Complex Wavelet Transform Research Articles

Image Denoising Based on Bivariate Distribution

The literature has shown that the performance of the de-noising algorithm was greatly influenced by the dependencies between wavelet coefficients. In this paper, the bivariate probability density function (PDF) was proposed which was symmetric, and the dependencies between the coefficients were considered. The bivariate Cauchy distribution and the bivariate Student’s distribution are special cases of the proposed bivariate PDF. One of the parameters in the probability density function gave the estimation method, and the other parameter can take any real number greater than 2. The algorithm adopted a maximum a posteriori estimator employing the dual-tree complex wavelet transform (DTCWT). Compared with the existing best results, the method is faster and more efficient than the previous numerical integration techniques. The bivariate shrinkage function of the proposed algorithm can be expressed explicitly. The proposed method is simple to implement.

Patch-Based Dual-Tree Complex Wavelet Transform for Kinship Recognition.

Kinship recognition is a prominent research aiming to find if kinship relation exists between two different individuals. In general, child closely resembles his/her parents more than others based on facial similarities. These similarities are due to genetically inherited facial features that a child shares with his/her parents. Most existing researches in kinship recognition focus on full facial images to find these kinship similarities. This paper first presents kinship recognition for similar full facial images using proposed Global-based dual-tree complex wavelet transform (G-DTCWT). We then present novel patch-based kinship recognition methods based on dual-tree complex wavelet transform (DT-CWT): Local Patch-based DT-CWT (LP-DTCWT) and Selective Patch-Based DT-CWT (SP-DTCWT). LP-DTCWT extracts coefficients for smaller facial patches for kinship recognition. SP-DTCWT is an extension to LP-DTCWT and extracts coefficients only for representative patches with similarity scores above a normalized cumulative threshold. This threshold is computed by a novel patch selection process. These representative patches contribute more similarities in parent/child image pairs and improve kinship accuracy. Proposed methods are extensively evaluated on different publicly available kinship datasets to validate kinship accuracy. Experimental results showcase efficacy of proposed methods on all kinship datasets. SP-DTCWT achieves competitive accuracy to state-of-the-art methods. Mean kinship accuracy of SP-DTCWT is 95.85% on baseline KinFaceW-I and 95.30% on KinFaceW-II datasets. Further, SP-DTCWT achieves the state-of-the-art accuracy of 80.49% on the largest kinship dataset, Families In the Wild (FIW).

A new deep learning pipeline to detect Covid-19 on chest X-ray images using local binary pattern, dual tree complex wavelet transform and convolutional neural networks.

In this study, which aims at early diagnosis of Covid-19 disease using X-ray images, the deep-learning approach, a state-of-the-art artificial intelligence method, was used, and automatic classification of images was performed using convolutional neural networks (CNN). In the first training-test data set used in the study, there were 230 X-ray images, of which 150 were Covid-19 and 80 were non-Covid-19, while in the second training-test data set there were 476 X-ray images, of which 150 were Covid-19 and 326 were non-Covid-19. Thus, classification results have been provided for two data sets, containing predominantly Covid-19 images and predominantly non-Covid-19 images, respectively. In the study, a 23-layer CNN architecture and a 54-layer CNN architecture were developed. Within the scope of the study, the results were obtained using chest X-ray images directly in the training-test procedures and the sub-band images obtained by applying dual tree complex wavelet transform (DT-CWT) to the above-mentioned images. The same experiments were repeated using images obtained by applying local binary pattern (LBP) to the chest X-ray images. Within the scope of the study, four new result generation pipeline algorithms having been put forward additionally, it was ensured that the experimental results were combined and the success of the study was improved. In the experiments carried out in this study, the training sessions were carried out using the k-fold cross validation method. Here the k value was chosen as 23 for the first and second training-test data sets. Considering the average highest results of the experiments performed within the scope of the study, the values of sensitivity, specificity, accuracy, F-1 score, and area under the receiver operating characteristic curve (AUC) for the first training-test data set were 0,9947, 0,9800, 0,9843, 0,9881 and 0,9990 respectively; while for the second training-test data set, they were 0,9920, 0,9939, 0,9891, 0,9828 and 0,9991; respectively. Within the scope of the study, finally, all the images were combined and the training and testing processes were repeated for a total of 556 X-ray images comprising 150 Covid-19 images and 406 non-Covid-19 images, by applying 2-fold cross. In this context, the average highest values of sensitivity, specificity, accuracy, F-1 score, and AUC for this last training-test data set were found to be 0,9760, 1,0000, 0,9906, 0,9823 and 0,9997; respectively.

A high payload data hiding scheme based on dual tree complex wavelet transform

In this paper, an image steganography method is proposed to overcome the limitations associated with the most existing image steganography methods based on either spatial domain or transform domain. Although these methods try to increase the embedding capacity, the produced quality of the stego-images is still low and the embedding capacity is still limited by the size of cover image. To address this problem, an image steganography method based on dual tree complex wavelet transform (DT-CWT) is presented to increase the capacity and to keep the quality at its highest possible value. Also considering human visual system which is less sensitive to the edges, more secret bits can be hidden in the coefficients associated with edge pixels. Experimental results show the superiority of the proposed method in terms of capacity and image fidelity compared to the existing steganographic methods. Moreover, the proposed method is robust against universal analysis.

Feature Extraction and Classification of ECG Signal Based on The Standard Extended Wavelet Transform Technique: Cardiology Based Telemedicine

For early detection of cardiac abnormalities, an ECGs cardiac signal is relied upon due to it includes a lot of information that can be utilized for heart disease classification. The ECG signal is too sensitive to various types of noise since it is low frequency and has a small amplitude, these noises decrease the diagnostic accuracy and may outcome in a wrong decision by the clinician. Therefore, rejecting the ECG signal is a necessary condition for successful diagnosis of heart attacks. In this manuscript, the standard extended of Discrete Wavelet Transformc called Dual-Tree Complex Wavelet Transform (Dual-Tree (CWT)) method is utilized to denoise the noisy ECG signal and extract the key features followed by the implementation of the peak detection algorithm. The quality is measured based on performance metrics, and an increase in Signal to Noise Ratio ( SNR) is achieved utilizing the technique. The heart rate (HR) calculation is in line with the gold standard of the various benchmark databases utilized for the proposed procedure and precise heart failure has been calculated.

Robust Blind Watermarking Technique Against Geometric Attacks for Fingerprint Image Using DTCWT-DCT

In this research paper, a new blind and robust fingerprint image watermarking scheme based on a combination of dual-tree complex wavelet transform (DTCWT) and discrete cosine transform (DCT) domains is demonstrated. The major concern is to afford a solution in reducing the consequence of geometric attacks. It is due to the fingerprint features that may be impacted by the incorporated watermark, fingerprint rotations, and displacements that result in multiple feature sets. To integrate the bits of the watermark sequence into a differential process, two DCT-transformed sub-vectors are implemented. The initial sub-vectors were obtained by sub-sampling in the host fingerprint image of both real and imaginary parts of the DTCWT wavelet coefficients. The basic difference between the relevant sub-vectors of the watermarked fingerprint image in the extraction stage directly provides the inserted watermark sequence. It is not necessary to extract watermark data from an original fingerprint image. Therefore, the technique suggested is evaluated using 80 fingerprint images from 10 persons, from both CASIA-V5-DB and FVC2002-DB2 fingerprint database. For each person, eight fingerprints are set as the template and the watermark are inserted in each image. A comparison between the obtained results with other geometric robust techniques results is performed afterwards. The comparison results show that the proposed technique has stronger robustness against common image processing processes and geometric attacks such as cropping, resizing, and rotation.

Dual-Transform Source Separation Using Sparse Nonnegative Matrix Factorization

In this article, we propose a new source separation method in which the dual-tree complex wavelet transform (DTCWT) and short-time Fourier transform (STFT) algorithms are used sequentially as dual transforms and sparse nonnegative matrix factorization (SNMF) is used to factorize the magnitude spectrum. STFT-based source separation faces issues related to time and frequency resolution because it cannot exactly determine which frequencies exist at what time. Discrete wavelet transform (DWT)-based source separation faces a time-variation-related problem (i.e., a small shift in the time-domain signal causes significant variation in the energy of the wavelet coefficients). To address these issues, we utilize the DTCWT, which comprises two-level trees with different sets of filters and provides additional information for analysis and approximate shift invariance; these properties enable the perfect reconstruction of the time-domain signal. Thus, the time-domain signal is transformed into a set of subband signals in which low- and high-frequency components are isolated. Next, each subband is passed through the STFT and a complex spectrogram is constructed. Then, SNMF is applied to decompose the magnitude part into a weighted linear combination of the trained basis vectors for both sources. Finally, the estimated signals can be obtained through a subband binary ratio mask by applying the inverse STFT (ISTFT) and the inverse DTCWT (IDTCWT). The proposed method is examined on speech separation tasks utilizing the GRID audiovisual and TIMIT corpora. The experimental findings indicate that the proposed approach outperforms the existing methods.

Research on a Noise Reduction Method Based on DTCWT and the Cyclic Singular Energy Difference Spectrum

The gear is the most important part of the transmission system of mechanical equipment, and the monitoring and diagnosis of it can improve the reliability of mechanical equipment. However, mechanical equipment generally works in harsh working conditions. The gear vibration signal is subjected to strong noise interference in working conditions, which brings great challenges for the effective diagnosis of gear faults. This paper proposed a noise reduction method based on the dual-tree complex wavelet transform (DTCWT) and cyclic singular energy difference spectrum. First, the gear vibration signal containing strong noise interference is decomposed into a series of signal components with different frequency characteristics by using the time-frequency analysis ability of DTCWT. Then, cyclic singular energy difference spectrum is proposed based on the idea of a cascaded cycle and the successive elimination of noise interference to process each signal component with different frequency characteristics, and the termination conditions of cyclic singular energy difference spectrum can be set according to the noise interference distribution characteristics in different frequency bands. The final noise reduction of the original gear vibration signal can be realized based on signal reconstruction after the noise reduction processing of each signal components with different frequency bands. Finally, experiments are carried out to verify the effectiveness of the proposed method, which is effective and suitable for the noise reduction of the vibration signal.

Image super-resolution by prediction of dual tree-CWT coefficient at a finer scale

This paper presents an image of Super-Resolution (SR) technique by the construction of DT-CWT coefficients for a larger scale from the information at a smaller scale for all the subbands. The DT-CWT coefficients prediction for each subband of an image at a finer level is based on phase prediction and estimation of the magnitude separately, followed by combining the magnitude and phase. Inverse DT-CWT is taken with the coefficients at a finer level of each subband along with a Low-Resolution (LR) image in place of a low subband to reconstruct a high-resolution image. The proposed technique is applied to various images, including satellite and standard images. The quantitative and visual results have established the superiority of the proposed scheme over conventional and various state-of-the-art techniques.

Design and implementation of a robust noise removal system in ECG signals using dual-tree complex wavelet transform

The key deliverable for any health monitoring system that offers telecardiology services is the recovery of the ECG signal related to cardiac diagnostics. Accurate analysis and diagnosis of heart diseases become difficult due to noises and artifacts. Therefore, a need for noise removal which is an inverse problem arises that leads to reliable signal recovery tasks. In this paper, authors have provided a detailed evaluation of the effect of the choice of the threshold value, threshold algorithm, and distribution function to evaluate the ECG signal de-noising performance employing Dual tree complex wavelet transform (DTCWT). In this research work, eight different sets of threshold value selection rules along with six distinct threshold functions are implemented and evaluated on MIT-BIH arrhythmia database. Authors have proposed an estimator that yields efficient results than a conventional estimator using Gaussian distribution function and extended the work to Normal distribution. The results show that the Universal modified threshold level-dependent threshold value selection with Non -Negative Garrote threshold function delivers higher performance in terms of SNR, lower values of MSE and PRD. The proposed approach accomplished good performance evaluation results as 58.23 dB, SNR and 9.63e-08, MSE in comparison with the 48.65 dB, SNR and 8.75e-07, MSE using conventional method for the normal distribution function. The novelty of this work also lies in an exhaustive empirical comparative analysis with the existing research work using the same database with the proposed normal distribution technique.

Dual Tree Complex Wavelet Transform with Multiobjective Optimization Algorithm for Real‐Time Power Quality Events Classification

AbstractThis article proposes an application of Dual Tree Complex Wavelet Transform (DTCWT) with non‐dominated sorting genetic algorithm III (NSGA III) based multi‐objective optimization and directed acyclic graph support vector machine (DAG‐SVM) for recognition and classification of power quality events. The proposed method first employs DTCWT for extraction of features then NSGA III algorithm for an effective optimization of extracted features. After that, DAG‐SVM based classifier are used to predict the classes of PQ disturbances. The NSGA III algorithm generates optimalsolutions based on multi objective optimization and then fitness function is generated with the help of Pareto front to obtain unique features set from power signals. The NSGA III not only optimizes selected features with DTCWT but also reduces the computational time in comparison with the traditional NSGA II. The obtained unique feature vectors are used for training of Directed Acyclic Graph‐SVM to classify the power quality disturbances. The short event detection, lesser computational timing, superior classification accuracy, and high anti‐noise performance are the main advantages of the proposed method.

Computational complexity reduction in HEVC intra prediction using dual tree complex wavelet transform and holoentropy

High efficiency video coding (HEVC) is the newest video codec to increases the coding efficiency of its ancestor H.264/Advance Video Coding at the cost of highly increased computational complexity. In this paper, a novel method using Dual tree Complex Wavelet Transform is proposed to reduce the computational time consumption in HEVC Encoding. DTCWT provides better directional selectivity. By using DTCWT, total intra prediction modes are reduced from 35 modes to 7 modes including DC and Planer mode. The encoding process in HEVC system is performed using clustered entropy computing, which distinguishes the video information has useful outliers. The pixel variations under varying frames are clustered based on the interestingness and the outliers are removed using an advanced entropy principle called as holoentropy. Compared to the current state of the art algorithms, the experimental results show that this scheme is computationally simple and achieves superior reconstructed video quality at less computational complexity.

A nonlinear solution to 3D seismic data conditioning using trained dictionaries

Seismic analysis for reservoir characterization has been a primary focus for the geophysical community for decades. One of the critical steps in delivering high-quality processed seismic data for seismic analysis is to remove undesirable prestack seismic phenomena prior to amplitude variation with offset (AVO) analysis. Contrary to the conventional approach, which is mainly 2D gather-based and assumes flat events, we have developed a 3D nonlinear approach with a single principle: the 3D geologic structure should be invariant from offset to offset. Trained dictionaries, generated by 3D complex wavelet transformation over pilot volumes, are progressively constructed by stacking over selected offsets or angles. A sparse nonlinear approximation using the L0 norm is imposed on the data against the trained dictionaries after applying a 3D complex wavelet transform to the data. The final step is to apply an inverse 3D complex wavelet transform to the sparsified coefficients to return to the data space. This workflow is repeated for all offsets or angles. The workflow is automatic and requires minimal user input, resulting in a fast and efficient process. Multiple field data examples have demonstrated significant signal-to-noise ratio uplift, AVO and azimuthal AVO conservation, preservation of steeply dipping structural events, and multiple suppression. The processing time is significantly shorter compared with alternative conventional processes.

Absolute Transformation and Clahe Based High Performance Lucid Proposal for Image Processing

Image fusion is a one of the enhancement technique which is used to take the decision the images by the various types of sensors. Image fusion is nothing but the combination of two images which is helps to improve the quality of the image. In this paper, visible image and Infrared image are combined to acquire the informative image. Before and after image fusion, a new transformation technique is introduced to improve the quality of the image. To prove the quality of the image after applying new transformation technique, the fusion is done by four different techniques is used like Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Non-Subsampled Contourlet Transform (NSCT) and Dual Tree Complex Wavelet Transform (DT-CWT). The comparison of following parameter values such as Entropy, Standard deviation, Mean gradient, Average pixel intensity and spatial frequency shows that proposed method is better to improve the image quality.

Proposed Copyright Protection Systems for 3D Video Based on Key Frames

Recently, three Dimension (3D) multimedia technology has grown over a wide range, where the 3D used in many applications such as medical, television, cinema, game, education, etc. The developments also include the computer network, these evaluations make the store and distribute the media very easy and at the same time very critical, where any person can access these data and manipulate it or redistribute it with illegal copyrights. Therefore, it is necessary to find a watermarking technique to keep the security of these media. 3D multimedia, especially 3D Video contains a huge amount of data, trying achievement copyright protection for all these data consumes the computation, and slow down securing process, thus 3D video key frame extraction process is necessary. In this paper, the histogram-based key frame extraction technique is applied to extract essential and important data of the 3D video. A modified invisible, and blind watermark system is suggested in this research for 3D Video copyrights and authentication protection using Dual-Tree Complex Wavelet Transform (DTCWT). The experiment results show that 3D video key extraction system has given high compression ratio ( from 4:1 to 5:1) and the protection system could put an invisible watermark while keeping the quality of the 3D video, as well as the proposed watermark system, is robust where the watermark extracted successfully after applying a different types of attack.

Recognition of Lung Tumor Area Based on Watershed Segmentation and CNN

Early recognition of tumor would assist in saving an enormous number of lives over the globe frequently. Study and remedy of lung tumor have been one of the greatest troubles faced by humans over the latest few decades. Effective recognition of lung tumor is a vital and crucial aspect of image processing. Several Segmentation methods were used to detect lung tumor at an early stage. An approach is presented in this paper to diagnose lung tumor from CT scan images. The input image (CT scan image) will be preprocessed initially using median filter to remove the noise. After applying preprocessing technique, the Dual-Tree Complex Wavelet Transform (DTCWT) segmentation technique is used for the edge detection. The Gray-Level Co-occurrence Matrix (GLCM) features are calculated based on the pixel values of the extracted image. These features can be compared with database images using Convolutional Neural Network (CNN) which facilitates in categorizing it as tumorous. After confirming that the affected area is tumorous, watershed segmentation algorithm is used to get the color features of the tumor.

RETRACTED ARTICLE: Composite feature vector based cardiac arrhythmia classification using convolutional neural networks

Electrocardiogram analysis for the classification of several cardiac arrhythmias has gained a significant research importance in the medical field. Towards such objective, this paper proposed a novel approach based on the fusion of multiple features extracted from a signal through various methods and Convolution Neural Networks. The multiple features are precisely consisting of morphological features, temporal features, and statistical features. Every electrocardiogram signal is initially pre-processed to remove the base line and then processed for segmentation through a simple strategy. Further, for every heart beat segment, three different set of features are extracted. Among them, morphological features are obtained through Dual Tree Complex Wavelet Transform and remaining features are extracted through statistical measures. Further, Principal Component Analysis is applied over the morphological feature set to reduce the dimensionality. Finally, a composite and final feature vector is formulated and then fed to Convolutional Neural Networks classifier to predict the label for a given input heartbeat. Simulation experiments conducted through the MIT-BIH benchmark database exhibited that the proposed system achieves better classification accuracy and on an average, it of 98%. Compared with state-of-art methods, the improvement is approximately 5%.

Detector of 3-D salient points based on the dual-tree complex wavelet transform for the positioning of hippocampi meshes in magnetic resonance images

BackgroundBrain Magnetic Resonance (MR) image segmentation methods based on deformable models depend on the initial positioning to maximize the chances of successful segmentation. To minimize this limitation, salient-point based registration is used to perform the initial positioning of brain structure meshes close to their image target representation. The analysis of brain structures (such as the hippocampus) can help in the diagnosis and follow-up of neurodegenerative diseases like Alzheimer's. MethodsWe present a technique for detection and description of 3-D salient points, which combines filter response maps estimated for different scales and orientations of the dual-tree complex wavelet transform (DT-CWT). We apply our technique to detect salient points in volumetric brain MR images and use the detected points in a positioning methodology. To illustrate the applicability, we applied our method for the positioning of hippocampi meshes in 3-D brain MR images and assessed the results by overlapping the positioned meshes with manual annotations made by medical specialists. ResultsOur method yielded mean values of normalized Dice Similarity Coefficient (nDSC) of 0.74/0.68 and Hausdorff Average Distance (HAD) of 0.73/0.75 for the left and right hippocampus, respectively. Comparison with Other MethodsThe mean nDSC and HAD results of our detector were significantly better than the ones achieved by an Affine and a Phase Congruency (PC) guided positioning. ConclusionsThe detection via DT-CWT decomposition is computationally less demanding than the detection via PC and represents a robust alternative for the positioning of mesh models.

A NOVEL ITERATIVE DEMOSAICING ALGORITHM USING FUZZY BASED DUAL TREE WAVELET TRANSFORM

In this research paper, an efficient demosaicking algorithm for Color Filter Array (CFA) is proposed to overcome the problem of reconstructing the correlated signals from the down sampled samples. The aim of this work is reconstruction of a full color image from the spatially under sampled color channels. The demosaicing is done by an iterative methodology for finding the values of missing pixels. The Dual Tree Complex Wavelet Transform (DTCWT) is used with the combination of fuzzy ‘if-then’ rule to refine the color plane values. The DTCWT has shift invariance and directionality property that achieves the perfect reconstruction of images and improves quality of the image. The new iterative interpolation algorithm uses color difference domain model and reduces false coloring by using an effective stopping criteria. The research work shows result as, the explicated interpolation method yields better psnr values than bilinear interpolation technique, edge based method, subband based method, and other iterative based demosaicing methods.

Power Quality Event Detection and Classifier Architecture on FPGA for Smart M eters

Smart meters have been developed to capture PQ events, detect the event, compress events and characterize events. The events are stored in local memory of smart meter as well are transmitted over communication channel. The smart meter hardware that performs complex signals processing activity such as event detection, classification and compression need to be implemented on reconfigurable platforms. FPGAs are used in smart meters as they support reconfigurability and also has inbuilt memory modules, processor modules and additional features for interfacing. High speed low power area efficient architectures for computation of Dual Tree Complex Wavelet Transform (DTCWT).