Curvelet Transform Research Articles

Hybrid fusion using Gram Schmidt and Curvelet transforms for satellite images

Optical satellites generally provide high-resolution panchromatic but low-resolution multispectral images which provide structural details of features and spectral information respectively. Nowadays, fusion of the two types of resolutions, to have complementary information, becomes increasingly essential for many applications such as microscopic, astronomical and satellite imagery. In this paper, a novel hybrid pixel-level image fusion method is proposed for benefiting from both panchromatic (PAN) and multispectral (MUL) images. The proposed method integrates Gram Schmidt (GS) and curvelet transforms (CVT), by the aid of local energy and maximum fusion rules, for reducing individual method limitations and achieving both better spectral consistency and spatial details preservation. After a pre-processing stage, orthonormal bases are obtained for low spatial resolution images by using GS transform. Then, high-resolution and low-resolution images are fused using CVT by the aid of histogram matching. Finally, the fused image is obtained by applying both curvelet and GS inverse transforms. The performance of the proposed method is evaluated using publicly available Pleiades benchmark-datasets. Consequently, the spectral and spatial qualities of the fused images are assessed subjectively as well as objectively using different quality metrics. Moreover, the proposed method is compared with state-of-the-art fusion techniques and results show the robustness of the proposed method that has the best result in spatial and spectral evaluation metrics such as, Quality with No Reference (QNR), Peak Signal to Noise Ratio (PSNR), Standard Deviation (SD), Entropy (ENT) and Spectral Correlation Coefficient (SCC) metrics.

Using FC-CLAHE-ADF to enhance digital mammograms for detecting breast lesions

Digital mammograms are commonly used for breast screening, especially to aid the detection of cancer. However, digital mammograms suffer with low contrast images due to the low exposure factors used. This paper presents a novel image enhancement technique for digital mammogram images known as Fuzzy Clipped Contrast-Limited Adaptive Histogram Equalization with Anisotropic Diffusion Filter (FC-CLAHE-ADF). This proposed FC-CLAHE-ADF has adopted a fuzzy-based and histogram-based image enhancement technique where it can further reduce the noise of the digital mammograms while preserving the contrast and brightness. A total of six digital mammograms were retrieved from Mammographic Image Analysis Society (MIAS) open-source database. The performance of FC-CLAHE-ADF was compared to Recursive Mean-Separate Histogram Equalization (RMSHE), Fast Discrete Curvelet Transform via Unequally Spaced Fast Fourier Transform (FDCT-USFFT), and FC-CLAHE only. In summary, this novel FC-CLAHE-ADF has provided the most superior results, among other selected enhancement techniques. The resulting images have been able to demonstrate breast lesions better.

Classification of Mangosteen Surface Quality Based on Image Processing Using Support Vector Machine

Mangosteen is one of the highest export commodities among other fruits in Indonesia. Mangosteen should be free from defects and damages to be accepted as export quality. In most of the mangosteen plantation in Indonesia, sorting of mangosteen is performed manually with human eye. This method is less effective and inaccurate because it depends on workers’ conditions and perceptions. The use of image processing technology for quality inspection has been done for various fruits. However, mangosteen quality inspection in Indonesia has not used image processing technology. The objective of this research is to develop a method using support vector machine to classify defect and non-defect mangosteen surface. The method involved mangosteen surface image capture, pre-processing, defect features extraction using Curvelet transformation and classification using support vector machine. We collected 120 input images using camera from defect and non-defect mangosteens. The proposed method resulted 96.67% of accuracy. It can be concluded that the proposed method has successful classify mangosteen surface.

Comparison Study for Three Compression Techniques (Wavelet, Contourlet and Curvelet Transformation)

Researches and studies on compressing digital images are aiming to make it easier to deal with networks, communications and Internet by reducing the size of the multimedia files transferred, and reducing the execution time and transmission time. In this research, the lossy compression method was adopted as one of the solutions that reduce the size of the data required to compress the image, through the process of compression of digital image data using Discrete Wavelet Transform algorithms using Haar filter, and Contourlet. Using Laplace and Directional Filter, Curvelet transformation using FDCT- Wrapping Technology .The performance of the algorithms used in the proposed research is also evaluated using a Ratio Compression (RC) scale, As well as the Peak signal to noise ratio (PSNR) scale, the mean sequence error (MSE) scale, the signal to noise ratio (SNR) scale, and finally, the Normalization correlation (NC) scale. Correspondence between the original image and the recovered image after compression, in order to choose the best algorithm that achieves the best compression ratio of the image and maintains the parameters of the recovered image based on the standards (MSE, PSNR, SNR, COR and CR) used with the three algorithms, and the results showed that the Curvelet transformation algorithm achieved : best compression ratio, but at the expense of image quality.

Multi-Focus Image Fusion with Multi-Scale Transform Optimized by Metaheuristic Algorithms

Focus is limited and singular in many image capture devices. Therefore, different focused objects at different distances are obtained in a single image taken. Image fusion can be defined as the acquisition of multiple focused objects in a single image by combining important information from two or more images into a single image. In this paper, a new multi-focus image fusion method based on Bat Algorithm (BA) is presented in a Multi-Scale Transform (MST) to overcome limitations of standard MST Transform. Firstly, a specific MST (Laplacian Pyramid or Curvelet Transform) is performed on the two source images to obtain their low-pass and high-pass bands. Secondly, optimization algorithms were used to find out optimal weights for coefficients in low-pass bands to improve the accuracy of the fusion image and finally the fused multi-focus image is reconstructed by the inverse MST. The experimental results are compared with different methods using reference and non-reference evaluation metrics to evaluate the performance of image fusion methods.

Feature extraction and power quality event classification using Curvelet transform and optimized extreme learning machine

This article presents an efficient method for power quality events (PQEs) detection and classification based on Curvelet transform (CT) and optimized extreme learning machine (OELM). Initially, various PQEs signal data are extracted even under noisy and simultaneously occurred multi-event conditions to reflect the real-time conditions. Relevant features of all these extracted signals are computed by using a multi-resolution and multidirectional fast discrete CT (FDCT) approach. These features are used to classify the events accurately by the proposed OELM. In this classification strategy, a modified differential evolution (MDE) is introduced to optimize the conventional ELM to enhance its precision rate. The proposed novel approach is tested and analyzed under various noisy conditions with 20 dB, 30 dB, and 50 dB with single and multi PQEs conditions. Comparative results with other recently proposed approaches by various authors reveal that the proposed CT- and OELM-based classifier titled CT-OELM can be considered as a competitive choice for implementing in the real-time monitoring system.

Fast simulation of two-phase flow in three-dimensional digital images of heterogeneous porous media using multiresolution curvelet transformation

Advances in instrumentation have made it possible to obtain high-resolution images of heterogeneous porous media. Such advances and the rapid increase in computational power mean that direct numerical simulation of multiphase flow in two- and three-dimensional (3D) images of porous media is feasible and, therefore, models of pore space that represent simplification and approximation of the actual morphology are dispensable. The bottleneck for image-based simulation is its long computation time. We propose an approach for speeding-up simulation of multiphase flow in 3D images of porous media that utilizes curvelet transformations (CTs). The CTs are designed for denoising of images that contain complex curved surfaces, such as those of heterogeneous porous media. This is possible because the morphology of most porous media contain extended correlations, implying that their images carry redundant information that can be eliminated by a suitable CT. As a result, simulation of multiphase flow in the coarser images are far less computationally intensive. The new approach is used to simulate two-phase flow of CO2 and brine in a 3D image of Berea sandstone. We demonstrate that the results with the CT-processed image are as accurate as those with the original one, while computations are significantly faster by a speedup factor between one and more than two orders of magnitude.

Greedy segmentation based diabetic retinopathy identification using curvelet transform and scale invariant features

Diabetic retinopathy (DR) is the major reason of vision loss in the active population. It can usually be prevented by regulating the blood glucose and providing a timely treatment. DR has clinical features recognized by the experts including the blood vessel area, exudates, neovascularization, hemorrhages, and microaneurysm. Because DR has some varieties and complexities due to its geometrical and haemodynamic features, it is hard and time-consuming to detect DR in manual diagnosis. In Computer Aided Diagnosis (CAD) systems, the features of DR fundus images are detected using computer vision techniques. In this paper, a CAD system is proposed, which distinguishes automatically whether the fundus is normal or it suffers from diabetic retinopathy disease. As preprocess morphological operations like filtering, opening, and dilation are applied to the images firstly, then, Optic Disk (OD) segmentation is implemented using Greedy algorithm. Because of the intensity of an OD is similar to some DR intensities, OD regions are removed from the fundus images for an accurate feature extraction. The features extracted with Curvelet Transform (CT) and Scale Invariant Feature Transform (SIFT), respectively, are concatenated to provide a feature set that defines the fundus data optimally. Finally, the feature set is given to the Support Vector Machines (SVM), K-Nearest Neighborhood (KNN), and Naïve–Bayes (NB) classifiers for the DR identification purpose. The proposed method achieves the highest accuracy and sensitivity as 92.8% and 97.6%, respectively, with SVM and specificity as 92.5% with KNN classifier.

Speeding-up Simulation of Multiphase Flow in Digital Images of Heterogeneous Porous Media by Curvelet Transformation

Multiphase fluid flow in porous media is important to a wide variety of processes of fundamental scientific and practical importance. Developing a model for the pore space of porous media represents the first step for simulating such flows. With rapid increase in the computation power and advances in instrumentation and imaging processes, it has become feasible to carry out simulation of multiphase flow in two- and three-dimensional images of porous media, hence dispensing with development of models of pore space that are based on approximating their morphology. Image-based simulations are, however, very time consuming. We describe an approach for speeding-up image-based simulation of multiphase flow in porous media based on curvelet transformations, which are specifically designed for processing of images that contain complex curved surfaces. Most porous media contain correlations in their morphology and, therefore, their images carry redundant information that, in the curvelet transform space, can be removed efficiently and accurately in order to obtain a coarser image with which the computations are far less intensive. We utilize the methodology to simulate two-phase flow of oil and water in two-dimensional digital images of sandstone and carbonate samples, and demonstrate that while the results with the curvelet-processed images are as accurate as those with the original ones, the computations are speeded up by a factor of 110–150. Thus, the methodology opens the way toward achieving the ultimate goal of simulation of multiphase flow in porous media, namely, making image-based computations a standard practice.

Performance Evaluation of Face Recognition system by Concatenation of Spatial and Transformation Domain Features

Face biometric system is one of the successful applications of image processing. Person recognition using face is the challenging task since it involves identifying the 3D object from 2D object. The feature extraction plays a very important role in face recognition. Extraction of features both in spatial as well as frequency domain has more advantages than the features obtained from single domain alone. The proposed work achieves spatial domain feature extraction using Asymmetric Region Local Binary Pattern (ARLBP) and frequency domain feature extraction using Fast Discrete Curvelet Transform (FDCT). The obtained features are fused by concatenation and compared with trained set of features using different distance metrics and Support Vector Machine (SVM) classifier. The experiment is conducted for different face databases. It is shown that the proposed work yields 95.48% accuracy for FERET, 92.18% for L-space k, 76.55% for JAFFE and 81.44% for NIR database using SVM classifier. The results show that the proposed system provides better recognition rate for SVM classifier when compare to the other distance matrices. Further, the work is also compared with existing work for performance evaluation.

Extraction Method of Water Surface Weak Texture Based on Improved Curvelet Transformation

Extraction Method of Water Surface Weak Texture Based on Improved Curvelet Transformation

Liver Lesions and Acute Intracerebral Hemorrhage Detection Using Multimodal Fusion

Medical image fusion is designed to help physicians in their decisions by providing them with a preclinical image with enough information. Accurate assessment and effective treatment of the disease reduce the time it takes to relieve the symptoms of the disease. This article utilizes an effective data fusion approach to work on two different imaging modalities; computed tomography (CT) and magnetic resonance imaging (MRI). The data fusion approach is based on the combination of singular value decomposition (SVD) and the Fast Discrete Curvelet Transform (FDCT) techniques to reduce processing time during the fusion process. The SVD-FDCT data fusion approach is being tested with two multimodal medical image fusion applications. The first application concerns the detection of liver lesions and the second application concerns the early detection of acute intracerebral hemorrhage. Experimental tests demonstrate that not only the SVD-FDCT data fusion algorithm can treat the curved objects and edges effectively as the FDCT do. But also, the throughput of the fusion algorithm is comparable to related fusion algorithms such as principal component analysis (PCA), Transform and Discrete Wavelet Transform (DWT), dual-tree complex wavelet transform (DT-CWT), and Curvelet fusion algorithms.

An improved iris recognition system based on the fusion of the curvelet and DTCWT

In recent years, iris recognition has been emerged as one of the most popular biometric techniques because it guarantees high universality, distinctiveness, permanence, collectability, performance, acceptability, circumvention. In the paper we propose an improved system for iris recognition with high accuracy by fusing curvelet and dual tree complex wavelet transform. In our system, the main features are extracted from pre-processed/normalized iris images using both curvelet and Dual Tree Complex Wavelet Transform (DTCWT) tranforms. After performing different classifiers independently, all the results are fused to get final classification in the decision level to increase the accuracy of system. Finally, the random forest classifier and CATIA dataset are used to measure the performance of the proposed method. The experimental results show that the technique of the paper based on fusion of the curvelet and DTCWT is promising when compared with other existing similar techniques.

A Robust Medical Images Watermarking Using FDCuT-DCT-SVD

One way to prevent image duplication is by applying watermarking techniques. In this work, the watermarking process is applied to medical images using the Fast Discrete Curvelet Transforms (FDCuT), Discrete Cosine Transform (DCT), and Singular Value Decomposition (SVD) methods. The medical image of the host is transformed using FDCuT so that three subbands are obtained. High Frequency (HF) subband selected for DCT and SVD applications. Meanwhile, SVD was also applied to the watermark image. The singular value on the host image is exchanged with the singular value on the watermark. Insertion of tears by exchanging singular values does not cause the quality of medical images to decrease significantly. The experimental results prove that the proposed FDCuT-DCT-SVD algorithm produces good imperceptibility. The proposed algorithm is also resistant to various types of attacks, including JPEG compression, noise enhancement attacks, filtering attacks, and other common attacks.

Novel Adaptive Sparse-Spike Deconvolution Bearing Fault Detection Method Based on Curvelet Transform

This paper has proposed a novel bearing fault detection method about adaptive Sparse-spike Deconvolution based on Curvelet Transform (CTSSD), where the novel technique about adaptive Sparse-spike Deconvolution names after ASSD. Its purpose is to recover the pulse sequence from a vibration signal including complex noise, and to evaluate the periodic pulse position and pulse amplitude. Firstly, in order to make the results sparse and improves the stability of the result, the L1 norm regularization method is proposed in this paper, which is used to constrain the signal pulse sequence sparsely. Secondly, considering that regularization parameters are not adaptive, the Quantum behavior Particle Swarm Optimization (QPSO) algorithm is proposed to determine the optimal regularization parameters, adaptively. Finally, considering that the periodic features of ASSD extraction are not continuous, the Curvelet transform is further introduced. The fault signal is transformed into the Curvelet domain, and the Curvelet coefficient is used to characterize the fault signal pulse sequence. This method proposed in this paper is applied to the simulation signal and the vibration signal of rolling bearing fault, and is compared with the ASSD and the minimum entropy deconvolution (MED) to verify the reliability and effectiveness.

Simultaneous Interpolation and Deblending of 3-D Seismic Data by Iterative Thresholding

Blended acquisition can improve the efficiency of seismic data acquisition sharply, thus decreasing the acquisition costs. However, there may exist irregularity in blended data, which poses challenges for traditional seismic data processing. Thus, the deblending or interpolation should be done as a prerequisite. Because the deblending and interpolation can affect each other, we propose a unified 3-D joint deblending and interpolation method with a sparsifying transform and a sparsity promotion strategy in the blending fold of 4. To overcome the huge computational cost of 3-D curvelet transform (CT), we implement iterative thresholding in each principal frequency slice efficiently with 2-D CT. With decades of iterations, we can obtain an estimate of the regularized and deblended data. The core idea is that unblended signal can be characterized sparsely, and the blending noise and sampling irregularity have low-amplitude values in the CT domain. If blending was not used during acquisition, the proposed method becomes a pure interpolation algorithm. Similarly, if no sampling irregularity is present in the recorded data, the proposed method turns into a traditional deblending method. Numerical examples on the 3-D synthetic and field artificially blended data demonstrate the validity of the proposed method in simultaneously removing the blending noise and sampling irregularity. The regularized, deblended data can be beneficial for subsequent seismic data inversion and migration procedures.

Adaptive Multiple Subtraction Based on an Accelerating Iterative Curvelet Thresholding Method.

In the seismic exploration, recorded data contain primaries and multiples, where primaries, as signals of interest, can be used to image the subsurface geology. Surface-related multiple elimination (SRME), one important class of multiple attenuation algorithms, operates in two stages, multiple prediction and subtraction. Due to the phase and amplitude errors in the predicted multiples, adaptive multiple subtraction (AMS) is the key step of SRME. The main challenge of this technique resides in removing multiples without distorting primaries. The curvelet-based AMS methods, which exploit the sparsity of primary and multiple in curvelet domain and the misfit between the original and estimated signals in data domain, have shown outstanding performances in real seismic data processing. These methods are realized by using the iterative curvelet thresholding (ICT), which has heavy computation burden since it includes two forward/inverse curvelet transform (CuT) pairs in each iteration. To ameliorate the computational cost, we propose an accelerating ICT method by exploiting the misfit between the original and estimated signals in curvelet domain directly. Since the proposed method only needs do one forward/inverse CuT pair, it is faster than the traditional ICT method. Considering that the error of the predicted multiple is frequency-dependent, we furthermore introduce the joint constraints within different frequency bands to stabilize and improve the multiple attenuation. Synthetic and field examples demonstrate that the proposed method outperforms the traditional ICT method. In addition, the proposed method has shown to be suitable for refining other AMS methods' results, yielding a SNR improvement of 0.5-2.8 dB.

A Contrast Adjusted Wavelet and Curvelet Transform Based Fusion of Breast Images

Restoration is one of the image processing techniques to restore the distorted image. The distorted image can be any type like blurred image, noise added either while storing or capturing of the images. the traditional restoration techniques are geometric correction, different types of filters to remove the noises. Generally, the restoration is applied to the single image to retrives its information. In this, the restoration process is applied in the application of image fusion of medical images. the reason to chose the image fusion process is to improve its entropy. The medical images used in this paper is the mammogram and MRI-breast image. In this, the image fusion is performed with the help of wavelet and curvelet transform. The curvelet transform is applied to the restored mammogram image with the help of contrast adjusted top-hat filter process. The wavelet transform is applied to the MRI image because it has more volume of data to acquire important details. The fused image is evaluated with the help of entropy, mean standard deviation and variance. The fused image has efficient value as compared to its original image but it is higher than the DTCWT-fused image. To verify the quality of the proposed method, the psnr is evaluated to determine the noise present in the image. From the evaluation, the noise is less and entropy is higher in the proposed method. Hence, the contrast adjusted wavelet curvelet fusion is the best restoration and fusion process in the breast images.

An Intertwining of Curvelet and Linear Canonical Transforms

In this article, we introduce a novel curvelet transform by combining the merits of the well-known curvelet and linear canonical transforms. The motivation towards the endeavour spurts from the fundamental question of whether it is possible to increase the flexibility of the curvelet transform to optimize the concentration of the curvelet spectrum. By invoking the fundamental relationship between the Fourier and linear canonical transforms, we formulate a novel family of curvelets, which is comparatively flexible and enjoys certain extra degrees of freedom. The preliminary analysis encompasses the study of fundamental properties including the formulation of reconstruction formula and Rayleigh’s energy theorem. Subsequently, we develop the Heisenberg-type uncertainty principle for the novel curvelet transform. Nevertheless, to extend the scope of the present study, we introduce the semidiscrete and discrete analogues of the novel curvelet transform. Finally, we present an example demonstrating the construction of novel curvelet waveforms in a lucid manner.

Face Recognition Using Various Feature Extraction Approaches

This paper introduces an experimental study on the recognition of the person’s face by utilizing three Techniques of extraction: Principle Components Analysis (PCA), Linear Discriminant Analysis (LDA) and Contourlet- Curvelet Transform (CCT). The results of these approaches were observed and compared to discover the perfect scheme for identification of human faces. The tests have been carried out on the faces databases of (ORL),(UMIST), and (JAFFE). The results acquired by the methods were quantified by altering the ratio of train to test photos in three categories: 75/25, 55/45 and 35/65. The evaluation results showed that the CCT extraction method provides better results than the others. The highest recognition rate was recorded for the CCT approach (recognition rate=98.980%) when the (train/test) photos ratio is (75/25). Furthermore, the best recognition rates for the LDA and PCA were 96.391% and 95.127% respectively. The Matlab R2019b program was used for implementing and testing the algorithms.