检索结果-内蒙古大学图书馆

2nd International conference on Optical Communication and Optical Information processing, OCOIP 2024

作者： Yao, Yuxuan Yang, Guanglin Laboratory of Signal and Information Processing School of Electronics Peking University Beijing100871 China

ISBN: (数字)9781510688995

ISBN: (纸本)9781510688988

Holography is pivotal in various applications ranging from microscopy to data storage. However, the practical implementation of holography often necessitates compression, which inevitably degrades the quality of the reconstructed images. Addressing this challenge, a scheme of computer-generated hologram compression with convolutional neural networks optimized is proposed. In this scheme, our research investigates the potential of genetic algorithm, a class of evolutionary algorithms inspired by natural selection, to optimize the initial weights of the network. Experimental results show that the scheme is feasible. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Empirical Wavelet Frames

引用

ADVANCES IN DATA SCIENCE AND ADAPTIVE ANALYSIS 2025年第0期

作者： Gilles, Jerome Castro, Richard San Diego State Univ Dept Math & Stat 5500 Campanile Dr San Diego CA 92182 USA

Due to their adaptive nature, empirical wavelets (EWs) had several successes in many fields from engineering, science, medical signal/image processing. Recently, a general theoretical framework has been developed in the one-dimensional case, showing the possibility to build EWs from any classic mother wavelets. Given extensive literature both in theory and applications of classic wavelet frames, it is legitimate to ask about the feasibility of building EW frames. We address this question in this paper. We prove several results which provide conditions on the existence of EW frames taking into account the above-mentioned adaptability.

关键词： Empirical wavelets frames adaptive time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

Review on Deep Learning Network Architectures for image Reconstruction 5

Review on Deep Learning Network Architectures for Image Reco...

引用

5th International conference on image processing and Capsule Networks, ICIPCN 2024

作者： Lokula, Babitha Prasad, L.V Narasimha Tirumuri, Ramakrishna K L deemed to be university Institute of Aeronautical Engineering department of ECE Vaddeshwaram India Institute of Aeronautical Engineering department of ECE Hyderabad India K L deemed to be university department of ECE Vaddeshwaram India

ISBN: (纸本)9798350367171

In order to obtain the low resolution(LR) image's detailed information, super resolution(SR) image reconstruction is essential. From 1D projections, we can reconstruct images in 2D and 3D. The LR images attained have different details of the same scene for which the super resolution reconstruction is possible. In the field of computer vision, image reconstruction is used in a variety of applications including robotics, entertainment, reverse engineering, augmented reality, human-computer interaction, and animation. In addition, applications in the medical field like Magnetic Resonance Imaging (MRI), Computed Tomography (CT), x-rays, and ultrasound, among others, make use of image reconstruction. We may encounter limitations while reconstructing the image, such as noise, missing information, a low signal to noise ratio, and a low contrast to noise ratio. We even come across different issues and challenges in application of SR techniques like image registration, computational efficiency, robustness and performance limitations. To address the above-mentioned issues, we study numerous SISR architectures. In this paper, we'll talk about various techniques, their benefits, drawbacks, and Single image Super Resolution (SISR) architectures that can help improve super resolution image reconstruction in a variety of applications. © 2024 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A new algorithm for image edge detection based on phase stretch transform 3

A new algorithm for image edge detection based on phase stre...

引用

3rd International conference on Advanced Algorithms and signal image processing, AASIP 2023

作者： Dandan, He Parthasarathy, Rajamohan School of Information Engineering PingDingShan University 467000 China Centre for Network Security and IoT Faculty of Engineering Built Environment and Information Technology SEGi University 47810 Malaysia

ISBN: (纸本)9781510668522

Edge is the important feature in images, which has important applications in image processing, image analysis and image understanding. Accordingly, Edge detection is the basic problem in image processing and computer vision, and is one of the important research content in image processing. In this paper, the edge detection principle of phase stretch transform is analyzed, and the mathematical expression of s-Type phase filter with linear or sublinear group delay is derived. Three new phase filters are designed and good edge detection results are obtained. The phase stretch transform based image edge detection is extended to the fractional-order Fourier transform domain, and the simulation results show that the phase stretch transform in the fractional-order Fourier transform domain can also be used for image edge detection and feature description. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Design and Verification of an FPGA-Based MRI image Cluster processing

Design and Verification of an FPGA-Based MRI Image Cluster P...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Duvvuru, Abhiram Reddy Guntaka, Kumar Sai Reddy Jadhav, Shrikant San Jose State University Dept. Electrical Engineering San Jose United States California State University Northridge Dept. Computer Engineering Northridge United States

ISBN: (纸本)9798331504847

The FPGA-based MRI Cluster image processing System is designed to overcome the limitations of traditional MRI image processing, which often suffers from errors, high costs due to re-scans, and diagnostic delays. This system implements preprocessing techniques, such as median, average, and denoising filters, using a custom FPGA processor developed with System Verilog. In this work, we focused on enhancing image quality and processing speed. For example, the Peak signal-to-Noise Ratio (PSNR) values for one of the cases are 36.21 dB and 36.03 dB, demonstrating competitive performance compared to Python and MATLAB. The FPGA method also achieves a Mean Squared Error (MSE) as low as 15.57 for one of the cases, highlighting reduced error rates. The results show that the FPGA system achieves superior throughput and reduced error rates, demonstrating its capability to deliver high-quality images in real-time with minimal distortion. Validated using the UVM methodology, the design ensures reliable parallel processing and scalability. This FPGA-based approach significantly improves over traditional MRI image processing methods, making it a more efficient and cost-effective solution for medical imaging applications. © 2025 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Lossless Compression of Aurora Spectral images: A Spatial-Temporal-Spectral Joint Approach 17

Transformer-based Lossless Compression of Aurora Spectral Im...

引用

17th IEEE International conference on signal processing, ICSP 2024

作者： Cao, xinlong Li, Jiaojiao Li, Yuanqing Yan, Jiapeng Zheng, Zhenxing Xi'an University of Posts & Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi'an710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an710121 China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi'an710121 China

ISBN: (纸本)9798350387384

Aurora spectral image lossless compression has seen significant advancements in recent years. However, most compression algorithms are based on traditional image compression techniques, focusing solely on spectral and spatial correlations without considering temporal correlations. To further enhance compression performance, this paper proposes a Transformer-based point-by-point prediction algorithm for auroral spectral images, which simultaneously uses spatial, spectral and temporal contexts for prediction. Our prediction network consists of two parts: an encoder and a decoder. The encoder is composed of the encoding unit of the original Transformer and is used to extract features from spatial, spectral and temporal contexts. The decoder consists of fully connected layers and is used for prediction. Experimental results show that the average bitrate of this method is reduced by 0.179 bpp compared with the JPEG2000 algorithm, and the average bitrate is reduced by 0.054 bpp compared with the online DPCM algorithm. © 2024 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Human Detection: comparative analysis using YoloV5s, Yolov5l, Yolov5m, Yolov5n, Yolov5x Model 4

Camouflaged Human Detection: comparative analysis using Yolo...

引用

4th International conference on Artificial Intelligence and signal processing

作者： Mulla, Sufiya Mandavkar, Rajlaxmi Jamadar, Simran Magdum, Sneha Gurav, Uma KITs Coll Engn Autonomous Dept CSE Data Sci Kolhapur Maharashtra India

ISBN: (纸本)9798350350661;9798350350654

This research paper discusses about, The Camouflaged human or object Detection using different variations of YOLOV5. Our project deep dives into the analysis of YOLO(You Only Look Once) algorithm and it's different types for performance analysis. The proposed model, trained on the dataset with different regions and angles of images, utilizes YOLOv5 for efficient camouflaged human detection, with manual annotation of images used for training the dataset and calculated different outputs for performance analysis. There can be lot of applications of the Camouflaged object detection project. Even if it is Biodiversity conservation in Nature like detecting the animals or plants which gets camouflaged in the nature and are difficult to detect or detecting enemy military invasion. This algorithm can be combined with one or more other image processing algorithms also for better accuracy and easy implementation purpose. This research work is carried out on different variants of YOLOv5 algorithm. We have used the different variants like Yolov5l, Yolov5m, Yolov5n, Yolov5x enhancing accuracy and robustness. The performance analysis is carried out in terms of P curve (Precision), R curve(recall), PR curve(precision and recall) and F1 curve of each training set and also the confusion matrix for all the algorithms is calculated and it is observed that Yolov5l works better as compared to other YOLO variants.

关键词： YOLOv5 image processing Camouflaged object detection

来源：评论

学校读者我要写书评

暂无评论

Transplantation and optimization calculation of power inspection image matching application based on the ARM platform 3

Transplantation and optimization calculation of power inspec...

引用

3rd International conference on Advanced Algorithms and signal image processing, AASIP 2023

作者： Wei, Wei Rundong, Gan xun, Li Haibin, Su Zhu, Zhan Guizhou Power Grid Co. Ltd. Information Center Guiyang China Fangxin Technology Co. Ltd. Changsha China Hunan Electric Power Computing Power Integration Engineering Technology Research Center Changsha China

ISBN: (纸本)9781510668522

image matching is an important step in the process of power inspection image stitching and 3D reconstruction, which directly affects the effect of power line image stitching and 3D reconstruction, and is widely used in power line inspection. Traditional power inspection image matching applications are mostly implemented on x86 architecture, but ARM architecture has gradually entered the server field in recent years, showing high efficiency and energy-saving advantages, so it is necessary to transplant power inspection image matching applications to the server platform of ARM architecture. Since the application of image matching is very computation-based, in the process of porting the algorithm to the ARM platform, this paper adopts the Gaussian pyramid algorithm to accelerate the application of image matching through the search method from coarse to fine. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： image matching

来源：评论

学校读者我要写书评

暂无评论

ENHANCED INTERPRETABILITY IN LEARNED image COMPRESSION VIA CONVOLUTIONAL SPARSE CODING

ENHANCED INTERPRETABILITY IN LEARNED IMAGE COMPRESSION VIA C...

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Tu, Yiwen Tan, Wen Bao, Youneng Wang, Genhong Meng, Fanyang Liang, Yongsheng Harbin Inst Technol Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Shenzhen Technol Univ Shenzhen Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Compared to traditional image compression methods, learned image compression (LIC) methods have demonstrated increasingly superior rate-distortion performance. However, LIC networks are often regarded as black boxes, still lacking a theoretical understanding. Sparse coding provides the sparse and interpretable modeling for analyzing or synthesizing natural images in various signal and image processing applications. Therefore, we introduce convolutional sparse coding (CSC) into transform network for enhancing the interpretability of LIC methods. In this paper, we first employ CSC layers to achieve certain theoretical modeling for LIC network, and adopt a weight sharing strategy in encoderdecoder pair and attention mechanism to balance the complexity and performance. Additionally, we analyze the model robustness against data input perturbations and consider the impact of sparsity trade-off parameter in the CSC layer optimization process. Experimental results demonstrate that our method achieves comparable performance with the corresponding baseline, and our model is more robust.

关键词： Learned image compression sparse coding interpretability robustness

来源：评论

学校读者我要写书评

暂无评论

Medical image Segmentation of Systemic Lupus Erythematosus related Cerebral Small Vessel Disease

Medical Image Segmentation of Systemic Lupus Erythematosus r...

引用

2023 International conference on image, signal processing, and Pattern Recognition, ISPP 2023

作者： Yao, Zhiyuan xie, Zhiheng Cao, Lei College of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9781510666351

image segmentation is an important and difficult task in many medical applications. The segmentation results can be used to help doctors diagnose diseases, observe the lesion areas, and make surgical plans. Traditional medical image segmentation methods rely on experienced radiologists, which makes medical image segmentation time-consuming and costly. With the help of computer technology, the use of deep learning neural network for medical image segmentation has been applied in multiple disease lesions or organ segmentation tasks. Cerebral small vessel disease is a manifestation of systemic lupus erythematosus. In this paper, we apply Unet, Nested Unet and Recurrent Residual Unet to segment the collected medical images of systemic lupus erythematosus patients. The results of Unet and Nested Unet is better than Recurrent Residual Unet. All of the three networks can segment parts of lesion areas, but small areas are missed. The results of our experiments showed the performance of the existing segmentation neural networks on our dataset still need to be further improved to meet the requirements of practical applications. © 2023 SPIE.

关键词： Medical applications

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：