检索结果-内蒙古大学图书馆

Solving Quadratic Systems With Full-Rank Matrices Using Sparse or Generative Priors

IEEE TRANSACTIONS ON signal processing 2025年 73卷 477-492页

作者： Chen, Junren Ng, Michael K. Liu, Zhaoqiang Univ Hong Kong Dept Math Hong Kong 852 Peoples R China Hong Kong Baptist Univ Dept Math Hong Kong 852 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

The problem of recovering a signal x is an element of R-n from a quadratic system{yi=x(T)A(ix), i=1,...,m} with full-rank matrices A(i) frequently arises in applications such a sun assigned distance geometry and sub-wavelength imaging. With i.i.d. standard Gaussian matrices A(i) , this paper addresses the high-dimensional case where m << n by incorporating prior knowledge of x. First, we consider a k-sparse x and introduce the thresholded Wirtinger flow (TWF) algorithm that does not require the sparsity level k. TWF comprises two steps: the spectral initialization that identifies a point sufficiently closetox (up to a sign flip) when m=O(k(2)logn),and the thresholded gradient descent which, when provided a good initialization, produces a sequence linearly converging to x with m=O(k log n) measurements. Second, we explore the generative prior, assuming that x lies in the range of an L-Lipschitz continuous generative model with k-dimensional inputs in an l(2)-ball of radius r. With an estimate correlated with the signal, we develop the projected gradient descent (PGD)algorithm that also comprises two steps: the projected power method that provides an initial vector with O(root k log(L)/m) l(2)-error given m=O( k log(Lnr))measurements, and the projected gradient descent that refines the l(2)-error to O(delta) at a geometric rate when m=O(k log Lrn/delta(2)). Experimental results corroborate our theoretical findings and show that: (i)our approach for the sparse case notably outperforms the existing provable algorithm sparse power factorization;(ii) leveraging the generative prior allows for precise image recovery in the MNIST dataset from a small number of quadratic measurements.

关键词： Sparse matrices Complexity theory signal processing algorithms Vectors Phase measurement Compressed sensing Standards Particle measurements image segmentation image reconstruction Generative prior projected gradient descent projected power method quadratic system sparse prior wirtinger flow

来源：评论

学校读者我要写书评

暂无评论

Adaptive Wavelet Techniques for Pattren Analysis 4

Adaptive Wavelet Techniques for Pattren Analysis

引用

4th IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering, MI-STA 2024

作者： Abdallatif, Munira H. Rgibi, Ahmed E. Alarbish, Amany K. Abdaljlil, Sana A. Oshah, Abdallah A. Sabratha University Faculty of Engineering Sabratha Libya

ISBN: (纸本)9798350372632

Wavelet analysis, a computational method, decomposes data into frequency components, analyzed by scale, effective for signals with discontinuities. Originating from diverse fields like mathematics, physics, and engineering, wavelet theory finds applications in image compression, radar, and more. Using scalable wavelet functions, it allows precise signal reconstruction, differing from constant scale methods. This study compares adapted and traditional wavelets, emphasizing Finite Impulse Response (FIR) efficiency. Applying these wavelets for pattern recognition, particularly in spike detection in EEG data, highlights their versatility in complex signal processing. © 2024 IEEE.

关键词： signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

signal Modulation Recognition of Satellite Internet Based on Dual Input Convolutional Neural Network

Signal Modulation Recognition of Satellite Internet Based on...

引用

9th International Conference on signal and image processing (ICSIP)

作者： Pan, Yiyu Gao, Feng China Elect Technol Grp Corp Southwest Inst Commun Chengdu Peoples R China

ISBN: (纸本)9798350350920

In order to identify the main modulation modes used in satellite Internet communication systems, a communication signal modulation recognition algorithm based on double-ended convolutional neural network is proposed. The time domain waveform of the signal is transformed into the high-power spectrum and the time-frequency image, and further converted into gray images as the shallow feature expressions of the signal. The modulation recognition problem is converted into an image recognition problem, and a modulation recognition model based on dual input convolutional neural network is designed. Through the training of the network, the shallow features are extracted and mapped deeply, and the modulation recognition of the target signal is finally completed. The simulation results show that the performance of the proposed algorithm is significantly improved compared with the single feature input modulation recognition algorithm, and it has good recognition performance for satellite Internet signals

关键词： modulation recognition satellite Internet ResNet dual input

来源：评论

学校读者我要写书评

暂无评论

MSFRNet: Multiscale Feature Recomposition Network for Singleimage Dehazing

引用

CIRCUITS SYSTEMS AND signal processing 2025年 1-22页

作者： Pushpalatha, D. Prithvi, P. Natl Inst Technol Dept Elect & Commun Engn Warangal 506004 Telangana India

Single-image dehazing plays a critical role in enhancing complex computer vision tasks, such as object tracking, recognition and detection, especially in adverse weather conditions. Haze reduction improves visual clarity and quality, leading to more accurate downstream processing. However, many existing methods fail to account for the intricate blending of haze and background, leading to feature redundancy and suboptimal restoration in practical applications. To address these challenges, we propose a Novel, lightweight four-stage architecture referred as Multiscale Feature Recomposition Network (MSFRNet) for restoring haze-free images. Our network integrates two key components: Twin Prior Fusion Module (TPFM) and Pyramid Dilated Split Attention Unit (PDSAU). The TPFM integrates multiple sources of prior information, enhancing structural integrity and preserving fine details, while the PDSAU efficiently disentangles haze from important image features and recombines them for accurate image dehazing. Our network demonstrates significant performance improvements in terms of both accuracy and speed when tested on synthetic and real-world datasets, and outperformsover the existing state-of-the-art networks. With a runtime of just 7 ms and the designed lightweight architecture uses 2.24 million parameters, which showcases our network is highly efficient for real-time, and resource-constrained applications.

关键词： image dehazing Multiscale feature recomposition network (MSFRNet) Pyramid dilated split attention unit (PDSAU) Twin prior fusion module (TPFM)

来源：评论

学校读者我要写书评

暂无评论

Advanced video encryption using the opposition lotus effect-elliptic curve cryptography in signal processing applications

引用

signal image AND VIDEO processing 2025年第5期19卷 1-12页

作者： Alsowail, Rakan A. King Saud Univ Comp Skills Selfdev Skills Dept Deanship Common Year 1 Riyadh 11362 Saudi Arabia

The rapid advancement of network technologies and multimedia applications across various sectors, including military and industry, underscores the importance of safeguarding digital data, especially videos and images. Encryption of video is essential in making sensitive content into a completely unrecognizable form. However, traditional methods of encryption face severe difficulties in terms of resolution loss, high computational complexity, and low optimization, which makes the technique less practical and authentic. Addressing such issues, this paper describes the Opposition Lotus Effect-Elliptic Curve Cryptography (OLE-ECC) algorithm. The integration of elliptic curve cryptography with the Opposition Lotus Effect Algorithm enhances video encryption by generating secure key pairs resistant to cryptographic attacks. The video data is encrypted using generated keys by dividing the video stream into segments and applying encryption algorithms to each. This process involves four key phases such as channel segmentation, channel scrambling, generation of key streams from the logistic graph, and channel propagation. The use of multi-equation multi-key cryptography increases the safety of video data significantly while encrypted because it involves applying a number of mathematical equations along with multiple keys. This technique effectively manages the encryption of dynamically generated video files and allows the possibility of encrypting different segments of the video with different keys, making it efficient in performance for real-time streaming applications. For video decryption, the encrypted video is sent over the communication channel, the decryption process includes bit-wise exclusion, rearrangement of channel blocks, and pixel reordering, which increases the reliability of the recovered video frames. Furthermore, the program for revealing, combined with xOR operations, allows the recovery of hidden pixels without loss of quality. Message Authorization Codes a

关键词： Elliptic curve cryptography Lotus effective algorithm Multi-equation multi-key cryptography Opposition-based learning strategy Video encryption

来源：评论

学校读者我要写书评

暂无评论

Accurate and Compact Approximate 4:2 Compressors with GDI Structure

引用

CIRCUITS SYSTEMS AND signal processing 2023年第7期42卷 4148-4169页

作者： Ghanatabadi, Mohammad Ebrahimi, Behzad Akbari, Omid Islamic Azad Univ Dept Elect & Comp Engn Sci & Res Branch Tehran Iran Tarbiat Modares Univ Dept Elect & Comp Engn Tehran Iran

The technology development, combined with chip size reductions, has significantly increased power density. Furthermore, the power limitation in portable devices has increased the importance of power consumption considerably. Approximate computing as an emerging paradigm leverages the error resiliency of applications to decrease power consumption. In this paper, we propose four approximate 4:2 compressors. We utilize the gate diffusion input to achieve significant area reduction in the proposed compressors. Afterward, we employ these compressors in the structure of Dadda multipliers. Compared to the state-of-the-art works, the proposed compressors result in, on average, 45% and 42% higher accuracy and lower area, respectively. Circuit simulations were carried out at a 32-nm carbon nanotube field-effect transistor technology node by HSPICE. The comparisons between our proposed compressors and exact compressor indicate that there has been an average improvement of 55%, 60% and 46% in the number of transistors, power consumption, and delay, respectively. In addition, the proposed multipliers were used in three image processing applications, including image multiplication, sharpening, and smoothing. The results show up to 46% and 70% improvement in the mean structure similarity index metric and peak signal-to-noise ratio compared to the state-of-the-art.

关键词： Approximate computing 4 2 compressors Accuracy improvement Multiplier Area-efficient image processing applications

来源：评论

学校读者我要写书评

暂无评论

Gait Deviation Assessment: from signal to image Analysis 13

Gait Deviation Assessment: from Signal to Image Analysis

引用

13th International Conference on image processing Theory Tools and applications

作者： Hermez, Lorenzo Galarraga, Omar Houmani, Nesma Vigneron, Vincent Garcia-Salicetti, Sonia Inst Polytech Paris Telecom SudParis SAMOVAR F-91120 Palaiseau France UGECAM Ile de France Movement Anal Lab F-77170 Coubert France Univ Paris Saclay EA 4526 Informat Bioinformat & Syst Complexes IBISC F-91020 Evry France

ISBN: (纸本)9798331541859;9798331541842

In this paper, we propose a novel framework for gait quality assessment based on image analysis, extending the traditional signal- based approach. Specifically, we construct Cycle Dissimilarity images (CDI) from raw gait signals. Such images summarize all local dissimilarities existing in the dynamics between a gait signal and one normal gait reference. Also, we construct a typical dissimilarity image, by matching each normal gait reference to itself. Then, we propose to quantify gait deviations by computing the distance between the CDIs and the typical dissimilarity images. Our results indicate that, compared to the signal-based approach, this new framework leads to a more precise gait deviation assessment, and a more refined characterization of motor impairments, as hemiparesis, tetraparesis, and paraparesis.

关键词： clinical gait analysis cycle dissimilarity image normal gait reference image dynamic time warping deviation score motor impairments

来源：评论

学校读者我要写书评

暂无评论

image Enhancement for Better VRU Detection in Challenging Weather Conditions 6

Image Enhancement for Better VRU Detection in Challenging We...

引用

6th International Conference on Communications signal processing and their applications

作者： Elgazwy, Ahmed Ouda, Hossameldin Elmoghazy, Ammar Abdelkader, Ghadeer Page, Austin Elgazzar, Khalid Khamis, Alaa Ontario Tech Univ IoT Res Lab Oshawa ON Canada Connected Vehicles & HMI Grp Canadian Tech Ctr Gen Motors Saitama Japan

ISBN: (纸本)9798350384826;9798350384819

This paper introduces a new approach to improve the performance of object detection techniques in challenging weather conditions through image enhancement. In 2018, a tragic accident occurred while testing a self-driving vehicle under severe bad lighting conditions, where a person crossing the street with a bicycle was not detected early enough for the vehicle to take action, which led to the death of the cyclist. This shows the dire need for robust, fast, and efficient detection techniques in adversarial conditions. In this paper, we propose a novel processing pipeline that contains a multilabel classifier trained to capture quality issues in a given frame and then passes it to proper filters to enhance the quality. The image qualities we target in this study include low visibility/bad lighting conditions, blurring, and image distortion. The raw frame goes through a multi-label classifier first to detect possible quality degradation. The frame then passes through various filters to fix the detected qualities accordingly. Performance evaluation shows that the proposed multilabel classifier achieves 80% accuracy during testing with a 20-ms average inference time for each frame. The proposed pipeline also enhances the frame processing delay by 3x and increases the confidence score of the YOLO detection algorithm by 5% on average.

关键词： image enhancement VRU detection assisted and automated driving vehicles inclement weather perception

来源：评论

学校读者我要写书评

暂无评论

Warship image Segmentation Network based on Void Convolution and Attention Mechanism

Warship Image Segmentation Network based on Void Convolution...

引用

9th International Conference on signal and image processing (ICSIP)

作者： Chen, Hongyan Yin, Donghui Qin, Zhen Wu, Qiong Acad PAP Dept Informat & Commun Hangzhou Peoples R China

ISBN: (纸本)9798350350920

In recent years, deep learning (DL) technology has developed rapidly in the field of image segmentation, which improves the accuracy of image segmentation compared with traditional image segmentation. This paper proposes an improved Mask R-CNN network based on cavity convolution and attention mechanism, which is more suitable for warship image segmentation. In addition, to solve the problem of insufficient data sets, the method of data enhancement is adopted to establish warship data sets. Through experiments, it is found that the warship image segmentation method in this paper can get more accurate segmentation effect on the warship image segmentation task, in which the average segmentation accuracy of small target warships is improved by about 8.5%.

关键词： mask R-CNN image segmentation empty convolution attention mechanism data enhancement

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable AI-enabled vectored median filter for real-time image denoising and edge preservation in FPGA-based smart imaging systems

引用

Multimedia Tools and applications 2025年 1-15页

作者： Sambamurthy, Nanduri Kamaraju, Maddu Department of Electronics and Communication Engineering Seshadri Rao Gudlavalleru Engineering College Andhra Pradesh Gudlavalleru521356 India

This paper introduces an innovative reconfigurable AI-enabled vectored median filter designed for FPGA-based multi-image processing systems. The central focus is on mitigating image quality degradation caused by mixed impulsive noise during the transmission and reception of images in various applications, diverging from the conventional emphasis on smart vision systems. In our proposed integrated system, we integrate an RGB-Y filter with an AI-enabled impulse detection and impulse de-noising-based image filter. This pioneering approach effectively suppresses noise in multi-color images while preserving essential edge details crucial for diverse smart vision systems. The algorithm introduces a novel technique of substituting noisy pixels with processed central values within the image filtering window, ensuring fidelity to the original pixel—an imperative consideration for applications beyond traditional smart imaging. To address elevated noise densities encountered in a broad spectrum of applications, our methodology adopts a hybrid sorting approach for median filtering and impulse processing. This ensures robust noise reduction without imposing excessive computational complexity. The AI-enabled vectored median filter system achieves a noteworthy reduction in dynamic power consumption, showcasing a remarkable 46% decrease in power consumption and an 82% reduction in area when compared to existing systems. This holds significant advantages in meeting resource and power-aware constraints across various smart vision systems. A comprehensive performance evaluation, including metrics such as PSNR (Peak signal-to-Noise Ratio), MSE (Mean Squared Error), IEF (image Enhancement Factor), and SSIM (Structural Similarity Index), validates the effectiveness of the filter in enhancing image quality—a pivotal factor for a diverse range of multi-image processing systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Median filters

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：