检索结果-内蒙古大学图书馆

Variance-based reconfigurable modules for mode decision in intra prediction algorithm

AIN SHAMS ENGINEERING JOURNAL 2025年第7期16卷

作者： Sildas, Vanila Chandramani, Premanand Venkatesh Srinivasan, R. Ananthanarayanan, Rathinam SRM Valliammai Engn Coll Dept Elect & Elect Engn Kattankulathur 603203 Tamil Nadu India Axalume Inc San Diego CA USA Sri Sivasubramaniya Nadar Coll Engn Dept Informat Technol Kalavakkam 603110 Tamil Nadu India SRM Inst Sci & Technol Dept Elect & Elect Engn Kattankulathur 603203 Tamil Nadu India

This work is to design and migrate the hardware architecture implementation from static configuration to dynamic reconfiguration by investigating the viability of five types of intra prediction mode decision based on Similarity index in H.264 video processing. The variance-based five Similarity indices of cosine Similarity, sum of absolute differences (SAD), sum of squared differences (SSD), Hamming distance, and Euclidean distance are proposed to identify the best mode selection in the H.264 intra prediction process. The input parameter for Similarity selection was the variance-based threshold of the original block. The Similarity-based mode decision algorithm is reconfigurable hardware units made to perform nine modes of operations. A reconfigurable hardware implementation of system-on-chip architecture is compared in terms of power usage, resource utilization, and reconfiguration time for all the Similarity procedures. The variance-based hamming distance intra prediction algorithm can achieve 44% computational complexity reduction to select the optimal mode with minimum hardware resource utilisation compared to other proposed techniques.

关键词： Prediction algorithms Reconfigurable logic System-on-a-chip image analysis Video Compression

来源：评论

学校读者我要写书评

暂无评论

Novel hyperchaotic image encryption method using machine learning-RBF

引用

NONLINEAR DYNAMICS 2024年第20期112卷 18527-18550页

作者： Zhou, Shuang Zhang, Hongling Zhang, Yingqian Zhang, Hao Chongqing Normal Univ Sch Math Sci Chongqing 401331 Peoples R China Xiamen Univ Malaysia Sch Elect Engn & Artificial Intelligence Sepang 43900 Malaysia Xiamen Univ Tan Kah Kee Coll Sch Informat Sci & Technol Zhangzhou 363105 Peoples R China Taiyuan Univ Technol Coll Informat & Comp Taiyuan 030024 Peoples R China

In this paper, we put forward a novel hyperchaotic image encryption method using machine learning-RBF. First, a new 4D continuous hyperchaotic system is designed to address the degradation issue of low-dimensional continuous chaotic systems, which has a simpler structure, wider chaotic range, better distribution, and higher complexity compared with other chaotic systems based on Hopfield-type neural networks. Additionally, it has good randomness and can be implemented using hardware-based digital signal processing. Then, based on this system, we explore a new image encryption method using machine learning-radial basis function (RBF) neural network and true random numbers. Results show that compared with some other algorithms, our method is more secure and withstand common attacks.

关键词： Chaotic systems Radial basis function image encryption

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME CAPABILITY OF DLR'S BEAMFORMING SYNTHETIC APERTURE RADAR processing.architecture 49

REAL-TIME CAPABILITY OF DLR'S BEAMFORMING SYNTHETIC APERTURE...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal processing.(ICASSP)

作者： Schlemon, Maron Schulz, Martin Scheiber, Rolf Jaeger, Marc Oliva, Joel Amao German Aerosp Ctr DLR Microwaves & Radar Inst Cologne Germany Tech Univ Munich Chair Comp Architecture & Parallel Syst Munich Germany

ISBN: (纸本)9798350374520;9798350374513

Synthetic Aperture Radar (SAR) enables the generation of realistic and high-resolution 2D or 3D representations of landscapes. Typically, radar instruments are deployed in specially equipped, low-flying aircraft that capture a significant amount of raw data, necessitating image reconstruction processing. However, the aircraft's limited onboard processing.capabilities (power, size, weight, cooling, and communication bandwidth to ground stations) and the need to generate multiple SAR products, such as slant-range and geo-coded images during a single flight, require efficient onboard processing.and transmission to the ground station. This paper outlines the processing.architecture of the digital beamforming SAR (DBFSAR) employed by the German Aerospace Center (DLR) and the specific measures implemented to enable onboard processing. We elucidate the essential software optimizations and their integration into the SAR onboard routines, facilitating (near) real-time capability under certain conditions. Furthermore, we share the insights gained from our work and discuss their applicability to other processing.scenarios with limited resource availability.

关键词： Real-time SAR Resource-Constrained Computing On-Board SAR processing

来源：评论

学校读者我要写书评

暂无评论

Salp swarm algorithm with iterative mapping and local escaping for multi-level threshold image segmentation: a skin cancer dermoscopic case study

引用

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING 2023年第2期10卷 655-693页

作者： Hao, Shuhui Huang, Changcheng Heidari, Ali Asghar Chen, Huiling Li, Lingzhi Algarni, Abeer D. Elmannai, Hela Xu, Suling Wenzhou Univ Dept Comp Sci & Artificial Intelligence Wenzhou 325035 Peoples R China Ningbo Univ Affiliated Hosp Med Sch Dept Dermatol Ningbo 315020 Zhejiang Peoples R China Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol POB 84428 Riyadh 11671 Saudi Arabia

If found and treated early, fast-growing skin cancers can dramatically prolong patients' lives. Dermoscopy is a convenient and reliable tool during the fore-period detection stage of skin cancer, so the efficient processing.of digital images of dermoscopy is particularly critical to improving the level of a skin cancer diagnosis. Notably, image segmentation is a part of image preprocessing.and essential technical support in the process of image processing. In addition, multi-threshold image segmentation (MIS) technology is extensively used due to its straightforward and effective features. Many academics have coupled different meta-heuristic algorithms with MIS to raise image segmentation quality. Nonetheless, these meta-heuristic algorithms frequently enter local optima. Therefore, this paper suggests an improved salp swarm algorithm (ILSSA) method that combines iterative mapping and local escaping operator to address this drawback. Besides, this paper also proposes the ILSSA-based MIS approach, which is triumphantly utilized to segment dermoscopic images of skin cancer. This method uses two-dimensional (2D) Kapur's entropy as the objective function and employs non-local means 2D histogram to represent the image information. Furthermore, an array of benchmark function test experiments demonstrated that ILSSA could alleviate the local optimal problem more effectively than other compared algorithms. Afterward, the skin cancer dermoscopy image segmentation experiment displayed that the proposed ILSSA-based MIS method obtained superior segmentation results than other MIS peers and was more adaptable at different thresholds.

关键词： meta-heuristic algorithm multi-level threshold image segmentation salp swarm algorithm skin cancer diagnosis local escaping operator dermoscopy digital image

来源：评论

学校读者我要写书评

暂无评论

Research on Deep Learning-Driven High-Resolution image Restoration for Murals From the Perspective of Vision Sensing

引用

IEEE ACCESS 2023年 11卷 71472-71483页

作者： Xiao, Haiying Zheng, Hao Meng, Qiang Henan Univ Fine Arts Coll Kaifeng 475000 Peoples R China Zhengzhou Univ Phys Educ Coll Informat Management Ctr Zhengzhou 450000 Peoples R China

Due to the fact that murals are usually displayed on a large area, it is necessary to develop intelligent algorithms for high-resolution images. In recent years, deep learning has been widely applied in the field of image processing. For the problem of high-resolution image restoration in murals, deep learning technology can also be used to solve it. This article carries out systematic research on deep learning-driven high-resolution image restoration for murals from the perspective of vision sensing. Firstly, principal characteristics of mural paintings such as textures and structures are extracted using conventional vision feature representation. Then, the extracted feature contents are mapped into restorage schemes with the assistance of deep neural network structure, so that digital restoration of mural paintings can be realized. The proposed solution blocks high priority sample blocks, prevents sample blocks with a large number of unknown pixels from being processed, and reduces the continuous accumulation of errors caused by matching errors to achieve digital restoration of murals. The simulation results on real-world image sets show that compared to the baseline method, the recovery accuracy can be improved by more than 20%. This method can restore the main structure and texture details of complex scene images, especially in the case of large-scale information loss.

关键词： image restoration digital restoration high resolution image deep learning

来源：评论

学校读者我要写书评

暂无评论

image representation method based on Gaussian function and non-uniform partition

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第1期82卷 839-861页

作者： Zhao, WeiKang KinTak, U. Luo, HuiBin Macau Univ Sci & Technol Fac Innovat Engn Sch Comp Sci & Engn Macau Peoples R China

image representation or reconstruction methods are important in digital image processing. Due to different image features happening in different regions, in this work, an image representation algorithm based on Gaussian function and non-uniform partition is proposed to represent the image with different functions in non-uniform regions. That means the pixel values in each region can be approximated by an extension of the Gaussian function after applying the least square approximation. The experimental results prove that the proposed algorithm has better performance than other non-uniform partition algorithms in terms of reconstructed image quality and time complexity. In addition, the partition mesh density can reflect the texture complexity of image regions and help to determine where the watermark can be embedded. Therefore, a novel watermark algorithm based on the proposed non-uniform partition is constructed and tested. The results show that it can embed a big gray watermark into the host image without causing its obvious distortion. This indicates some of the advantages of the proposed image representation algorithm.

关键词： image representation image reconstruction Gaussian function Non-uniform partition Watermark embedding

来源：评论

学校读者我要写书评

暂无评论

The Big Bang of Deep Learning in Ultrasound-Guided Surgery: A Review

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2023年第9期70卷 909-919页

作者： Masoumi, Nima Rivaz, Hassan Hacihaliloglu, Ilker Ahmad, M. Omair Reinertsen, Ingerid Xiao, Yiming Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada Univ British Columbia Dept Radiol Dept Med Vancouver BC V6T 1Z4 Canada SINITEF Digital Dept Hlth Res N-7465 Trondheim Norway Concordia Univ Dept Comp Sci & Software Engn Montreal PQ H3G 1M8 Canada

Ultrasound (US) imaging is a paramount modality in many image-guided surgeries and percutaneous interventions, thanks to its high portability, temporal resolution, and cost-efficiency. However, due to its imaging principles, the US is often noisy and difficult to interpret. Appropriate image processing.can greatly enhance the applicability of the imaging modality in clinical practice. Compared with the classic iterative optimization and machine learning (ML) approach, deep learning (DL) algorithms have shown great performance in terms of accuracy and efficiency for US processing. In this work, we conduct a comprehensive review on deep-learning algorithms in the applications of US-guided interventions, summarize the current trends, and suggest future directions on the topic.

关键词： Three-dimensional displays Catheters Heart Brachytherapy Location awareness image segmentation Ultrasonic imaging Deep learning (DL) intervention percutaneous surgical guidance ultrasound (US)

来源：评论

学校读者我要写书评

暂无评论

Neural invertible variable-degree optical aberrations correction

引用

OPTICS EXPRESS 2023年第9期31卷 13585-13600页

作者： Cui, Shuang Wang, Bingnan Zheng, Quan Chinese Acad Sci Inst Software Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Optical aberrations of optical systems cause significant degradation of imaging quality. Aberration correction by sophisticated lens designs and special glass materials generally incurs high cost of manufacturing and the increase in the weight of optical systems, thus recent work has shifted to aberration correction with deep learning-based post-processing. Though real-world optical aberrations vary in degree, existing methods cannot eliminate variable-degree aberrations well, especially for the severe degrees of degradation. Also, previous methods use a single feed-forward neural network and suffer from information loss in the output. To address the issues, we propose a novel aberration correction method with an invertible architecture by leveraging its information-lossless property. Within the architecture, we develop conditional invertible blocks to allow the processing.of aberrations with variable degrees. Our method is evaluated on both a synthetic dataset from physics-based imaging simulation and a real captured dataset. Quantitative and qualitative experimental results demonstrate that our method outperforms compared methods in correcting variable-degree optical aberrations. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Aberration correction digital imaging image processing image quality Lens design Optical aberrations

来源：评论

学校读者我要写书评

暂无评论

Filling the Holes on 3D Heritage Object Surface Based on Automatic Segmentation Algorithm

引用

EXPERT SYSTEMS 2025年第2期42卷

作者： Nguyen, Sinh Van Le, Son Thanh Tran, Minh Khai Le, Sach Thanh Vietnam Natl Univ HCM City Int Univ Sch Comp Sci & Engn Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Ho Chi Minh Vietnam Ho Chi Minh City Univ Technol Fac Comp Sci & Engn Ho Chi Minh Vietnam

Reconstructing and processing.3D objects are activities in the research field of computer graphics, image processing.and computer vision. The 3D objects are processed based on geometric modelling (a branch of applied mathematics and computational geometry) or machine learning algorithms based on image processing. The computation of geometrical objects includes processing.the curves and surfaces, subdivision, simplification, meshing, holes filling or reconstructing the 3D surface's objects on both point cloud data and triangular mesh. While the machine learning methods are developed using deep learning models. With the support of 3D laser scan devices and LiDAR techniques, the obtained dataset is close to the original shape of the real objects. Besides, photography and its application based on modern techniques in recent years help us collect data and process the 3D models more precisely. This article proposes a new method for filling holes on the 3D object's surface based on automatic segmentation. Instead of filling the hole directly as the existing methods, we now subdivide the hole before filling it. The hole is first determined and segmented automatically based on the computation of its local curvature. It is then filled on each part of the hole to match its local curvature shape. The method can work on both 3D point cloud surfaces and triangular mesh surfaces. Compared to the state-of-the-art (SOTA) methods, our proposed method obtained higher accuracy of the reconstructed 3D objects.

关键词： 3D mesh digital heritage hole-filling point clouds reconstruction segmentation virtual museum

来源：评论

学校读者我要写书评

暂无评论

A novel image inpainting method based on a modified Lengyel-Epstein model

引用

COMPUTER VISION AND image UNDERSTANDING 2024年 249卷

作者： Wang, Jian Luo, Mengyu Chen, Xinlei Xu, Heming Kim, Junseok Nanjing Univ Informat Sci & Technol Sch Math & Stat Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Ctr Appl Math Jiangsu Prov Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Jiangsu Int Joint Lab Syst Modeling & Data Anal Nanjing 210044 Peoples R China Korea Univ Dept Math Seoul 02841 South Korea Nanjing Univ Informat Sci & Technol Sch Teacher Educ Nanjing 210044 Peoples R China

With the increasing popularity of digital images, developing advanced algorithms that can accurately reconstruct damaged images while maintaining high visual quality is crucial. Traditional image restoration algorithms often struggle with complex structures and details, while recent deep learning methods, though effective, face significant challenges related to high data dependency and computational costs. To resolve these challenges, we propose a novel image inpainting model, which is based on a modified Lengyel-Epstein (LE) model. We discretize the modified LE model by using an explicit Euler algorithm. A series of restoration experiments are conducted on various image types, including binary images, grayscale images, index images, and color images. The experimental results demonstrate the effectiveness and robustness of the method, and even under complex conditions of noise interference and local damage, the proposed method can exhibit excellent repair performance. To quantify the fidelity of these restored images, we use the peak signal-to-noise ratio (PSNR), a widely accepted metric in image processing. The calculation results further demonstrate the applicability of our model across different image types. Moreover, by evaluating CPU time, our method can achieve ideal repair results within a remarkably brief duration. The proposed method validates significant potential for real-world applications in diverse domains of image restoration and enhancement.

关键词： image inpainting Lengyel-Epstein model Explicit Euler's method

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：