Curvelet Transform Research Articles

Weak Seismic Signal Enhancement Using Curvelet Transform and Compressive Sampling

Conventional curvelet-domain denoising methods suppress random noise by thresholding the amplitude of curvelet coefficients, which makes it hard to distinguish weak seismic signals from random noise because they share the same characteristic of weak amplitude in the curvelet domain. Here we put forward an innovative weak seismic signal enhancement method taht can distinguish weak seismic signals from random noise. After compressive sampling, the curvelet coefficients of weak seismic signals show significant amplitude reduction, whereas random noise does not. We take advantage of this characteristic and design a sensitivity coefficient, the absolute ratio of curvelet coefficients before and after compressive sampling. The sensitivity coefficient can distinguish weak seismic signals from random noise in the curvelet domain better than thresholding the amplitude of curvelet coefficients. The results of synthetic and field seismic data applications both indicate that our method outperforms the conventional curvelet-domain denoising method on weak seismic signal enhancement.

An Optimised Defensive Technique to Recognize Adversarial Iris Images Using Curvelet Transform

Deep Learning is one of the most popular computer science techniques, with applications in natural language processing, image processing, pattern identification, and various other fields. Despite the success of these deep learning algorithms in multiple scenarios, such as spam detection, malware detection, object detection and tracking, face recognition, and automatic driving, these algorithms and their associated training data are rather vulnerable to numerous security threats. These threats ultimately result in significant performance degradation. Moreover, the supervised based learning models are affected by manipulated data known as adversarial examples, which are images with a particular level of noise that is invisible to humans. Adversarial inputs are introduced to purposefully confuse a neural network, restricting its use in sensitive application areas such as biometrics applications. In this paper, an optimized defending approach is proposed to recognize the adversarial iris examples efficiently. The Curvelet Transform Denoising method is used in this defense strategy, which examines every sub-band of the adversarial images and reproduces the image that has been changed by the attacker. The salient iris features are retrieved from the reconstructed iris image by using a pre-trained Convolutional Neural Network model (VGG 16) followed by Multiclass classification. The classification is performed by using Support Vector Machine (SVM) which uses Particle Swarm Optimization method (PSO-SVM). The proposed system is tested when classifying the adversarial iris images affected by various adversarial attacks such as FGSM, iGSM, and Deepfool methods. An experimental result on benchmark iris dataset, namely IITD, produces excellent outcomes with the highest accuracy of 95.8% on average.

Personal Authentication Based on Curvelet Transform of Palm Print Moments

Image transformation provide deep meaning about images feature, so many type of image transformation are appear in the last decade years, one of them is curvelet transformation which improve the image processing techniques specially in field of feature extraction. Personal authentication adopt biometric information to be one of the major coefficients in this field.
 Palm print one of the main approaches for personal identification. So studying the moments extracted from coefficients of curvelet transform of palm print image adopted in order to get high efficient system for personalization systems. Two major phases are constructed in this research to adopt the moments of low frequency coefficient of the curvelet for personal identification. In the first phase a database was built for 50 persons by acquisition nine images for both hands (9 for left hand and 9for right hand). images are acquired and then processed to extract ROI (region of interest) by looking for the palm centroid then a square shape will be fixed based on that centroid. This preprocess play an important step for stable features. Histogram is applied to the images and then apply SOBLE operator and morphological operation to highlight features of palm print, then apply decomposition on each image based on curvelet transformation. Select low frequency coefficient (which hold the details). Evaluation of seven moments for each image (18images) then store there in the database file (so each person will have 126 values), this phase called personal database preparation. While the second phase is the detection phase, which apply the same steps to evaluate the moments as done in first phase then go through the database looking for the closest person to the tested one.
 System evaluation measured by statistical metrics which show good result goes up to 96% when applied on 50 person with different acquisition conditions. Also the effect of ROI dimension with individual hands and integrated both of them studied, which yield to recommended dimension of 192*192.

Optimized Convolutional Neural Network Recognition for Athletes’ Pneumonia Image Based on Attention Mechanism

After high-intensity exercise, athletes have a greatly increased possibility of pneumonia infection due to the immune function of athletes decreasing. Diseases caused by pulmonary bacterial or viral infections can have serious consequences on the health of athletes in a short period of time, and can even lead to their early retirement. Therefore, early diagnosis is the key to athletes’ early recovery from pneumonia. Existing identification methods rely too much on professional medical knowledge, which leads to inefficient diagnosis due to the shortage of medical staff. To solve this problem, this paper presents an optimized convolutional neural network recognition method based on an attention mechanism after image enhancement. For the collected images of athlete pneumonia, we first use contrast boost to adjust the coefficient distribution. Then, the edge coefficient is extracted and enhanced to highlight the edge information, and enhanced images of the athlete lungs are obtained by using the inverse curvelet transformation. Finally, an optimized convolutional neural network with an attention mechanism is used to identify the athlete lung images. A series of experimental results show that, compared with the typical image recognition methods based on DecisionTree and RandomForest, the proposed method has higher recognition accuracy for lung images.

An efficient watermarking technique using contourlet transform for medical images

The purpose of digital image watermarking is to hide secret information, objects, or logos on some multimedia content to secure the information or attack. Unauthorized individuals may attempt to access data or images during data transmission for illicit purposes. By establishing a hospital logo or Electronic Health Record (EHR) into a source images, medical image watermarking secures the data contained in medical images. In this paper, we present a brand-new watermarking scheme for medical images using contourlet transform. Each subband's energy value is calculated, and the middle energy subband is taken into account for the embedding process. Four different types of digital image watermarking techniques are used to compare the performance of the proposed watermarking scheme. (I)DWT without Band selection (II) DWT - SVD (IIII) DWT with Bandselection (IV) Curvelet Transform Peak Signal to Noise Ratio (PSNR), a performance metric, shows that the proposed method produces 52.63 percent of PSNR value for CT images and 53.98 percent of PSNR value for MRI images. When compared to other watermarking techniques, the contourlet transform provides better results, as evidenced by the Peak Signal to Noise Ratio.

An Intelligent Multimodal Medical Image Fusion Model Based on Improved Fast Discrete Curvelet Transform and Type-2 Fuzzy Entropy

An Intelligent Multimodal Medical Image Fusion Model Based on Improved Fast Discrete Curvelet Transform and Type-2 Fuzzy Entropy

Multimodal Medical Image Fusion with Improved Multi-Objective Meta-Heuristic Algorithm with Fuzzy Entropy

Medical image fusion enhances the significant and the valuable information such as exact abnormality localisation of the multimodal medical images. In the field of clinical environment, medical imaging acts as an important role in helping the doctors/radiologists. The information available in the images is important during the diagnosis. This can be enhanced using the multimodal medical image fusion technique through the integration of the information from several imaging modalities. Nowadays, several methodologies are proposed for fusing the medical images. Yet, the multimodal medical image fusion remains as a challenging task owing to the deprivation of medical images at the phase of acquisition. To handle this problem, this paper plans to develop the enhanced multi-objective medical image fusion model. Before initiating the fusion process, both the images to be fused are split into high-frequency sub-bands and low-frequency sub-bands by the improved Fast Discrete Curvelet Transform (FDCuT). Here, the fusion of low-frequency sub-images is accomplished by the averaging method, and high-frequency sub-images are fused by the optimised Type-2 fuzzy entropy. Both the FDCuT and Type-2 fuzzy entropy are enhanced by the multi-objective meta-heuristic algorithm by Adaptive Electric fish optimisation (A-EFO). The multi-objective function focuses on the “Peak Signal to Noise Ratio (PSNR), Structural SIMilarity (SSIM), Feature SIMilarity (FSIM)”. The comparison of the developed methodology over the traditional approaches observes enhanced performance with respect to visual quality measures.

GPR denoising via shearlet transformation and a data‐driven tight frame

ABSTRACTGround‐penetrating radar (GPR) is commonly used to detect buried and near‐surface geophysical structures. GPR denoising is necessary because some level of interference, such as from clutter, random noise and/or the column artefact, are inevitable and can cause false geological interpretations. Existing sparse representation methods, including wavelet transformation, curvelet transformation and dictionary learning, are critical in GPR denoising. However, they perform poorly in some cases because GPR data cannot be represented efficiently under severe interference. Thus, this study proposes an approach that combines shearlet transformation (ST) and a data‐driven tight frame (DDTF) to improve data sparsity. The ST can provide the prior information of GPR data to the DDTF, while the DDTF can self‐adaptively represent GPR data. First, we separate significant reflections and interferences using ST. Second, we apply the DDTF to further suppress the interferences by setting different thresholds in different ST scales and directions. Finally, we adopt inverse transformations to recover the GPR data. In the experiments, ST is used to show the differences between the significant reflections and interferences of the synthetic GPR data. We also sequentially remove each interference of the synthetic GPR data to clearly highlight the performance of the method. To ensure the effectiveness of the ST‐DDTF approach, we test the method using synthetic GPR data from different models, along with some example field GPR data. The ST‐DDTF method, which is aimed at improving data sparsity, shows state‐of‐the‐art results relative to more standard GPR denoising methods. Although our approach is time consuming, it is useful in processing small GPR data and obtaining accurate denoising results.

Offline Handwritten Character and Numeral Recognition

Automatic Character Recognition for the handwritten Indic script has listed up as most the challenging area for research in the field of pattern recognition. Although a great amount of research work has been reported, but all the state-of-art methods are limited with optimal features. This article aims to suggest a well-defined recognition model which harnessed upon handwritten Odia characters and numerals by implementing a novel process of decomposition in terms of 3rd level Fast Discrete Curvelet Transform (FDCT) to get higher dimension feature vector. After that, Kernel-Principal Component Analysis (K-PCA) considered to obtained optimal features from FDCT feature. Finally, the classification is performed by using Probabilistic Neural Network (PNN) on handwritten Odia character and numeral dataset from both NIT Rourkela and IIT Bhubaneswar. The outcome of proposed scheme outperforms better as compared to existing model with optimized Gaussian kernel-based feature set.

Unconstrained Hand Dorsal Veins Image Database and Recognition System

Hand veins can be used effectively in biometric recognition since they are internal organs that, in contrast to fingerprints, are robust under external environment effects such as dirt and paper cuts. Moreover, they form a complex rich shape that is unique, even in identical twins, and allows a high degree of freedom. However, most currently employed hand-based biometric systems rely on hand-touch devices to capture images with the desired quality. Since the start of the COVID-19 pandemic, most hand-based biometric systems have become undesirable due to their possible impact on the spread of the pandemic. Consequently, new contactless hand-based biometric recognition systems and databases are desired to keep up with the rising hygiene awareness. One contribution of this research is the creation of a database for hand dorsal veins images obtained contact-free with a variation in capturing distance and rotation angle. This database consists of 1548 images collected from 86 participants whose ages ranged from 19 to 84 years. For the other research contribution, a novel geometrical feature extraction method has been developed based on the Curvelet Transform. This method is useful for extracting robust rotation invariance features from vein images. The database attributes and the veins recognition results are analyzed to demonstrate their efficacy.

Robust Facial Recognition System using One Shot Multispectral Filter Array Acquisition System

Face recognition in the visible and Near Infrared range has received a lot of attention in recent years. The current Multispectral (MS) imaging systems used for facial recognition are based on multiple cameras having multiple sensors. These acquisition systems are normally slow because they take one MS image in several shots, which makes them unable to acquire images in real time and to capture moving scenes. On the other hand, currently there are snapshot multispectral imaging systems which integrate a single sensor with Multispectral Filter Arrays (MSFA) allow having at each acquisition an image on several spectra. These systems drastically reduce image acquisition time and are able to capture moving scenes in real time. This paper proposes a study of robust facial recognition using Multispectral Filter Array acquisition system. For this goal, a MSFA one-shot camera was used to collect the images and a robust facial recognition method based on Fast Discrete Curvelet Transform and Convolutional Neural Network is proposed. This camera covers the spectral range from 650 nm to 950 nm. A comparison of the facial recognition system using Multispectral Filter Arrays camera is made with those that using multiple cameras. Experimental results proved that face recognition systems whose acquisition systems are designed using MSFA perform more efficiently with an accuracy of 100%.

An Efficient Hybrid Clustering and Feature Extraction Techniques for Brain Tumor Classification

Most aggressive and common disease is Brain tumors and it leads to very short life expectancy in its highest grade. For proper treatment, such tumors needs to be identified in early stages and detecting brain tumors, medical imaging is used as an important tool. Although, for diagnosing such tumors, MRI (Magnetic Resonance Imaging) is used very often and it is assumed as a highly suitable technique. From brain magnetic resonance imaging (MRI) data, edema and tumor inference is a challenging task due to brain tumors blurred boundaries, complex structure and external factors like noise. For alleviating noise sensitivity and enhancing segmentation stability, a hybrid clustering algorithm is proposed in this research work. Certain processes like classification, feature extraction, hybrid clustering and pre-processing are included in this proposed model. For segmentation of brain tumors, proposed a morphological operation. Skull stripping and contrast enhancement are two process performed in pre-processing stage. It is possible to detect high contrast regions under contrast enhancement. In second stage, Enhanced K- means algorithm is combined with Fuzzy C- Means Clustering (FCM), where images are segmented as clusters. Algorithm’s stability can be enhanced using this clustering techniques while minimizing clustering parameter’s sensitivity. Segmented objects are converted into representations using representation and feature extraction techniques. Major attributes and features are described in a better manner using these techniques. The Fast Discrete Curvelet Transform (FDCT) is used for performing feature extraction in this technique for minimizing complexity and enhancing performance. At last, for classification, deep belief network (DBN) is used in this work. And it uses the concept of optimized DBN, for which Improved dragonfly optimisation algorithm (IDOA) is utilized. This proposed model is termed as IDOA-DBN model. When compared with other classification techniques, brain tumors can be detected effectively using proposed model.

IMAGE RETRIEVAL BASED ON DISCRETE CURVELET TRANSFORM

Content-Based Image Retrieval (CBIR) is a process of searching for an image according to the content or feature that is within it. Nowadays, most image retrieval applications have been developed to meet these needs, so this application will provide comfort in introducing and searching for an image. This paper proposed a standard structured framework with three stages: Preprocessing is the first step, in which noise from images is removed using various filters. The filters' results are compared to determine the best and most appropriate filter for the images. Feature Extraction of images using Curvelet Transform is the second stage. The third stage includes similarity measurement between query image features to database image features and extracting the identical image from the image dataset. The system was performed using Matlab 2017b, GUI and, with ten different classes of 1000 images using a coral database. The results show improved performance of precision and recall when higher decomposition levels are used.

Image Enhancement Based on Fan Filter Parameters Adjustment

In the field of image processing, there is an urgent need to adopt image transformations. In this paper, work is done on image coefficients after decomposing them through Curvelet transformations obtained through the fan filter. The research deals with two stages: the first is to study the effect of the Fan filter by adopting angles (8, 16, 32) on the image (Lina.jpg) of size (256*256) after being analyzed using Curvelet transformations at scales (2,3,4) through comparing a set of measurements (Contrast, Energy, Correlation, MSE, and PSNR) for both the original and reconstructed images. It can be found that Contrast and Energy criteria remain the same for the original and reconstructed images according to different levels of analysis or directions, so the value of the Correlation measure is 1. The value of the MSE criterion is very small and is almost not affected by the change of the number of angles in one scale, but it is slightly affected by increasing the scale analysis. What was mentioned above applies to the PSNR criterion as well. As for the second stage of the research, which included decomposing the image to its coefficients, canceling the effect of one of these coefficients, and then reconstructing it. The results proved that the two criteria (Contrast and Energy) were not affected with falling Correlation criteria from 1 to values ​​ranging from (0.9987_0.9997) depending on the number of scales used in the Curvelet analysis and the number of angles used in Fan filter (8,16,32). The results also showed an increase in the MSE value when dropping some frequencies, and a corresponding decrease in the PSNR value. Whereas, the decrease in the MSE scale was demonstrated at a specific scale with the increase in the number of angles in the Fan filter, in contrast to the PSNR scale.

Multi-stage guided-filter for SAR and optical satellites images fusion using Curvelet and Gram Schmidt transforms for maritime surveillance

ABSTRACT Synthetic aperture radar (SAR) images depend on the dielectric properties of objects with certain incident angles. Thus, vessels and other metallic objects appear clear in SAR images however, they are difficult to be distinguished in optical images. Synergy of these two types of images leads to not only high spatial and spectral resolutions but also good explanation of the image scene. In this paper, a hybrid pixel-level image fusion method is proposed for integrating panchromatic (PAN), multispectral (MS) and SAR images. The fusion method is performed using Multi-stage guided filter (MGF) for optical images pansharpening, to get high preserving spatial details and nested Gram-Schmidt (GS) and Curvelet-Transform (CVT) methods for SAR and optical images,to increase the quality of the final fused image and benefit from the SAR image properties. The accuracy and performance of the proposed method are appraised using Landsat-8 Operational-Land-Imager (OLI) and Sentinel-1 images subjectively as well as objectively using different quality metrics. Moreover, the proposed method is compared to a number of state-of-the-art fusion techniques. The results show significant improvements in both visual quality and the spatial and spectral evaluation metrics. Consequently, the proposed method is capable of highlighting maritime activity for further processing.

Curvelet Transform based Denoising of Multispectral Remote Sensing Images

With the advent of sensor technology, the exertion of multispectral image (MSI) is comely omnipresent. Denoising is an essential quest in multispectral image processing which further improves recital of unmixing, classification and supplementary ensuing praxis. Explication and ocular analysis are essential to extricate data from remote sensing images for broad realm of supplications. This paper describes curvelet transform based denoising of multispectral remote sensing images. The implementation of curvelet transform is done by using both wrapping function and unequally spaced fast Fourier transform (USFFT) and they diverge in selection of spatial grid which is used to construe curvelets at every orientation and scale. The coefficients of curvelets are docket by a scaling factor, angle and spatial location criterion. This paper crisps on denoising of Linear Imaging Self Scanning Sensor (LISS) III images. The proposed denoising approach has also been collated with some existing schemes for assessment. The efficacy of proposed approach is analyzed with calculation of facet matrices such as Peak signal to noise ratio and Structural similarity at distinct variance of noise..

Medical image fusion with convolutional neural network in multiscale transform domain

Multimodal medical image fusion approaches have been commonly used to diagnose diseases and involve merging multiple images of different modes to achieve superior image quality and to reduce uncertainty and redundancy in order to increase the clinical applicability. In this paper, we proposed a new medical image fusion algorithm based on a convolutional neural network (CNN) to obtain a weight map for multiscale transform (curvelet/ non-subsampled shearlet transform) domains that enhance the textual and edge property. The aim of the method is achieving the best visualization and highest details in a single fused image without losing spectral and anatomical details. In the proposed method, firstly, non-subsampled shearlet transform (NSST) and curvelet transform (CvT) were used to decompose the source image into low-frequency and high-frequency coefficients. Secondly, the low-frequency and high-frequency coefficients were fused by the weight map generated by Siamese Convolutional Neural Network (SCNN), where the weight map get by a series of feature maps and fuses the pixel activity information from different sources. Finally, the fused image was reconstructed by inverse multi-scale transform (MST). For testing of proposed method, standard gray-scaled magnetic resonance (MR) images and colored positron emission tomography (PET) images taken from Brain Atlas Datasets were used. The proposed method can effectively preserve the detailed structure information and performs well in terms of both visual quality and objective assessment. The fusion experimental results were evaluated (according to quality metrics) with quantitative and qualitative criteria.

A Mosaic Method for Side-Scan Sonar Strip Images Based on Curvelet Transform and Resolution Constraints.

Due to the complex marine environment, side-scan sonar signals are unstable, resulting in random non-rigid distortion in side-scan sonar strip images. To reduce the influence of resolution difference of common areas on strip image mosaicking, we proposed a mosaic method for side-scan sonar strip images based on curvelet transform and resolution constraints. First, image registration was carried out to eliminate dislocation and distortion of the strip images. Then, the resolution vector of the common area in two strip images were calculated, and a resolution model was created. Curvelet transform was then performed for the images, the resolution fusion rules were used for Coarse layer coefficients, and the maximum coefficient integration was applied to the Detail layer and Fine layer to calculate the fusion coefficients. Last, inverse Curvelet transform was carried out on the fusion coefficients to obtain images in the fusion area. The fusion images in multiple areas were then combined in the registered images to obtain the final image. The experiment results showed that the proposed method had better mosaicking performance than some conventional fusion algorithms.

Digital Mammograms with Image Enhancement Techniques for Breast Cancer Detection: A Systematic Review.

Digital mammograms with appropriate image enhancement techniques will improve breast cancer detection, and thus increase the survival rates. The objectives of this study were to systematically review and compare various image enhancement techniques in digital mammograms for breast cancer detection. A literature search was conducted with the use of three online databases namely, Web of Science, Scopus, and ScienceDirect. Developed keywords strategy was used to include only the relevant articles. A Population Intervention Comparison Outcomes (PICO) strategy was used to develop the inclusion and exclusion criteria. Image quality was analyzed quantitatively based on peak signal-noise-ratio (PSNR), Mean Squared Error (MSE), Absolute Mean Brightness Error (AMBE), Entropy, and Contrast Improvement Index (CII) values. Nine studies with four types of image enhancement techniques were included in this study. Two studies used histogram-based, three studies used frequency-based, one study used fuzzy-based and three studies used filter-based techniques. All studies reported PSNR values whilst only four studies reported MSE, AMBE, Entropy, and CII values. Filter-based was the highest PSNR values of 78.93, among other types. For MSE, AMBE, Entropy, and CII values, the highest were frequency-based (7.79), fuzzy-based (93.76), filter-based (7.92), and frequency-based (6.54) respectively. In summary, image quality for each image enhancement technique is varied, especially for breast cancer detection. In this study, the frequency-based of Fast Discrete Curvelet Transform (FDCT) via the UnequiSpaced Fast Fourier Transform (USFFT) shows the most superior among other image enhancement techniques.

Assessment of Internal Damage in Sandwich Structures by Post-Processing of Mode Shapes Using Curvelet Transform.

Identification and quantification of structural damage is one of the crucial aspects of proper maintenance of mechanical and civil structures, which is directly related to their integrity and safety. The paper presents a novel approach for detecting various types of damage in sandwich structures by processing the mode shapes using a hybrid algorithm based on the curvelet transform and the standardized damage index concept. The proposed approach uses the properties of directional selectivity, absence of the boundary effect, typical of such a class of transforms, and excellent filtration capabilities of the curvelet transform as well as the classification hypothesis in the standardized damage index, which allows the exclusion of irrelevant information and emphasizes proper damage location and shape. The proposed hybrid algorithm allowed to successfully identify a subsurface core damage in sandwich structures, such as local lack of a core or its debonding from facings. The performed quantification study aimed to evaluate the correctness of identified damage shape confirmed the validity and accuracy of the proposed algorithm not only for the damage detection and localization but also for the estimation of the size of structural damage.