检索结果-内蒙古大学图书馆

Conference on image and signal processing for Remote Sensing XXVI

作者： Aburaed, Nour Panthakkan, Alavikunhu Al-Saad, Mina El Rai, Marwa Chendeb Al Mansoori, Saeed Al-Ahmad, Hussain Marshall, Stephen Univ Dubai Dubai U Arab Emirates Mohammed Bin Rashid Space Ctr Dubai U Arab Emirates Univ Strathclyde Glasgow Lanark Scotland

ISBN: (纸本)9781510638808

Nowadays, satellite images are used in various governmental applications, such as urbanization and monitoring the environment. Spatial resolution is an element of crucial impact on the usage of remote sensing imagery. As such, increasing the spatial resolution of an image is an important pre-processing step that can improve the performance of various image processing tasks, such as segmentation. Once a satellite is launched, the more practical solution to improve the resolution of its captured images is to use Single image Super Resolution (SISR) techniques. In the recent years, Deep Convolutional Neural Networks (DCNNs) have been recognized as a highly effective tool to reconstruct a High Resolution (HR) image from its Low Resolution (LR) counterpart, which is an open problem due to the inherent difficulty of estimating the missing high frequency components. The aim of this research paper is to design and implement a satellite image SISR algorithm by estimating high frequency details through training Deep Convolutional Neural Network (DCNNs) with respect to wavelet analysis. The goal is to improve the spatial resolution of multispectral remote sensing images captured by DubaiSat-2 satellite. The accuracy of the proposed algorithm is assessed using several metrics such as Peak signal-to-Noise Ratio (PSNR), wavelet-based signal-to-Noise Ratio (WSNR) and Structural Similarity Index Measurement (SSIM).

关键词： Remote Sensing wavelet Transform Super Resolution Convolutional Neural Network Deep Learning

来源：评论

学校读者我要写书评

暂无评论

A new multi-level radial difference encoded pattern for image classification and retrieval

引用

MULTIDIMENSIONAL SYSTEMS AND signal processing 2020年第4期31卷 1411-1433页

作者： Pavithra, L. K. Sree Sharmila, T. SSN Coll Engn Dept Informat Technol Chennai 603110 Tamil Nadu India

An image can be represented by different types of feature descriptors. Each descriptor holds specific details about the image. The image classification and retrieval applications use these extracted features to classify the query image and retrieve similar kinds of images presented in huge databases for the given query image. The discriminant feature in the form of a binary pattern available around each pixel of the image is extracted by taking the local pixel difference between each pixel and its neighboring pixels (i.e., sampling points) present in different radii. The discrete wavelet representation (i.e., multi-resolution) of the image has more information about the image compared to the image present in the spatial domain since each level of the multi-level decomposition discloses significant details about the image in separate channels. However, binary pattern extraction around each coefficient of the different levels of decomposed images lacks in producing the discriminant texture feature representation since it extracts a feature from each decomposition level at a time and concatenates them. Thus, the proposed work extracts the binary pattern around each coefficient of different levels of decomposed image from different radii. Then, the obtained binary patterns available in different decomposition levels are encoded to represent the discriminant texture feature around each pixel location. Consequently, the proposed work selects the multi-level decomposition based on the stationary wavelet transform, since it has the same resolution in each level of decomposition. The performance of the proposed feature descriptor is assessed over seven different sets of databases using image classification and image retrieval applications. Finally, the performance of the proposed work is compared with the state-of-the-art techniques involved in extracting spatial arrangement details of pixels available in the image.

关键词： Distance measure Ensemble classification image retrieval Multi-level decomposition Radial difference binary pattern

来源：评论

学校读者我要写书评

暂无评论

Fractional Spectral Graph wavelets and Their applications

引用

MATHEMATICAL PROBLEMS IN ENGINEERING 2020年第1期2020卷

作者： Wu, Jiasong Wu, Fuzhi Yang, Qihan Zhang, Yan Liu, Xilin Kong, Youyong Senhadji, Lotfi Shu, Huazhong Southeast Univ Lab Image Sci & Technol LIST Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China Univ Rennes INSERM LTSI UMR 1099 F-35042 Rennes France Univ Rennes Ctr Rech Informat Biomed Sino Francais CRIBs INSERM Rennes France Southeast Univ Nanjing Peoples R China Taiyuan Univ Technol Coll Data Sci Taiyuan 030024 Peoples R China

One of the key challenges in the area of signal processing on graphs is to design transforms and dictionary methods to identify and exploit structure in signals on weighted graphs. In this paper, we first generalize graph Fourier transform (GFT) to spectral graph fractional Fourier transform (SGFRFT), which is then used to define a novel transform named spectral graph fractional wavelet transform (SGFRWT), which is a generalized and extended version of spectral graph wavelet transform (SGWT). A fast algorithm for SGFRWT is also derived and implemented based on Fourier series approximation. Some potential applications of SGFRWT are also presented.

关键词： wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

DWT-QR based blind image watermarking method using firefly algorithm 28

DWT-QR based blind image watermarking method using firefly a...

引用

28th signal processing and Communications applications Conference (SIU)

作者： Altay, Seyma Yucel Ulutas, Guzin Ataturk Univ Bilgisayar Muhendisligi Bolumu Erzurum Turkey Karadeniz Tech Univ Bilgisayar Muhendisligi Bolumu Trabzon Turkey

ISBN: (纸本)9781728172064

Digital watermarking is a method used to protect intellectual property rights and copyrights. This study represents a blind method based on Discrete wavelet Transform (DWT) and QR decomposition. In this method, the cover image is firstly divided into non-overlapping blocks, and then the blocks with low standard deviation are selected to embed the watermark. After each of the selected blocks is decomposed by DWT, low frequency sub-bands are subjected to QR decomposition. The first row of the R matrix resulting from QR decomposition is used to embed the watermark bits. Firefly Algorithm (FA) is utilized to optimize the gain factor of embedding, which is effective in determining the robustness and imperceptibility of the watermarking scheme. To appraise the performance of the study, Peak signal to Noise Ratio (PSNR) is used to measure the perceptual quality and Normalized Correlation (NC) is used to evaluate robustness. According to experimental results, the perceptual quality of the proposed method is found to be higher than that of similar studies in the literature. In addition, it is established that the robustness of the method against attacks such as noise, cropping, compression, and filtering is better.

关键词： Firefly algorithm discrete wavelet transform robustness QR decomposition digital watermarking

来源：评论

学校读者我要写书评

暂无评论

A Multiplier-Less Level-3 Haar wavelet Transform Approximation Requiring Five Additions Only

A Multiplier-Less Level-3 Haar Wavelet Transform Approximati...

引用

Proceedings of the IEEE Dallas Circuits and Systems Workshop (DCAS)

作者： Morgana M. A. Da Rosa Guilherme Paim Henrique B. Seidel Sé rgio Almeida Eduardo A. C. Da Costa Sergio Bampi Graduate Program on Electronic Engineering and Computing Universidade Cat&#x00F3 lica de Pelotas (UCPel) Brazil Graduate Program in Microelectronics (PGMICRO) Federal University of Rio Grande do Sul (UFRGS) Brazil

ISBN: (数字)9781665498852

ISBN: (纸本)9781665498869

Approximate transform kernels have emerged as an alternative design to reduce the hardware complexity of digital signal processors by exploiting the intrinsic error resilience of many embedded consumer electronics applications such as signal, image and video processing, and computer vision. The approximate level-4 Haar wavelet transform (AxHWT-4) is the state-of-the-art approximate transform for ECG (electrocardiogram) signal processing and reduces more than nine times the energy consumption compared to the exact transform. In this work, we propose an approximate level-3 Haar wavelet transform (AxHWT-3) for increasing the hardware design efficiency with related to the AxHWT-4 while obtaining higher R-peak detection accuracy in the electrocardiogram signal. Our AxHWT-3 approximation is performed in the Haar matrix kernel to eliminate its multiplications which in the hardware design results in savings of energy consumption and VLSI hardware area. Our AxHWT3 proposal achieves an R-peak detection accuracy of more than 99% and reduces the energy consumption by 15.98 times and the VLSI area by 12.64 times compared to the exact solution (i.e., the original level-3 Haar). In addition, the proposed AxHWT3 outperforms the state-of-the-art AxHWT-4 with a savings of about 32% in power dissipation and 19.5% in VLSI area.

关键词： wavelet transforms Energy consumption Computer architecture Very large scale integration Electrocardiography signal processing Hardware

来源：评论

学校读者我要写书评

暂无评论

Segmentation and region quantification of bubbles in small bowel capsule endoscopy images using wavelet transform

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Sadeghi, Vahid Vard, Alireza Sharifi, Mohsen Mir, Hossein Mehridehnavi, Alireza Medical Image & Signal Processing Research Center School of Advanced Technologies in Medicine Isfahan University of Medical Sciences Isfahan Iran Department of Bioelectrics and Biomedical Engineering School of Advanced Technologies in Medicine Isfahan University of Medical Sciences Isfahan Iran Gastroenterologist & Hepatologist Fellowship of Endosonography Isfahan University of Medical Sciences Isfahan Iran

Objective: A large number of captured frames by the wireless capsule endoscopy have been contaminated with different amounts of bubbles. Bubbles can degrade the visualization quality of the small intestine mucosa. The aim of this study is to develop an objective method for evaluating the amount of bubbles in WCE images. Methods: Frames with varying levels of bubble occlusion were selected from the Kvasir capsule endoscopy dataset. The round shape bubbles have an edge in their boundaries. Edges in the spatial domain correspond to high-frequency bands in the frequency domain. Two automated edge detection approaches have been developed in a rule-based manner and evaluated to assess the amount of bubbles. The first approach involved high pass filtering using fast Fourier transform (FFT), while the second approach has been based on wavelet image decomposition and reconstruction by omitting approximation coefficients subband. Results: Both Fourier and wavelet transforms obtained approximately the same dice similarity score (DSC), and precision metrics, which were equal to 0.87, and 0.91, respectively. Based on the specificity measure, the FFT outperformed the Hough and wavelet transforms. However, the wavelet transform obtained a higher dice similarity score (DSC) (0.93), accuracy (0.95), and sensitivity metric (0.97) and was the fastest, with an execution time of 0.01 s per frame, making it suitable for real-time applications. Conclusion: The proposed technique provides an easy-to-implement method for quality reporting or objective comparison tools of different bowel preparation paradigms in real-time applications due to its fast execution time. The obtained results from two different datasets proved that the presented method has good generalization. © 2023

关键词： Bubble Fourier transform Small bowel wavelet transform Wireless capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

A generalized machine learning workflow to visualize mechanical discontinuity

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2022年第0期210卷 109963-109963页

作者： Liu, Rui Misra, Siddharth Texas A&M Univ Harold Vance Dept Petr Engn Coll Engn College Stn TX 77843 USA Texas A&M Univ Coll Geosci Dept Geol & Geophys College Stn TX 77843 USA

Accurate detection and mapping of mechanical discontinuity in materials has widespread industrial and research applications. We developed a generalized machine-learning framework for visualizing single mechanical discontinuity embedded in material of any composition, velocity, density, porosity, and size with limited data. The proposed visualization of discontinuity requires accurate estimations of the length, location, and orientation of the embedded discontinuity by processing multipoint wave-transmission measurements. k-Wave simulator is used to create a large dataset of elastic waveforms recorded during multi-point wave-transmission measurements through materials containing single mechanical discontinuity. k-Wave simulator considers the wave attenuation, dispersion, and mode conversion in wave motion. Discrete wavelet transform (DWT) and statistical feature extraction are essential for data preprocessing prior to the data-driven model development. DWT also minimizes the effect of noise. Using hyper-parameter tuning and cross validation, gradient boosting regression can visualize the mechanical discontinuity with an accuracy of 0.85, in terms of coefficient of determination. A double-layered neural network-based regression has better performance with an accuracy of 0.95. Use of convolutional neural network converts the predictive task from a waveform processing to an image processing problem. Convolutional neural network achieved a generalization performance of 0.91. The proposed generalized workflow requires robust simulation of wave propagation, signal processing, feature engineering, and model evaluation. Sensors closest to the source and those located opposite the source are the most significant for the desired visualization. Notably, the sensors closest to the source capture the non-linear associations, whereas the sensor on the border opposite to the source capture the linear associations between the measured waveforms and the properties of the mechanical d

关键词： Machine learning Regression Wave propagation Mechanical discontinuity Discrete wavelet transform signal processing

来源：评论

学校读者我要写书评

暂无评论

image Compression and Noise Reduction through Algorithms in wavelet Domain 26

Image Compression and Noise Reduction through Algorithms in ...

引用

IEEE 26th International Symposium for Design and Technology in Electronic Packaging (SIITME)

作者： Dumitrescu, Catalin Raboaca, Maria Simona Manta, Ioana Univ Politehn Bucuresti Fac Transports Bucharest Romania Natl Ctr Hydrogen & Fuel Cells Natl R&D Inst Cryogen & Isotop Technol ICSI Rm Va Ramnicu Valcea Romania

ISBN: (纸本)9781728175065

image compression and noise reduction are two important application in the field of digital image processing. The use of transformed domains plays an important role in both mentioned applications, offering a different representation of the data, in which the main characteristics to be processed become more distinct. image compression aims to reduce the number of bits needed for the digital representation of the image with or without an acceptable loss of image quality. The underlying idea behind the use of linear transforms in signal processing is a more efficient quantization of the coefficients corresponding to the transformed domain, compared to the case of the coefficients corresponding to the primary space. From this point of view, the wavelet transforms allow, due to the multi-resolution representation that they accomplish and the correlation between the sub-images of this representation, a more efficient quantization and entropic encoding of the coefficients corresponding to the transformed domain. In the field of image compression, the multi-resolution analysis property of the wavelet transform allows progressive quality-scalable and spatially scalable transmissions, very useful in applications that require interactive searching or when bandwidth transmission channels are available. The wavelet transform focuses most of the signal energy in the low pass sub-band with the lowest resolution, the coefficients of this sub-band having high absolute values. The rest of the coefficients obtained after decomposition have small absolute values, being canceled after the quantization process. A good compression rate can be obtained in this case if the absolute values of the coefficients and their locations are encoded separately.

关键词： image compression wavelet decomposition image denoise wavelet noise reduction

来源：评论

学校读者我要写书评

暂无评论

DEEP MULTI-SCALE GABOR wavelet NETWORK FOR image RESTORATION

DEEP MULTI-SCALE GABOR WAVELET NETWORK FOR IMAGE RESTORATION

引用

IEEE International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Dong, Hang Zhang, Xinyi Guo, Yu Wang, Fei Xi An Jiao Tong Univ Coll Artificial Intelligence Xian Peoples R China Xi An Jiao Tong Univ Sch Software Engn Xian Peoples R China

ISBN: (纸本)9781509066315

Due to the limitations of the imaging processors and complex weather conditions, image degradation is often inevitable. Existing deep learning-based image restoration methods often rely on the powerful feature representation capacity of deep networks and pay less attention to the inherent properties of the degradation signal, e.g. variations in spatial scale and orientations across the image, which makes them ineffective for the image restoration tasks. In this paper, we propose a Multi-scale Gaborwavelet Network (MsGWN) for image restoration. We apply the multi-scale architecture to extract the contaminated feature from input at different spatial scales, and thus the contaminated feature can be effectively restored in a corse-to-fine manner. However, using multi-scale architecture alone cannot remove the degradations with different orientations. To overcome this problem, we introduce a Gabor wavelet Module (GWM) to further extract the contaminated features from four orientations. By decomposing the features into four multi-orientation components, the restoration process can be facilitated by avoiding learning the mixed degradations all-in-one. We evaluate the proposed method on image demoireing, image deraining, and image dehazing. Experiments on these applications demonstrate that the proposed method can achieve favorable results against the state-of-the-art approaches.

关键词： image restoration Multi-scale Multi-orientation Gabor wavelet Deep learning

来源：评论

学校读者我要写书评

暂无评论

Opti-EN-net: Optimized ensemble deep neural network for the classification of Retinal Detachment through fundus images

引用

BIOMEDICAL signal processing AND CONTROL 2024年 91卷

作者： Yadav, Sonal Murugan, R. Goel, Tripti Natl Inst Technol Silchar Dept Elect & Commun Engn Biomed Imaging Lab BIOMIL Silchar 788010 Assam India

Background and problem statement: Retinal Detachment is a severe ocular situation that may lead to serious visual impairment without prior warning. The early identification of retinal detachment can enhance the probability of successful reattachment and improve vision outcomes. Manual diagnosing of retinal detachment is laborious, tedious, and very hard for enormous clinical applications. We proposed an innovative computer-assisted screening tool to identify retinal detachment from retinographic color fundus images. Methods: This work utilized five stages. Firstly, the data augmentation approaches are considered to increase the assorted variety of samples. Secondly, preprocessing techniques are used for better image analysis. Then, Resnet50 architecture is trained to extract relevant characteristics from the preprocessed fundus images. Afterward, a genetic algorithm selects the optimal features from the extracted features. Subsequently, the structure of Resnet50 undergoes a modification by removing the layers after the fully connected layer (FCL) with two randomized neural networks to classify retinal detachment, namely an extreme learning machine and a random vector functional-link network. In addition, the weights and biases of the earlier Resnet50 layers are frozen during the training these two classification algorithms. Finally, the outcomes of these two classification algorithms are ensembled using a majority voting mechanism to improve overall classification performance. Results: The performance scores of this work reveal that the Resnet50-GA-RVFL and Resnet50-GA-ELM models achieved accuracies of 98.70% and 97.78%, respectively. In contrast, our proposed Opti-EN-net model exhibited an increased accuracy of 99.44%, outperforming several recent state-of-the-art methodologies. Conclusion: The outcomes reveal that our proposed Opti-EN-net framework has promising capabilities in accurately identifying retinal detachment in its early stages, thereby reducing the wor

关键词： Retinal detachment wavelet packet decomposition Convolution neural network Genetic algorithm Random vector functional link network Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：