Wavelet Image Research Articles

A novel radiomics signature based on T2-weighted imaging accurately predicts hepatic inflammation in individuals with biopsy-proven nonalcoholic fatty liver disease: a derivation and independent validation study.

Currently, there are no effective methods for assessing hepatic inflammation without resorting to histological examination of liver tissue obtained by biopsy. T2-weighted images (T2WI) are routinely obtained from liver magnetic resonance imaging (MRI) scan sequences. We aimed to establish a radiomics signature based on T2WI (T2-RS) for assessment of hepatic inflammation in people with nonalcoholic fatty liver disease (NAFLD). A total of 203 individuals with biopsy-confirmed NAFLD from two independent Chinese cohorts with liver MRI examination were enrolled in this study. The hepatic inflammatory activity score (IAS) was calculated by the unweighted sum of the histologic scores for lobular inflammation and ballooning. One thousand and thirty-two radiomics features were extracted from the localized region of interest (ROI) in the right liver lobe of T2WI and, subsequently, selected by minimum redundancy maximum relevance and least absolute shrinkage and selection operator (LASSO) methods. The T2-RS was calculated by adding the selected features weighted by their coefficients. Eighteen radiomics features from Laplacian of Gaussian, wavelet, and original images were selected for establishing T2-RS. The T2-RS value differed significantly between groups with increasing grades of hepatic inflammation (P<0.01). The T2-RS yielded an area under the receiver operating characteristic (ROC) curve (AUROC) of 0.80 [95% confidence interval (CI): 0.71-0.89] for predicting hepatic inflammation in the training cohort with excellent calibration. The AUROCs of T2-RS in the internal cohort and external validation cohorts were 0.77 (0.61-0.93) and 0.75 (0.63-0.84), respectively. The T2-RS derived from radiomics analysis of T2WI shows promising utility for predicting hepatic inflammation in individuals with NAFLD.

Robustness and reproducibility of radiomics in T2 weighted images from magnetic resonance image guided linear accelerator in a phantom study

PurposeQuantitative radiomics features extracted from medical images have been shown to provide value in predicting clinical outcomes. The study for robustness and reproducibility of radiomics features obtained with magnetic resonance image guided linear accelerator (MR-Linac) is insufficient. The objective of this work was to investigate the stability of radiomics features extracted from T2-weighted images of MR-Linac for five common effect factors. Materials and methodIn this work, ten jellies, five fruits/vegetables, and a dynamic phantom were used to evaluate the impact of test–retest, intraobserver, varied thicknesses, radiation, and motion. These phantoms were scanned on a 1.5 T MRI system of MR-Linac. For test–retest data, the phantoms were scanned twice with repositioning within 15 min. To assess for intraobserver comparison, the segmentation of MR images was repeated by one observer in a double-blind manner. Three slice thicknesses (1.2 mm, 2.4 mm, and 4.8 mm) were used to select robust features that were insensitive to different thicknesses. The effect of radiation on features was studied by acquiring images when the beam was on. Common movement images of patients during radiotherapy were simulated by a dynamic phantom with five motion states to study the motion effect. A total of 1409 radiomics features, including shape features, first-order features, and texture features, were extracted from the original, wavelet, square, logarithmic, exponential and gradient images. The robustness and reproducibility features were evaluated using the concordance correlation coefficient (CCC). ResultThe intraobserver group had the most robust features (936/1079, 86.7%), while the group of motion effects had the lowest robustness (56/936, 6.0%), followed by the group of different thickness cohorts (374/936, 40.0%). The stability of features in the test–retest and radiation groups was 1072 of 1312 (81.7%) and 810 of 936 (86.5%), respectively. Overall, 25 of 1409 (2.4%) radiomics features remained robust in all five tests, mostly focusing on the image type of the wavelet. The number of stable features extracted from when the beam was on was less than that extracted when the beam was off. Shape features were the most robust of all of the features in all of the groups, excluding the motion group. ConclusionCompared with other factors fewer features remained robust to the effect of motion. This result emphasizes the need to consider the effect of respiration motion. The study for T2-weighted images from MR-Linac under different conditions will help us to build a robust predictive model applicable for radiotherapy.

Distributed Optical Fiber Sensing System for Large Infrastructure Temperature Monitoring

In this article, a distributed optical fiber sensing system for large infrastructure temperature monitoring is proposed. To meet the requirements of monitoring networks in terms of measurement accuracy, spatial resolution, and real-time or quasireal-time performance, a quaternion wavelet transform (QWT) image denoising algorithm is proposed to address the original edge node data for the structural monitoring networks of large infrastructures. A distributed Brillouin optical time-domain analysis (BOTDA) sensing system with a 40-km sensing fiber is established. The raw Brillouin gain spectrum (BGS) image is decomposed into one magnitude image and three phase images by QWT. The phase images of the OWT are distributed randomly and disorderly with respect to the noise, while the magnitude image of the quaternion wavelet is greatly affected by the noise. The useful message energy of the magnitude image is concentrated on a small number of coefficients with large amplitude, while the noise mainly corresponds to the coefficients with smaller amplitude. Then, the Bayes shrink threshold method is introduced to filter out noise in the magnitude image. The results indicate that the signal-to-noise ratio (SNR) and the frequency uncertainty have been improved significantly. The accuracy of the retrieved Brillouin frequency shift from denoised BGS images reaches 0.2 MHz, which corresponds to a temperature error of ±0.1 °C. Less than 4 s are required to process a BGS image with 50 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 40 000 pixels by the QWT denoising technique. The uploaded data obtained from 40 M bytes of raw data are reduced to 0.08 M bytes for each measurement. We hope that with technological progress and algorithm optimization, the distributed optical fiber sensing system based on the QWT image denoising algorithm will have an important role in the real-time application of large-scale infrastructure structural health monitoring for the Internet of Things.

Resting-state electroencephalography based deep-learning for the detection of Parkinson's disease.

Parkinson’s disease (PD) is one of the most serious and challenging neurodegenerative disorders to diagnose. Clinical diagnosis on observing motor symptoms is the gold standard, yet by this point nerve cells are degenerated resulting in a lower efficacy of therapeutic treatments. In this study, we introduce a deep-learning approach based on a recently-proposed 20-Layer Convolutional Neural Network (CNN) applied on the visual realization of the Wavelet domain of a resting-state EEG. The proposed approach was able to efficiently and accurately detect PD as well as distinguish subjects with PD on medications from subjects who are off medication. The gradient-weighted class activation mapping (Grad-CAM) was used to visualize the features based on which the approach provided the predictions. A significantly high accuracy, sensitivity, specificity, AUC, and Weighted Kappa Score up to 99.9% were achieved and the visualization of the regions in the Wavelet images that contributed to the deep-learning approach decisions was provided. The proposed framework can then serve as an effective computer-aided diagnostic tool that will support physicians and scientists in further understanding the nature of PD and providing an objective and confident opinion regarding the clinical diagnosis of the disease.

CNN Deep Learning with Wavelet Image Fusion of CCD RGB-IR and Depth-Grayscale Sensor Data for Hand Gesture Intention Recognition.

Pixel-based images captured by a charge-coupled device (CCD) with infrared (IR) LEDs around the image sensor are the well-known CCD Red–Green–Blue IR (the so-called CCD RGB-IR) data. The CCD RGB-IR data are generally acquired for video surveillance applications. Currently, CCD RGB-IR information has been further used to perform human gesture recognition on surveillance. Gesture recognition, including hand gesture intention recognition, is attracting great attention in the field of deep neural network (DNN) calculations. For further enhancing conventional CCD RGB-IR gesture recognition by DNN, this work proposes a deep learning framework for gesture recognition where a convolution neural network (CNN) incorporated with wavelet image fusion of CCD RGB-IR and additional depth-based depth-grayscale images (captured from depth sensors of the famous Microsoft Kinect device) is constructed for gesture intention recognition. In the proposed CNN with wavelet image fusion, a five-level discrete wavelet transformation (DWT) with three different wavelet decomposition merge strategies, namely, max-min, min-max and mean-mean, is employed; the visual geometry group (VGG)-16 CNN is used for deep learning and recognition of the wavelet fused gesture images. Experiments on the classifications of ten hand gesture intention actions (specified in a scenario of laboratory interactions) show that by additionally incorporating depth-grayscale data into CCD RGB-IR gesture recognition one will be able to further increase the averaged recognition accuracy to 83.88% for the VGG-16 CNN with min-max wavelet image fusion of the CCD RGB-IR and depth-grayscale data, which is obviously superior to the 75.33% of VGG-16 CNN with only CCD RGB-IR.

Development of a new machine vision algorithm to estimate potato's shape and size based on support vector machine

AbstractDevelopment of a new machine vision‐based algorithm, to estimate potato's shape and size, will have great significance to agricultural industry in developing countries. Machine vision, one of hot technique, uses machines to execute measurement, calculating, and judgment instead of human eyes. In this study, a new machine vision algorithm, based on support vector machine, was proposed for estimating potato's shape and size. After captured the square RGB image with 512 × 512 pixels, the original image was processed by gray scale and linear transformation, filtering, entity, and boundary detecting. Then, geometric characteristics, image wavelet moment, and fractal dimension of boundary were extracted for marking the potato's characteristic. In addition, the effect of four kind of support vector machine (SVM) kernel function was comparing by several experiments with 64 potato samples. By experimental confirmation, SVM based on the polynomial kernel is more suitable for discriminating potato's shape with an accuracy of 88.89%; SVM based on the linear kernel is more suitable for estimating potato's size with an accuracy of 87.41%.Practical applicationsPotato is a high‐yield, nutrient‐rich crop with high nutritional value. This study proposes a potato shape and size estimation algorithm based on machine vision. Through experimental verification, the detection accuracy of the algorithm initially meets the actual engineering application. The shape and size of potatoes can be detected to classify potatoes. In the process of food processing such as potato chips, the classification of potatoes is conducive to improving the quality of food processing.

A proposed brain tumor detection algorithm using Multi wavelet Transform (MWT)

Magnetic resonance imaging)MRI) is a technological development in the medical field. It is used to give images of the human body with high accuracy and good quality, facilitating the process of identifying and classifying diseases in the human body. One of the diseases that are diagnosed using MRI is a brain tumor, MRI which helps in the early diagnosis of the tumor, and helps the doctor to diagnose and identify the tumor and thus make the fastest medical decision. This paper used to identification and extraction of brain tumors from magnetic resonance images based on Multi Wavelet Transform (MWT) and image processing techniques. This project Multi Wavelet Transform (MWT) used in preprocessing stage to enhance the input image and denoising. Thresholding based is used for segmentation methods, classification of brain tumor is done using Statistical Classification Methods to classify the input MRI of brain into normal or abnormal. Firstly the location of tumor was presented & next its area computed.

Bearing Fault Detection in ASD-Powered Induction Machine Using MODWT and Image Edge Detection

Today the industry depends on various types of three-phase induction machines, requiring operating at variable speeds to perform more complex processes. Therefore, it is vital to monitor their operation conditions to maintain the optimal efficiency of the processes they perform and avoid significant economic losses. The proposed work presents the design and development of a method for bearing damage detection based on Maximal Overlap Discrete Wavelet Transform and image processing for edge detection. Accuracies achieved with three types of damage exceed 90%. The signals for the test are acquired from seven different operating conditions for each type of damage. Supply comes from a power grid source and an adjustable speed drive. The Maximal Overlap Discrete Wavelet Transform is applied with different filtering levels to the three phases of the stator current, the magnitude of the filtered signals is acquired, a periodic two-dimensional array is generated and further smoothed by a Gaussian filter allowing the observation of patterns at the edges. Finally, the obtained images are scanned with a 2-D mask aiming to detect and count patterns associated to the fault detection process. Statistical analysis is performed over characteristic signatures obtained from the current magnitude of the three phases at different classes of damage and several mechanical load conditions.

Defogging Algorithm Based on Image Features and Wavelet Transform

Defogging Algorithm Based on Image Features and Wavelet Transform

Применение вейвлет-анализа для исследования интенсивности транспортного потока

The relevance of the work is the specific properties of the wavelet analysis, which make it possible to identify not only the amplitude-scale (frequency) characteristics of the time series under consideration, but also the evolution of these characteristics during the observation time. As a result of the study, it is advisable to identify those indicators of the intensity of traffic flow that may turn out to be indicators of possible problematic situations (congestion, traffic accidents, etc.). It is advisable to use them in the future when regulating and controlling traffic on the basis of processing information about traffic flows that comes from stationary video recording complexes of traffic violations. The object of study is a road with intensive one-way traffic, equipped with a software and hardware complex that allows measuring the characteristics of the flow of motor transport. The subject of the study is the daily intensity of the flow of cars. The purpose of this study is to identify patterns in the indicators evolution obtained using wavelet analysis as a result of processing of the time series of the car traffic intensity on the road network. As a theoretical and methodological approach, the wavelet transforms using the MHat wavelet, and the Morlet wavelet is used. The approach used by the authors allowed us to establish the correspondence of some characteristics obtained during the wavelet analysis with the evolution of the traffic flow intensity function during the daily observation time, which is the scientific novelty of the study. The wavelet analysis of the data of the video surveillance software and hardware complexes obtained during the day allowed us to construct time dependences of amplitude-scale (frequency) indicators of the car traffic intensity on the road connecting the central and rear areas of the city of Perm. As a result of the study of time series, experimental three-dimensional distributions of wavelet images, scalograms, skeletons and scalegrams of the function of the daily intensity of the traffic flow were obtained. An explanation of the characteristic features of the obtained dependencies and their relationship with the initial function of the traffic flow intensity is proposed. The practical significance lies in obtaining amplitude-scale (frequency) characteristics as a result of wavelet analysis of the traffic intensity using MHat and Morlet wavelets, which is of practical interest from the point of view of predicting the movement of vehicles, controlling the operation of traffic lights, monitoring the operation of equipment, etc. The direction of further research is to obtain, process, analyze and generalize the results of performing amplitude-scale wavelet analysis for time series of traffic flow intensity on parts of the road network with different vehicle traffic intensity.

RNS-Based FPGA Accelerators for High-Quality 3D Medical Image Wavelet Processing Using Scaled Filter Coefficients

Medical imaging using different modalities has many problems. The main ones are low informativeness, various distortion noises, and a large amount of information. Fusion, denoising, and visual data compression are used to solve them in practice. Discrete wavelet transform is one way to implement various fusion, denoising, and compression methods for 2D and 3D medical image processing. Medical imaging systems produce increasingly accurate images with scanning technology and digital devices development. These images have improved quality using both higher spatial resolutions and color bit-depth. Processing a large volume of medical imaging data requires considerable resources and processing time. Modern wavelet-based devices for medical image processing do not meet the current performance demand. Hardware accelerators are being designed to solve this problem. This paper proposes new (field-programmable gate array) FPGA accelerators using wavelet processing (WP) with scaled filter coefficients (SFC) and parallel computing in residue number system (RNS) to improve the performance of high-quality 3D medical image WP systems. The computational complexity is reduced using the developed WP method with SFC and the proposed wavelet filter coefficients scaling algorithm. Parallel computing is organized in RNS using moduli sets of a particular type. Hardware implementation of 3D medical image WP using the proposed FPGA accelerators increases device performance by 2.89-3.59 times, increasing the hardware resources by 1.18-3.29 times compared to state-of-the-art solutions. The device performance improvement is achieved while maintaining high-quality 3D medical image processing in peak signal-to-noise ratio terms.

Analysis of image compression methods based on wavelet transforms for maritime applications

The purpose of the article is to develop recommendations for choosing image compression method based on wavelet transformation, depending on image type, quality and compression requirements. Among the wavelet image compression methods, Embedded Zerotree Wavelet coder (EZW) and Set Partition In Hierarchical Trees (SPIHT) are considered, and the Haar wavelet and wavelet transformation in the oriented basis with the first, third, fifth and seventh decomposition levels is used as the base wavelet transform. These compression methods were compared with each other and with the standard JPEG method on the following parameters: mean square error, maximum error, peak to noise ratio, number of bits per pixel, compression ratio, and image size. The proposed methods can be successfully applied in the transmission of seabed relief images obtained from satellites or sea buoys.

Unsupervised radar signal recognition based on multi‐block – Multi‐view Low‐Rank Sparse Subspace Clustering

In the field of radar reconnaissance, unsupervised recognition of radar signals is a particularly important method for classifying different signals and estimating signal parameters. For untagged signals, a new unsupervised recognition method based on the time-frequency (TF) analysis and Multi-view Low-Rank Sparse Subspace Clustering (MLRSSC) is proposed. Specifically, the authors use image wavelet decomposition to create four views for TF images (TFIs), which introduces the concept of multi-view subspace clustering into radar signal recognition. Compared with other advanced clustering algorithms, the authors' algorithm pays more attention to combining the inherent properties of TFIs. Aiming at the unique ridgeline distribution phenomenon of TFI, a multi-block technology capable of robustly distributing TFIs subspaces is proposed. Then, Multi-block and MLRSSC are combined to propose the Multi-block Joint Multi-view Subspace Clustering (M-MLRSSC). The simulation shows that in the TFIs data set with a certain signal-to-noise ratio, M-MLRSSC has obtained superior results, which is better than a variety of advanced subspace clustering algorithms.

Retrieval of nearshore bathymetry from Sentinel-1 SAR data in high energetic wave coasts: The Portuguese case study

The ability to derive bathymetry using remote sensing techniques enables rapid and cost-efficient mapping of large coastal areas. This contribution focuses on the application of both fast Fourier transform (FFT) and wavelet spectral analysis to obtain satellite-derived bathymetry maps of the nearshore, from freely available and easily accessible Sentinel-1 synthetic aperture radar (SAR) data with 10 m pixel resolution. For this purpose, an extension of 220 km of the Portuguese west coast is analyzed using six satellite images obtained during the years 2018, 2019 and 2020. This extension allows to assess the applicability to coastal sectors with distinct geomorphological constraints. The peak wave periods corresponding to the acquisition of these images approximately range between 11 and 16 s. The spectral analysis is carried to estimate the water depths in near-shore water regions from the observed wavelength patterns. This signature of the sea surface, reflected in the variations of the wavelengths, is captured by the satellite images, making it possible to infer the underlying bathymetry. The bathymetric estimates obtained from both methodologies are compared with data extracted from the Coastal Nautical Charts provided by the Portuguese Hydrographic Institute. Wavelet image processing methodology shows very positive results, particularly extending the depth inversion limits of the FFT methodology, allowing to obtain bathymetric data for the entire shoaling zone where the wavelength patterns are visible. The achieved results also highlight that both FFT and wavelet methodologies are dependent from the seabed slope. For gentle slopes, the inferred depths from 2018 SAR images lead to relative errors between 2.5 and 20% when compared with the observed isobaths (10, 20 and 30 m). For steeper slopes, the errors are generally greater than 20% and increase with depth. The capabilities of the wavelet methodology to map shallow marine environments for high energetic coasts seems promising, regarding research purposes and management interventions.

Multi-fault recognition of gear based on wavelet image fusion and deep neural network

The coal mining environment where the plate conveyor is located often has narrow space, violent mechanical vibration, and explosion-proof requirements. Therefore, collecting vibration signals by installing sensors will have adverse problems such as difficult installation, strong noise, and potential safety hazards. In view of the weakness of the gear torsional load in the current signal, this paper proposes using three-phase current signal fusion to extract its phase difference information. At the same time, in order to extract the current information and phase information change caused by the early fault of the scraper conveyor gear, a gear fault diagnosis method based on the deep convolution neural network and three-phase current continuous wavelet image fusion is proposed. This method transforms the gear fault diagnosis problem into an image analysis problem. By fusing the time-frequency images of three-phase current, the phase difference information of the image can be obtained, and then the fluctuation state of motor torque can be determined. Then, the deep convolution neural network model is built to realize the fault feature recognition of the wavelet fusion image.

Digital Video Image Preprocessing Algorithm Based on Embedded System

To solve the massive noise contained in the images acquired under low illumination, we designed a digital video image Preprocessing device with the denoising function. Based on the embedded CPU and operating system, video images are acquired by the camera. The noise contained in the video images is filtered by the improved median filtering algorithm and wavelet image denoising. Subsequently, the images are transmitted through USB and network interface, and the storage function of image files is implemented. The device can remove the noise contained in videos effectively, which is conducive to performing more advanced processing on the images.

Mathematical Modeling for Ceramic Shape 3D Image Based on Deep Learning Algorithm

Ceramic image shape 3D image modeling focuses on of ceramic that was obtained from the camera imaging equipment such as 2D images, by normalization, gray, filtering denoising, wavelet image sharpening edge enhancement, binarization, and shape contour extraction pretreatment processes such as extraction ceramic image shape edge profile, again, according to the image edge extraction and elliptic rotator ceramics phenomenon. The image distortion effect was optimized by self-application, and then the deep learning modeler was used to model the side edge contour. Finally, the 3D ceramic model of the rotating body was restored according to the intersection and central axis of the extracted contour. By studying the existing segmentation methods based on deep learning, the automatic segmentation of target ceramic image and the effect of target edge refinement and optimization are realized. After extracting and separating the target ceramics from the image, we processed the foreground image of the target into a three-dimensional model. In order to reduce the complexity of the model, a 3D contextual sequencing model is adopted to encode the hidden space features along the channel dimensions, to extract the causal correlation between channels. Each module in the compression framework is optimized by a rate-distortion loss function. The experimental results show that the proposed 3D image modeling method has significant advantages in compression performance compared with the optimal 2D 3D image modeling method based on deep learning, and the experimental results show that the performance of the proposed method is superior to JP3D and HEVC methods, especially at low bit rate points.

Statement of retraction: research on digital image wavelet transform filtering optimization processing method based on DSP Internet of Things

Statement of retraction: research on digital image wavelet transform filtering optimization processing method based on DSP Internet of Things

Prior ensemble learning : Theory and application to MR image priors.

Compressed sensing (CS) reduces the measurement time of magnetic resonance (MR) imaging, where the use of regularizers or image priors are key techniques to boost reconstruction precision. The optimal prior generally depends on the subject and the hand-building of priors is hard. A methodology of combining priors to create a better one would be useful for various forms of image processing that use image priors. We propose a theory, called prior ensemble learning (PEL), which combines many weak priors (not limited to images) efficiently and approximates the posterior mean (PM) estimate, which is Bayes optimal for minimizing the mean squared error (MSE). The way of combining priors is changed from that of an exponential family to a mixture family. We applied PEL to an undersampled (10%) multicoil MR image reconstruction task. We demonstrated that PEL could combine 136 image priors (norm-based priors such as total variation (TV) and wavelets with various regularization coefficient (RC) values) from only two training samples and that it was superior to the CS-SENSE-based method in terms of the MSE of the reconstructed image. The resulting combining weights were sparse (18% of the weak priors remained), as expected. By the theory, the PM estimator was decomposed into the sparse weighted sum of each weak prior's PM estimator, and the exponential computational complexity for RCs was reduced to polynomial order w.r.t. the number of weak priors. PEL is feasible and effective for a practical MR image reconstruction task.

High-Spatial-Resolution Strain Sensor Based on Distance Compensation and Image Wavelet Denoising Method in OFDR

A high-spatial-resolution strain sensor in OFDR was experimentally demonstrated by use of combining distance compensation (DC) and image wavelet denoising (IWD) method. Compared with using one method alone, the measured distribution strain could be varied from 200 to 2000 μϵ at a spatial resolution of 2.56 mm. Moreover, four times enhancement of the accuracy for the strain senor was achieved without hardware modification. This method is a significant step toward a high performance OFDR system, especially for evaluating the rapid change of object's structural condition.