检索结果-内蒙古大学图书馆

An MDAC-Less Pipelined ADC for AI-Powered Medical Imaging Applications

IEEE SENSORS JOURNAL 2024年第23期24卷 39182-39194页

作者： Dhiman, Saurabh Shrimali, Hitesh Indian Inst Technol Mandi Sch Comp & Elect Engn Mandi 175075 Himachal Prades India

An imaging system generally trades between image quality and power consumption. The higher the pixel density, the better the quality of image, however, at the expense of power hungry front-end data converters. Recently, the intensive back-end computation has been tailored with the integration of artificial intelligence (AI) algorithms in the image signal processing.(ISP) unit. Such AI-powered ISP has dragged the front-end data converters to its limits. Sensing the need of low-power, hardware-efficient front-end data conversion, this work proposes the unrolled monotonic binary split algorithm (UMBSA)-based pipelined analog-to-digital converter (ADC) architecture for the AI-driven medical imaging applications. The proposed algorithm eliminates the need of m-bit/stage digital-to-analog converter (DAC) and the resulting capacitor mismatch, thereby providing an area- and energy-efficient solution to the on-chip AI-based imaging systems. A 40-MSa/s, 8-bit prototype ADC is designed and fabricated in CMOS 180-nm silicon-on-insulator (SOI) technology for medical imaging applications. The measurement results show a 55 ***(2)/conv. step of figure-of-merit with 58.97 dBc of spurious-free dynamic range (SFDR) and 43.11 dB of signal-to-noise-and-distortion ratio (SNDR) at an input data rate of 3.22 MHz, respectively.

关键词： Algorithm analog-to-digital converter (ADC) capacitor mismatch data converters low power medical imaging monotonic switching multiplying digital-to-analog converter (MDAC) pipeline ADC positron emission tomography (PET) imaging

来源：评论

学校读者我要写书评

暂无评论

HDMA-CGAN: Advancing image Style Transfer with Deep Learning

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2024年第9期38卷

作者： Liu, Huaqun Hu, Benxi Cao, Yu Beijing Inst Graph Commun Sch New Media 1 Sect 2Xinghua St Beijing 102600 Peoples R China

The integration of artificial intelligence (AI) and deep learning heralds a transformative era in pattern recognition and computer vision, notably in image style transfer. We introduce the hierarchical dynamic multi-attention cycle generative adversarial network (HDMA-CGAN), an innovative deep learning architecture poised to redefine image style transfer capabilities. HDMA-CGAN employs a novel multi-attention mechanism and color optimization strategies, enabling precise style replication with improved fidelity and vibrancy. Our model surpasses existing benchmarks in image quality, validated by leading metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and Fr & eacute;chet inception distance (FID). Although HDMA-CGAN advances the state of the art, it necessitates high computational resources and faces challenges with very high-resolution images. Future work could explore optimizing the model's efficiency for real-time applications and extending its application to video content. This work enhances the tools available for visual content creation and digital media enhancement, leveraging advanced pattern recognition and AI techniques to significantly impact computer vision and image processing.

关键词： Deep learning image style transfer HDMA-CGAN generative adversarial networks multi-attention mechanisms color space optimization

来源：评论

学校读者我要写书评

暂无评论

Realization of digital Protection Algorithm of National Traditional Culture Based on Virtual Reality Technology

Realization of Digital Protection Algorithm of National Trad...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Chen, Hongxia Hou, Lanbao School of Literature and Media Jingchu University of Technology Jingmen448000 China School of Mathematics and Physics Jingchu University of Technology Jingmen448000 China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

National traditional culture and traditional technology are the products of historical precipitation and indispensable precious resources. The establishment of national cultural database is of great significance for the protection and inheritance of cultural heritage. Aiming at the specific functional requirements of traditional cultural digital protection system for image segmentation and retrieval, this paper focuses on the common algorithms of image segmentation and feature matching. This paper analyzes and compares the applicability and processing.effect of each algorithm in ethnic patterns. EGBIS image segmentation algorithm and shape context feature matching algorithm are used to achieve high precision image processing. This paper designs and implements a national culture retrieval system that meets the application needs. Combined with the image characteristics of ethnic patterns and the application requirements of the system, this paper defines the concepts of source images, primitives and hyperprimitives, and establishes a relational database based on them. This study has laid a certain theoretical foundation for the study of digital inheritance of national culture. © 2025 SPIE.

关键词： image segmentation image retrieval Databases Feature extraction image processing.algorithms and systems image processing Visualization Distance measurement Virtual reality Visual analytics

来源：评论

学校读者我要写书评

暂无评论

An effective method for salt and pepper noise removal based on algebra and fuzzy logic function

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第4期83卷 9547-9576页

作者： Gao, Jianqiang Li, Li Ren, Xiandong Chen, Qian Abdul-Abbass, Yahya Mourad Jining Med Univ Sch Med Informat Engn Rizhao 276826 Shandong Peoples R China Univ Wisconsin Madison Dept Civil & Environm Engn Madison WI 53706 USA Univ Kufa Fac Comp Sci & Math Najaf Iraq

image denoising techniques are very important in modern digital image processing. Many classical denoising algorithms have evolved over the years, such as Butterworth filter, Mean filter, Median filter, Laplacian filter, Multidimensional filter, Gaussian filter and Wiener filter. In this paper, a new method of removing high density salt and pepper noise is proposed via using Lukasicwicz algebra with square root (MV-algebra) and fuzzy logic function for digital images. In the proposed method, a new constructed fuzzy logic function in MV-algebra is used to remove the salt and pepper noise in contaminated images. The proposed method is called LASRNM, which has a strong mathematical foundation and strong robustness in removing salt and pepper noise. Therefore, experiments on five datasets illustrate that our proposed LASRNM method works the best in high density salt and pepper noise situation in terms of the peak signal noise ratio (PSNR), signal to noise ratio (SNR) and structural similarity (SSIM).

关键词： image denoising Filtering Salt and pepper noise Lukasicwicz algebra with square root

来源：评论

学校读者我要写书评

暂无评论

Super-resolution enhancement and segmentation for digital rock based on multi-task joint deep neural network

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2024年 243卷

作者： Wang, Yuetian Qin, Ruibao Wei, Dan Li, Xiongyan Wang, Peng Ye, Xinyu CNOOC Res Inst Ltd Res Inst Explorat & Dev Beijing 100028 Peoples R China CNOOC Res Inst Ltd Natl Engn Res Ctr Offshore Oil & Gas Explorat Beijing 100028 Peoples R China

Reliable segmentation of pores and minerals from high-resolution (HR) digital rock data is the fundamental prerequisite for accurately characterizing the digital rock's physical properties. Limited by the complexity of the super-resolution (SR) issues and the user bias for segmentation, conventional SR enhancement and segmentation methods are generally brutal in satisfying the research demands. In recent years, with the introduction of deep learning technology into digital rock research, deep learning-based approaches for SR enhancement or segmentation methods have emerged and achieved significantly better effects than conventional approaches. Most deep learning-based digital rock SR enhancement and segmentation processing.steps are currently separate. Still, preliminary studies have demonstrated that an end-to-end approach that integrates the two steps could achieve better performance. However, the training cost of 3D deep neural networks that can be directly applied to 3D digital rock processing.is usually expensive. In contrast, 2D networks cannot be effectively applied to SR segmentation of 3D digital rocks. Here, we present an end-to-end SR segmentation framework for 3D digital rock based on a 2D multi-task joint deep neural network. The multi-task joint networks utilize a parallel architecture that integrates the SegNet for the segmentation task and the EDSR for the SR task. We also improved the loss function to address the issue of category imbalance and proposed an approach to utilize the 2D network for 3D digital rock processing. We demonstrate the effectiveness of the proposed network framework, the improved loss function, and the 3D digital rock processing.strategies through ablation experiments on the high and lowresolution (LR) CT image datasets captured by imaging devices. The results show that the evaluation metrics and physical properties of the SR-segmented 2D\3D digital rocks align with the HR-segmented results (ground truth). It indicates that the

关键词： digital rock Deep learning Super-resolution Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation for remote sensing images using multi-layer semantic Markov random field with semantic text information

引用

digital SIGNAL processing 2025年 162卷

作者： Wei, Qian Miao, Tianyi Yao, Hongtai Jiao, Sumin Jin, Yong Hu, Zhentao Peng, Qinglan Henan Univ Sch Artificial Intelligence Zhengzhou 450046 Henan Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Henan Peoples R China

Semantic segmentation is an important task in remote sensing image processing. It assigns semantic labels to each pixel of the image. However, as the resolution of the remote sensing image increases, the boundary of the segmentation result appears to be blurred, and the region appears to be over-smoothing. Deep learning algorithms are unable to finely model textures due to operations such as convolution, pooling, and the introduction of a prior knowledge would increase the complexity of the network structure. The traditional Markov random field method can achieve effective fitting of the spatial structure through probabilistic statistical ideas, but it is highly dependent on the initialization results and does not make full use of the multi-modal information. In this paper, we propose a multi-layer structured object-based Gaussian-Markov random field model that introduces semantic text information. Firstly a multi-layer semantic structure is constructed and the deep learning-based methods are used to generate the initial results of each semantic layer;then the object-based Gaussian-Markov random field was constructed at each semantic layer. Specifically, object-based linear regression equations are constructed using parameters containing semantic text information in the feature field of each layer, and a two- point potential energy function combining statistical information and semantic text information is used in the label field. Given the above process, the multi-layer semantic inference process of the algorithm proposed in this paper is more interpretable. The proposed method is tested on the GID dataset, the LoveDA dataset, and some images from GeoEye. The experimental results show that the introduction of semantic text information and the multi-layer semantic structure can significantly improve the segmentation accuracy compared to other state-ofthe-art methods.

关键词： Remote sensing image Semantic inference Markov random field Information transmission Text information

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Based On-Board image Compression for the Φ-Sat-2 Mission

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 8063-8075页

作者： Guerrisi, Giorgia Del Frate, Fabio Schiavon, Giovanni Tor Vergata Univ Rome Dept Civil Engn & Comp Sci Engn I-00133 Rome Italy

The growing amount of data collected by Earth Observation (EO) satellites requires new processing.procedures able to manage huge quantity of information. Artificial intelligence (AI) and deep learning (DL) can provide advanced information also because of their ability to extract valuable information from complex data. Thanks to specific hardware platforms, these algorithms can be used also in space, opening the possibility for new procedures for intelligent data processing. The European Space Agency phi-Sat-2 mission was designed with the purpose of demonstrating the benefits of using AI in space by running AI-based applications on-board a CubeSat. We present here the convolutional autoencoder-based algorithm developed for on-board lossy image compression of the phi-Sat-2 mission and provide a first benchmark addressing a real space mission and a new image compression end-to-end architecture based on AI. image compression is a crucial application that allows to save transmission bandwidth and storage. In fact, images acquired by the sensor can be compressed on-board and sent to the ground where they are reconstructed. DL algorithms have already been successfully applied for image compression however performance degradation may occur in the context of a representative on-board environment. Therefore, besides analyzing the results for the local hardware environment, this article investigates the performance variation for the on-board setting. An additional piece of innovation is the introduction of an applicative metric for the evaluation of the compression to assess the applicability of the reconstructed images for other tasks. Such metric completes those more traditional based on the original-reconstructed image similarity.

关键词： Artificial intelligence (AI) convolutional neural networks (CNNs) CubeSat image compression on-board processing

来源：评论

学校读者我要写书评

暂无评论

Detection Of image Forgery Using Error Level Analysis 2

Detection Of Image Forgery Using Error Level Analysis

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Chandana, S. Nagarathna, C.R. Amrutha, A. Jayasri, A. Bnm Institute of Technology and Management Department of Ai and Ml Bangalore India

ISBN: (纸本)9798350306415

image forging is the manipulation of digital images using methods like copy-move, splicing, image removal etc. This paper provides an overview of the system's architecture, highlighting the integration of digital image processing. OpenCV, and machine learning algorithms image forgery detection is the process of identifying a modified image from the original. In the realm of digital image processing. image forgery detection is a critical task. The amount of altered and faked photographs has increased as digital imaging has become more prevalent and is used in a variety of fields, including forensics, media, and scientific study. They must guard the veracity of photos and stop the dissemination of false information and fake news. The detection of picture forgeries, however, is fraught with technological difficulties, including the requirement for reliable and accurate image features, the capacity to differentiate between various types of image alteration, and effective algorithms that can analyze enormous quantities of digital images. To meet these problems, the error level analysis image processing.technique and convolutional neural network are used to create a model that can predict the input images as forged ad unforged. The proposed model shows a better performance by giving an accuracy of 87%. © 2024 IEEE.

关键词： Convolutional Neural Networks (CNN) digital image processing Error Level Analysis (ELA) Forgery Detection Machine Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Evolving medical image classification: a three-tiered framework combining MSPLnet and IRNet-VGG19

引用

EVOLVING SYSTEMS 2025年第1期16卷 1-27页

作者： Annapoorani, G. Manikandan, P. Genitha, C. Heltin Anna Univ Dept CSE & IT Univ Coll Engn BIT Campus Tiruchirappalli India Jain Deemed Be Univ Comp Sci & Engn Bangalore Karnataka India St Josephs Coll Engn Dept Informat Technol Chennai India

Classification of images is an important process in the revolution of big data in healthcare. For classification and diagnosis, several developments have considerably improved digital clinical image processing. In many applications of medical imaging, medical image classification is a very essential task. Convolutional Neural Networks (CNNs) have displayed better performance in the classification of images for medical systems. However, CNN and conventional standardized classifiers suffer limitations in their performance due to a few reliability concerns, such as overfitting issues, feature extraction inefficiencies, and computational complexity. Therefore, a novel approach to medical image classification is proposed in this paper employing a three-tiered model that differs from conventional frameworks of multi-class classification to overcome these problems. In the first tier, the preparation of data includes the collection and transformation of five various clinical types of datasets such as Octoscope, Skin Cancer (PAD-UFES-20), The Kvasir dataset, Covid-19 dataset, and Chest X-Ray images (Pneumonia). The stage of pre-processing.guarantees the raw data is cleansed and organized for efficient analysis and training. In the second tier, sophisticated feature extraction utilizes a Multi-head Self-attention Progressive Learning Network on pre-processed data. The mechanism of Multi-head Self-attention and the techniques of Progressive Learning are leveraged to improve feature extraction, providing superior performance than traditional methods. In the third tier, the classification of features that are extracted is performed through Inception Residual Network-VGG19 (IRNet-VGG19), which combines the strengths of both Inception modules and the deep architecture of VGG19 to upgrade the accuracy of classification further. By evaluating all five datasets, the performance of IRNet-VGG19 shows better classification outcomes when compared with other existing approaches. The accur

关键词： Medical image classification Multi-head self-attention progressive learning network Inception modules VGG19 network

来源：评论

学校读者我要写书评

暂无评论

SonarNet: Hybrid CNN-Transformer-HOG Framework and Multifeature Fusion Mechanism for Forward-Looking Sonar image Segmentation

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： He, Ju Chen, Jianfeng Xu, Hu Yu, Yang Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

Forward-looking sonar (FLS) image segmentation plays a significant role in ocean engineering. However, the existing image segmentation algorithms present difficulties in extracting features from FLS images with weak semantic information, complex backgrounds, and strong environmental noises. Convolutional neural networks (CNNs) have demonstrated remarkable capabilities in semantic segmentation tasks, but the locality of convolution limits the ability to extract global context and long-range semantic information. The effective extraction of global contextual information is indispensable for achieving accurate segmentation results in sonar image processing. In this article, we propose a novel semantic segmentation architecture for FLS images called SonarNet. SonarNet is based on a hybrid CNN-transformer-HOG framework and comprises four modules: 1) the global-local encoder can extract both global and detailed feature information of the underwater target;2) the network decoder converts the high-semantic feature map into a pixel-level classification;3) as a bridge between dual encoders, the global-local fusion module ensures semantic consistency between different encoders;and 4) the HOG feature encoder and fusion can extract traditional manual features and perform feature alignment. We conducted comprehensive ablation experiments to validate the efficacy of the designed modules. Finally, experimentation revealed that SonarNet significantly outperforms other CNN-based and CNN-transformer FLS image segmentation methods.

关键词： Convolution neural network feature fusion forward looking sonar (FLS) image segmentation transformer

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：