed by the analysis of samples from more than two hundred typical images. At the same time, it is substantiated that between the low-frequency wavelet coefficients of the multi-scale transformation of the upper level of the expansion, approximately the same dependences are preserved uniformly in all directions. The practical significance of the study is determined by the fact that all the results obtained in the course of its implementation confirm the presence of characteristic dependencies between the wavelet transform coefficients at different levels of image decomposition. This fact indicates the possibility of achieving higher compression ratios of video data in the course of their encoding. The authors associate further research with the development of a mathematical model for adaptive arithmetic coding of video data and images, which takes into account the correlation properties of wavelet coefficients of a multi-scale transformation.

Nonlocal Low-Rank and Prior Image-Based Reconstruction in a Wavelet Tight Frame Using Limited-Angle Projection Data

Computed tomography (CT) reconstruction for limited-angle projection data is an ill-posed inverse problem, that often produces artifacts near the edges of an image. In this study, a hybrid minimization model based on a nonlocal low-rank approximation and a prior image in a wavelet tight framework is proposed to improve reconstructions from limited-angle projections. Low-frequency wavelet coefficients of the reconstructed image were estimated using a nonlocal low-rank approximation and the $l_{2}$ norm minimization was applied to the difference between the high-frequency components of a prior image and the reconstructed image. In addition, the alternative direction method of multipliers (ADMM) was used for alternately minimization to solve two regularization terms which produce the most parameters. Experimental results demonstrated that the proposed algorithm offers several advantages over conventional iterative reconstruction techniques, including faster convergence, suppression of limited-angle artifacts, noise reduction, and the preservation of edges and other image details. This study represents the first time that nonlocal low-rank prior information has been applied to limited-angle CT.

Multi-Scale Image Super-Resolution Via a Single Extendable Deep Network

Deep neural networks have achieved remarkable success in single image super-resolution (SISR). However, in most cases, image SR with different scale factors is considered as different tasks and solved by training specific models. It makes the image SR applications inefficient and tedious. Hence, to tackle these problems, we propose a lightweight and fast network (MSWSR) to implement multi-scale SR simultaneously by learning multi-level wavelet coefficients of the target image. The proposed network is composed of one CNN part and one RNN part. The CNN part is used for predicting the highest-level low-frequency wavelet coefficients, while the RNN part is used for predicting the rest frequency bands of wavelet coefficients. Moreover, the RNN part is extendable to more scales. For further lightweight, a non-square (side window) convolution kernel is proposed to reduce the network parameters. Experiments on commonly-used datasets demonstrate that the proposed method achieves favorable reconstruction performance with a fast speed and lightweight network. The code is available at https://github.com/FVL2020/MSWSR.

Characteristic of Five Subpopulation Leukocytes in Single-Cell Levels Based on Partial Principal Component Analysis Coupled with Raman Spectroscopy.

Characteristics of five subpopulation leukocytes in single-cell levels based on partial principal component analysis coupled with Raman spectroscopy were proposed to recognize the biochemical features of five subpopulation leukocytes. Using wavelet transform, the reconstructed spectra of the low-frequency wavelet coefficients were used to perform multiple principal component analysis based on segmented spectral data wreathing cover at 720-800 cm-1, 840-994 cm-1, and 1010-1070 cm-1 wavenumbers, respectively. Our approach is promising since it enables to establish a better understanding of the underlying molecular difference between the subtypes of leukocytes in a label-free manner and to estimate the source of infection.

Research on ultrasound image of interventional catheterization processing method based on wavelet transform and fuzzy theory

Interventional catheterization can help patients to accurately assess the condition, early diagnosis and intervention. Confirming the location of catheter by ultrasound has the advantages of real-time imaging, non-invasive, radiative, fast and convenient. Due to speckle noise and similar acoustic impedance, ultrasound images are not clear. In this paper an ultrasonic image processing algorithm based on wavelet transform and fuzzy theory is proposed. First, logarithmic transformation of ultrasound images is used to convert multiplicative noise into additive noise. Then the wavelet coefficients of the image are obtained by multiscale wavelet transform. The high frequency wavelet coefficients of the image are denoised by thresholding, and the low-frequency wavelet coefficients of the image are processed by fuzzy enhancement. Finally, the processed image is obtained through wavelet reconstruction and exponential transformation. Experiments show that this proposed method can effectively improve the visual effect of images.

Embedding with Pca Based Svd Framelet Transform with Visual Cryptography In Video

The goal of watermarking or steganography is not to restrict access to the original image, to ensure that embedded data remain recoverable. Digital watermarking is a technique providing embedded secure information in images, digital watermarking is the process of inserting data into an image in a way that it can be used to make an assertion about the image. But the proposed system studies a comprehensive approach of embedding secret information inside the video. A hybrid video steganographic scheme based on Framelet transform (FT) with Principal Component Analysis (PCA) is introduced. The main purpose of using PCA is to reduce correlation among wavelet coefficients from wavelet decomposition of each video frame. Using this decomposition, the secret message can be dispersed into the uncorrelated coefficients. Framelet transform helps to decompose video file into several frames. The secret message is embedded inside the principal components of low frequency wavelet coefficients. Achieving high bit rate data embedding is the main task. The proposed system is robust against numerous attacks like geometric attack, filtering, contrast adjustment. After embedding the secret information , (2,2_VSSS) as Visual cryptographic encryption is implemented to maintain the secrecy of this information against hackers.The main aim of this study is to obtain impercibility which is the human eye may not be able to detect differences between the original video and reconstructed image. Even after embedding, the quality of the stego image is good, which is proved by achieving better a PSNR value, and the stego image does not give much variation irrespective of different imaging conditions in the proposed VDWT mechanism. The proposed method achieves high PSNR than the existing methods, and nominal computational time is achieved for retrieving the secret information.

Robust image watermarking using sample area quantization

Digital watermarking is a way to protect the intellectual property of digital media. Among different algorithms, Quantization Index Modulation (QIM) is one of the popular methods in designing a watermark system. In this paper, a sample area quantization method is proposed for robust watermarking of digital images. First, the samples of the host signal form a polygon and low frequency wavelet coefficients of the carrier image is considered as the host sample. A watermark digit is embedded by quantizing the area of the polygon. Then, in order to minimize the distortion, the watermarked samples are obtained as close as possible to the host samples by solving an optimization problem while maintaining the quantized area at its fixed value. The optimization problem is solved using the gradient descend method. Finally, a maximum likelihood detector is designed to extract the watermark digits, assuming a Gaussian distribution for the host signal samples. The performance of the proposed method is theoretically obtained in terms of error probability in the presence of additive white Gaussian noise. Theoretical results are verified using simulation with artificial signals. The proposed method is compared to the state-of-the-art method under different attacks including: noise addition, JPEG compression, filtering, and geometrical attacks. The results confirm that the proposed method outperforms the other ones in terms of error probability against different attacks. The results also show that in the trade-off between robustness, distortion and capacity, by decreasing capacity the two other factors could be improved simultaneously.

MEMS gyroscope wavelet de-noising method based on redundancy and sparse representation

Since the wavelet analysis does not need exact noise model, wavelet decomposition is suitable for analyzing the signal with complex noise characteristics. In this paper, a real-time wavelet de-noising method is used for the error compensation of MEMS gyroscope. In order to avoid the shortcomings that wavelet threshold processing ignores the wavelet coefficient integrity, the sparse and redundant representation methods are used to optimize the wavelet coefficients. The reverse use of compressed sensing algorithm represents the low-frequency wavelet coefficients redundantly, and optimizes the sparse coefficients, and then reconstructs the low-frequency wavelet coefficients. The sparse representation method is used to sparsely represent the high-frequency wavelet coefficients, and the high-frequency wavelet coefficients are optimized. Then the optimized high and low frequency wavelet coefficients are used to reconstruct the original signal and the lag correction algorithm is used to reduce the boundary effect of wavelet decomposition. Finally, the feasibility of the algorithm is verified by simulation and experiments, which provides a new idea for wavelet de-noising.

Study on image feature recognition algorithm and its application in public security management

Public security is the topic of common concern of the government and the common people. In order to solve the puzzle of image distortion, being complex in algorithm and being difficult to take into account of the overall structure and details of the image in the image recognition algorithm of public security management system, the paper presented a fusion algorithm of texture consistency measure based on bi-orthogonal wavelet transform. By means of the orthogonal wavelet transform, the wavelet transform is used to decompose the source image, and then the low frequency and high frequency wavelet coefficient matrix of the fused image is determined according to a certain proportion and texture measure, thus the fusion image is obtained. The experimental results show that the algorithm can not only distinguish the false edges of the image, but also enrich the details of the image and take into account the overall visual image, so it can better improve the recognition effect of the image in the public security management system.

Determination of gel time and gel point of epoxy-amine thermosets by in-situ near infrared spectroscopy

A method of near-infrared spectroscopy combined with wavelet transform was proposed to determine in-situ the gel time and gel point of epoxy resin simultaneously. The reconstructed spectra of the low-frequency wavelet coefficients were used for determination of gel time, and the reconstructed spectra of some detail coefficients which are dominated by chemical information for determination of epoxy conversion. In-situ determination of gel point has been achieved using evolutionary near infrared spectra of epoxy curing. The accuracy of gel point achived to 0.01. Compared with the traditional determination method of gel point, in which TMA and DSC are respectively used for gel time and conversion, this method not only can determine in-situ gel time and conversion degree simultaneously, and remarkably improve accuracy of the gel point result but also is of low cost, and fast and easy to operate.

An Image Watermarking Algorithm Based on Discrete Hopfield Neural Network Encryption

With the rapid development of science and information technology, it is more and more important to design a robust image watermarking algorithm to protect the intellectual property and information security of images. First of all, this paper encrypts the watermark information to improve the security of the watermarking algorithm through discrete Hopfield neural network based on chaos. Then, based on the image wavelet decomposition, the watermark information is embedded into the low and middle frequency wavelet coefficients according to the minimum Visual error and pixel position distortion. Experiments show that the algorithm has good security, robustness and invisibility.

Change Detection Algorithm Based on Discrete Wavelet Transforms and Neighborhood Fuzzy C-Means

A new algorithm on Discrete Wavelet Transform (DWT) and neighborhood FCM is proposed to detect change area from remote sensing image. First, the subtraction and ratio image are obtained by the subtraction and ratio method from the two registered remote sensing images; Then, the DWT is applied to the subtraction and ratio image, the region intensity-based and energy-based fusion rules is adopted to the low frequency and high frequency wavelet coefficients, and the inverse DWT is used to obtain the final difference image; At last, the neighborhood FCM is carried out to get the change areas, the spatial distance information and gray difference information are considered in the objective function of FCM, which could avoid misclassification and enhance the detection probability. Experimental results show that the proposed algorithm has strong ability to suppress noise and good detection results; the detection probability of unban change area can reach to 98.45%, whereas, the detection probability is up to 87.5% for the discontinuous forest change area.

Comparative Study of Image Reconstruction Based on Compressive Sensing

Compressive sensing based image reconstruction that improves the algorithm to applying different approach which is DWT and DCT. First, by using wavelet transform, wavelet low frequency of the sub bands in which the image is decomposed in to low frequency and high frequency wavelet coefficients, second is to applied DCT on low frequency coordinates and construct the different transformation matrix. Use the measurement matrix measure the high frequency coefficient components and combine with DCT low frequency components image and sparse signal output is applied on compressive sensing. In compressive sensing, random measurement matrices are generally used and ?1minimisation algorithms often use linear programming to cover sparse signal vectors. But explicitly constructible measurement matrices providing performance guarantees were and ?1minimisation algorithms are often demanding in computational complexity for applications involving very large problem dimensions. To improve the PSNR (pick signal to noise ratio) of reconstructions image uses different coding such as Huffman and Arithmetic.

A high-performance speech perceptual hashing authentication algorithm based on discrete wavelet transform and measurement matrix

Aiming at the problems of existing speech authentication algorithms, such as poor robustness and discrimination, security vulnerability, low efficiency, poor ability of tamper detection and localization, a high-performance speech perceptual hashing authentication algorithm based on Discrete Wavelet Transform (DWT) and measurement matrix is proposed in this paper. Firstly, the speech signal is conducted with DWT by applying preprocessing, and the low-frequency wavelet coefficients are regarded as the perceptual feature value. Then the measurement matrix controlled by chaos map is applied to reduce the dimension of feature value. Finally, the feature value is used to generate the perceptual hash sequence by the process of hashing structure. The measurement matrix is designed as the secret key to enhance the security of the proposed algorithm. The experimental results demonstrates the proposed algorithm has high efficiency in perceptual robustness, discrimination, time consumption and security, as well as having a high accuracy of tampering detection and localization.

Integer Wavelet-Based Image Interpolation in Lifting Structure for Image Resolution Enhancement

A floating-point wavelet-based and an integer wavelet-based image interpolations in lifting structures and polynomial curve fitting for image resolution enhancement are proposed in this paper. The proposed prediction methods estimate high-frequency wavelet coefficients of the original image based on the available low-frequency wavelet coefficients, so that the original image can be reconstructed by using the proposed prediction method. To further improve the reconstruction performance, we use polynomial curve fitting to build relationships between actual high-frequency wavelet coefficients and estimated high-frequency wavelet coefficients. Results of the proposed prediction algorithm for different wavelet transforms are compared to show the proposed prediction algorithm outperforms other methods.

Multimodality image fusion using centre-based genetic algorithm and fuzzy logic

The Fusion method is used to detect and treatment for the disease in a successful manner which integrates various modalities. Nowadays, medical image fusion system is a demanding task in healthcare applications such as tumour detection, analysis, research, and treatment. In this paper, we propose a multimodality medical image fusion using Centre-Based Genetic Algorithm (CBGA) and fuzzy logic which is examined by the use of the quantitative measure. Here, at first, we estimate the segmentation map from the source images (MRI and CT). After that, the source images are decomposed based on lifting wavelet transform. Then, a fuzzy-based approach is used to fuse high-frequency wavelet coefficients of the MRI and CT images. Mainly, the output of three various fusion rules incorporated by fuzzy logic (weighted averaging, selection using Pixel-Based Decision Map; PDM, and selection using Region-Based Decision Map; RDM), based on a dissimilarity measure of the source images. Then a CBGA is used to fuse the low-frequency wavelet coefficient of the MRI and CT images. At last, we combine low- and high-frequency wavelet coefficients of the source images to obtain the fused image.

Threshold selection method for UWB TOA estimation based on wavelet decomposition and kurtosis analysis

In wireless sensor networks, ranging or positioning via ultra-wideband (UWB) has caused widespread research interests where the non-coherent energy detection (ED) method with low sampling rate and low complexity is widely studied. However, the traditional energy detection methods only analyze the signal energy in the time domain, so their error is relatively large. In this paper, the simulation results show that most of the signal energy concentrates in the low-frequency band, so a novel threshold selection method for time of arrival (TOA) estimation is proposed that analyzes the signals in both time domain and frequency domain. In this method, the received signal is decomposed by “db6” wavelet and the kurtosis of energy blocks of the low-frequency wavelet coefficients (Kc) is analyzed. At last, the mapping relationship between Kc and the normalized threshold for TOA estimation is created using polynomial fitting with degree 3. The simulation results show that the TOA estimation error of the proposed method is significantly less than the method without wavelet decomposition.