Dual-tree Discrete Wavelet Research Articles

A novel method of image denoising based on 2D dual-tree DWT and SWT

In this paper, we propose a new image denoising technique which consists in applying a stationary wavelet transform (SWT)-based image denoising technique, in the domain of 2D dual-tree discrete wavelet transform (DWT). In fact, this proposed technique consists first of applying the 2D dual-tree DWT to the noisy image. Then, the noisy wavelet coefficients obtained from this application are denoised by applying to each of them, a SWT-based image denoising technique. Finally, the denoised image is reconstructed by applying the inverse of the 2D dual-tree DWT to the obtained denoised wavelet coefficients. For applying this SWT-based image denoising technique, we use the soft thresholding, the Daubechies 4 as the mother wavelet, and the decomposition level is equal to 5. The performance of this image denoising technique proposed in this work is proven by its comparison to three other denoising techniques existing in the literature. These three techniques are the denoising technique based on the soft thresholding in the SWT domain, the image denoising technique based on soft thresholding in the domain of 2D dual-tree DWT and the image denoising approach using deep neural network. All the previously mentioned techniques, including our proposed denoising approach, are applied to a number of noisy images, and the obtained results are in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). Those results show that this proposed denoising technique outperforms the other three denoising techniques used in this evaluation.

Recaptured attack-resilient watermarking scheme

We propose a recaptured attack-resilient blind watermarking scheme. The work aims to recover the watermark information from the stego (watermarked image) reacquired through a digital liquid-crystal display monitor. In the age of digital globalization, problems like copyright and integrity infringement of digital content are growing exponentially. The content owner can prove their ownership by extracting the embedded watermark from the digitally breached data. The presented framework is robust to several geometrical and signal processing attacks, including lens distortions, intensity distortion, and moiré distortion caused by recapture attack. The singular values of a watermark image and a unique security key are embedded in the host image’s double-density dual-tree discrete wavelet transform (DDD-DWT) coefficients. However, most singular value decomposition (SVD) based watermarking algorithms are prone to false alarm rates and missed alarm rates, causing a security issue. On that account, the proposed watermarking scheme in this paper introduces a unique security key embedding for authentication at the decoder side. The experimental results show that the proposed framework provides high perceptibility with a WPSNR value >59 dB and robustness against various attacks and security.

Image processing techniques for the segmentation of cervical cancer

The most prevalent type of cancer in women worldwide is uterine cervical cancer. The majority of cervical cancer (CC) cases can be avoided by participating in screening programmes that look for precancerous lesions. Colposcopic cervigrams or images from digital colposcopy have been acquired in raw form. This study presents a novel framework that combines image enhancement, pre-processing, and image segmentation to identify cervical cancer. Three phases make up this framework: the Dual Tree Discrete Wavelet Transform (DTDWT) for pre-processing, the Curvelet transform and Contour Transform (CC) for image improvement, and the K-means clustering for segmentation.

Image fusion using dual tree discrete wavelet transform and weights optimization

Image fusion using dual tree discrete wavelet transform and weights optimization

Efficient DTCWT-TSVR algorithm for dense 5G mmWave Indoor Hotspot Communications

An efficient Dual Tree Discrete Wavelet Transform (DTDWT) based Twin Support Vector Regression (TSVR) algorithm is conceived in this article and applied to 28, 38, 60 and 73-GHz LOS (Line-of-Sight) wireless multipath transmission system in 5G Indoor Hotspot (InH) settings (empty, simple, semi-complex and complex conference rooms) under small receiver sensitivity threshold. The algorithm establishes a denoising process in the learning phase based on DTCWT which is suitable for time-series data. Additionally, the Close-In (CI) free space reference distance path loss model is analyzed and the large-scale propagation and probability distribution functions are investigated by determining the PLE (Path Loss Exponent) and the standard deviation of Shadow Factor (SF) for each indoor hotspot scenario under consideration. Performance are analyzed and evaluated in terms of Bit Error Rate (BER), Normalized Mean Squares Error (NMSE) and Root Mean Squares Error Vector Magnitude (RMS EVM).

The smooth transition GARCH model for simulation of highly nonstationary earthquake ground motions

The aim of this paper is to extend a stochastic model for simulation of highly nonstationary ground motions (GMs). In this model, the dual-tree complex discrete wavelet transform (DT-CDWT) is applied to a recorded ground motion to extract its wavelet coefficients and then the Smooth Transition Generalized Autoregressive Conditional Heteroscedastic (ST-GARCH) model is used to simulate these coefficients. This model simulates nonstationary features of real GMs greatly, because the conditional variance estimated by this model changes compatibly with the amplitude nonstationary features of real GMs. Because of having asymmetric structure, this model also estimates sudden changes in the amplitude of ground motions. Some of the special capabilities of this model are the simulation of multiple increasing–decreasing cycles in the temporal amplitude of GMs, prediction of several peaks in the frequency spectrum of GMs, estimation of steps of their energy curve, and simultaneous simulation of all shocks of a GM sequence. Also, this model simulates the time–frequency energy distribution of both wide-frequency and narrow-frequency bandwidth GMs.

Dual Tree Discrete Wavelet Transform and Entropy based Approach for Video Shot Boundary Detection

Shot Boundary detection is one of the most prominent steps for the various video processing techniques like indexing of videos, video retrieval, video summarization, video scene analysis, etc. In this paper, we have projected a useful technique based on dual-tree Discrete Wavelet Transform. The dual-tree structure with selected filters returns the approximate decomposition in an analytical manner. Due to the existence of the two trees, the noise component is characterized precisely. The outcome of the DTDWT is distortion less with normalized localized function and exact reconstruction of the signal. WE have used the entropy function to measure the uncertainty in the random variable. Finally, we evaluated the algorithm using Recall, Precision, and F1 measure. Experimental results demonstrate the efficiency of the given method.

A hybrid double-density dual-tree discrete wavelet transformation and marginal Fisher analysis for scoring sleep stages from unprocessed single-channel electroencephalogram.

We demonstrate an innovative approach of automated sleep recording formed on the electroencephalogram (EEG) with one channel. In this study, double-density dual-tree discrete wavelet transformation (DDDTDWT) was used for decomposing the image, and marginal Fisher analysis (MFA) was used for reducing the dimension. A proposed model on unprocessed EEG models was used on monitored training of 5-group sleep phase forecasting. Our network includes a 14-row structure, and a 30-s period was extracted as input in order to be categorized which is followed by second and third period prior to the first 30-s period. Another consecutive period for temporal tissue was added which is not required to a signal preprocess and attribute data derivation phase. Our means of evaluating and improving our approach was to use input from the Sleep Heart Health Study (SHHS), which is a large study field aimed at using research from numerous centers and people and which studies the records of specialist-rated polysomnography (PSG). Performance measures could reach the desired level, which is a precision of 0.87 and a Cohen's kappa of 0.81. The use of a large, collaborative study of specialist graders can enhance the likelihood of good globalization. Overall, the novel approach learned by our network showcases the models based on each category.

Optimal fusion aided face recognition from visible and thermal face images

This paper proposes a novel Eigen face recognition that is aided by fusion of visible and thermal face images to improve the face recognition accuracy. We adopt three different fusion schemes where in the face information is fused by the optimal weights obtained by different optimization algorithms. The first two fusion approaches operate in the dual tree discrete wavelet transform (DT-DWT), while the third one operates in the Curvelet transform (CT) domain. We employ particle swarm optimization (PSO), self-tuning particle swarm optimization (STPSO) and brain storm optimization algorithm (BSO) to find optimal fusion coefficients. The proposed fusion aided face recognition approaches are evaluated through extensive experiments using OCTVBS benchmark face database and the Eigen face detection methodology. Simulation results show that proposed face recognition techniques have significant performance improvement in recognition accuracy suggesting fusion aided face recognition approach that deserves further study and consideration whenever high recognition accuracy is desired.

Redundancy Removed Dual-Tree Discrete Wavelet Transform to Construct Compact Representations for Automated Seizure Detection

With the development of pervasive sensing and machine learning technologies, automated epileptic seizure detection based on electroencephalogram (EEG) signals has provided tremendous support for the lives of epileptic patients. Discrete wavelet transform (DWT) is an effective method for time-frequency analysis of EEG and has been used for seizure detection in daily healthcare monitoring systems. However, the shift variance, the lack of directionality and the substantial aliasing, limit the effects of DWT in some applications. Dual-tree discrete wavelet transform (DTDWT) can overcome those drawbacks but may increase information redundancy. For classification tasks with small dataset sizes, such redundancy can greatly reduce learning efficiency and model performance. In this work, we proposed a novel redundancy removed DTDWT (RR-DTDWT) framework for automated seizure detection. Energy and modified multi-scale entropy (MMSE) features in a dual tree wavelet domain were extracted to construct a complete picture of mental states. To the best of our knowledge, this is the first study to employ MMSE as an indicator of epileptic seizures. Moreover, a compact EEG representation can be obtained after removing useless information redundancy (redundancy between wavelet trees, adjacent channels and entropy scales) by a general auto-weighted feature selection framework via global redundancy minimization (AGRM). Through validation on Bonn and CHB-MIT databases, the proposed RR-DTDWT method can achieve better performance than previous studies.

Pedestrian Detection in Infrared Outdoor Images Based on Atmospheric Situation Estimation

Observation in absolute darkness and daytime under every atmospheric situation is one of the advantages of thermal imaging systems. In spite of increasing trend of using these systems, there are still lots of difficulties in analysing thermal images due to the variable features of pedestrians and atmospheric situations. In this paper an efficient method is proposed for detecting pedestrians in outdoor thermal images that adapts to variable atmospheric situations. In the first step, the type of atmospheric situation is estimated based on the global features of the thermal image. Then, for each situation, a relevant algorithm is performed for pedestrian detection. To do this, thermal images are divided into three classes of atmospheric situations: a) fine such as sunny weather, b) bad such as rainy and hazy weather, c) hot such as hot summer days where pedestrians are darker than background. Then 2-Dimensional Double Density Dual Tree Discrete Wavelet Transform (2D DD DT DWT) in three levels is acquired from input images and the energy of low frequency coefficients in third level is calculated as the discriminating feature for atmospheric situation identification. Feed-forward neural network (FFNN) classifier is trained by this feature vector to determine the category of atmospheric situation. Finally, a predetermined algorithm that is relevant to the category of atmospheric situation is applied for pedestrian detection. The proposed method in pedestrian detection has high performance so that the accuracy of pedestrian detection in two popular databases is more than 99%.

Classification of sleep stages based on LSTAR model

Sleep study is very important in the health since sleep disorders affect the productivity of individuals. One of the important topics in sleep research is the classification of sleep stages using the electroencephalogram (EEG) signal. Electrical activities of brain are measured by EEG signal in the laboratory. In real-world environments, EEG signal is also used in portable monitoring devices to analyze sleep. In this study, we propose an efficient method for classification of sleep stages. EEG signals are examined by a new model from autoregressive (AR) family, namely logistic smooth transition autoregressive (LSTAR) to study sleep process. In contrast to the AR model, LSTAR is a non-linear one; therefore, it is suitable for modeling non-linear signals such as EEG. In the current research, at first, each 30-second epoch of EEG signal is decomposed into the time-frequency sub-bands using the double-density dual-tree discrete wavelet transform (D3TDWT). In the second step, LSTAR model is used for feature extraction from each sub-band. Next, the dimension of feature vector is reduced by tensor locality preserving projection (tensor LPP) method, and then the obtained features are given to classifier to determine the stage of each epoch based on the number of considered classes. After classifying sleep stages, some misclassified epochs can be corrected according to the smoothing rule. We consider different classifiers and evaluate their performance. The results indicate the efficiency of the proposed method in comparison with the recently introduced methods in terms of accuracy and Kappa coefficient.

A Novel Framework for Detection of Cervical Cancer

Today, Uterine Cervical Cancer is most general form of cancer for women. Prevention of cervical cancer is possible via various screening courses. Colposcopy images of cervix are analyzed in this study for the recognition of cervical cancer. An innovative framework is suggested to correctly identify cervical cancer by employing effective pre-processing, image enhancement, and image segmentation techniques. This framework comprises of five phases, (i) Dual tree discrete wavelet transform to pre-process the image (ii) Curvelet transform and contour transform to enhance the image (iii) K-means for segmentation (iv) features computation using Gray level co-occurrence matrix (v) classification using adaptive Support vector machine. The experimental results evident that proposed technique is superior to existing methodologies.

Image quality improvement using dddtdwt

The enhancement of degraded images using different wavelet transform techniques are presented in this paper. The performance of the wavelet techniques is analysed in terms of Peak Signal to Noise Ratio values and Root Means Square error. The Double Density Dual Tree Discrete Wavelet Transform technique is mainly focused for analysis and the results are compared with discrete wavelet transform and the Double Density DWT.

Double Density Dual Tree Discrete Wavelet Transform implementation for Degraded Image Enhancement

Wavelet transform is a main tool for image processing applications in modern existence. A Double Density Dual Tree Discrete Wavelet Transform is used and investigated for image denoising. Images are considered for the analysis and the performance is compared with discrete wavelet transform and the Double Density DWT. Peak Signal to Noise Ratio values and Root Means Square error are calculated in all the three wavelet techniques for denoised images and the performance has evaluated. The proposed techniques give the better performance when comparing other two wavelet techniques.

Image quality degradation assessment based on the dual-tree complex discrete wavelet transform for evaluating watermarked images

We propose a new image quality degradation assessment method based on the dual-tree complex discrete wavelet transform (DT-CDWT) for evaluating the image quality of watermarked images. The peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) are widely used to evaluate image quality degradation resulting from embedding a digital watermark. The majority of digital image watermarking methods embed a digital watermark in the spatial or frequency domain of an original image. They evaluate image quality degradation using only the spatial domain in spite of the fact that the majority of digital image watermarking methods embed a digital watermark in the spatial or frequency domain. As a result, they do not always fairly evaluate the image quality degradation. Therefore, our method evaluates image quality degradation of the watermarked images using features in the spatial and frequency domains. To extract the features, we defined three indices: 1-norm estimation using bit-planes in the spatial domain, the sharpness, and 1-norm estimation based on the DT-CDWT domains. We describe our image quality assessment method in detail and present experimental results demonstrating that there is a strong positive correlation between the result obtained by our method and a subjective evaluation, in comparison with PSNR and SSIM.

HEVC and 3D dual-tree discrete wavelet transform based multiple description video coding

HEVC and 3D dual-tree discrete wavelet transform based multiple description video coding

Fast Compressed Sensing MRI Based on Complex Double-Density Dual-Tree Discrete Wavelet Transform.

Compressed sensing (CS) has been applied to accelerate magnetic resonance imaging (MRI) for many years. Due to the lack of translation invariance of the wavelet basis, undersampled MRI reconstruction based on discrete wavelet transform may result in serious artifacts. In this paper, we propose a CS-based reconstruction scheme, which combines complex double-density dual-tree discrete wavelet transform (CDDDT-DWT) with fast iterative shrinkage/soft thresholding algorithm (FISTA) to efficiently reduce such visual artifacts. The CDDDT-DWT has the characteristics of shift invariance, high degree, and a good directional selectivity. In addition, FISTA has an excellent convergence rate, and the design of FISTA is simple. Compared with conventional CS-based reconstruction methods, the experimental results demonstrate that this novel approach achieves higher peak signal-to-noise ratio (PSNR), larger signal-to-noise ratio (SNR), better structural similarity index (SSIM), and lower relative error.

An optimal weighted averaging fusion strategy for thermal and visible images using dual tree discrete wavelet transform and self tunning particle swarm optimization

Image fusion plays a vital role in providing better visualization of image data. In this paper, we propose a new algorithm that optimally combines information from thermal images with a visual image of the same scene to create a single comprehensive fused image. In this work, an improved version of particle swarm optimization alogithm is proposed to optimally combine the thermal and visible images. The proposed algorithm is named self tunning particle swarm optimization (STPSO). Because of the importance of the fusion rule, a weighted averaging fusion rule is formulated that uses optimal weights resulting from STPSO for the fusion of both high frequency and low frequency coefficients obtained by applying Dual Tree Discrete Wavelet Transform (DT-DWT). The objective function in STPSO is formulated with the twin objectives of maximizing the Entropy and minimizing the Root Mean Square Error (RMSE), which differentiates our work from existing fusion techniques. The efficiency of our fusion algorithm is also evaluated by adding Gaussian white noise to the source images. The fusion results are compared with existing multi-resolution based fusion techniques, such as Laplacian Pyramid (LAP), Discrete Wavelet Transform (DWT) and Non Sub-Sampled Contourlet Transform (NSCT). The simulation results indicate that the proposed fusion framework results in better quality fused images when evaluated with subjective and objective metrics. Comparision of these results with those from PSO shows that our algorithm outperforms generic PSO.

Extraction of well-exposed pixels for image fusion with a sub-banding technique for high dynamic range images

ABSTRACTThis paper presents a new method for image fusion with sub-band architecture for fusing the multiple-exposure images of natural scenes. In captured standard dynamic range (SDR) images with different exposure settings, fine details are extracted and preserved using the proposed method by transforming the pixel-based enhancement in the image using Dynamic Refined Adaptive Weight (DRAW) map. The sequence of the images is decomposed into different sub-bands with a dual tree discrete wavelet transform. We compute the DRAW map according to the appearance of the image based on features such as exposure, contrast and saturation. The coefficients of the sub-bands are blended into a high-quality image with the fine detail preserved. The experimental results are demonstrated, and the proposed results create visually pleasing images with the very sharp details preserved.