检索结果-内蒙古大学图书馆

Self-attention residual network-based spatial super-resolution synthesis for time-varying volumetric data

IET image processing 2024年第6期18卷 1579-1597页

作者： Ma, Ji Ye, Yuhao Chen, Jinjin Zhejiang Univ Technol Sch Comp Sci & Technol Hangzhou Peoples R China Commun Univ Zhejiang Sch Design & Art Hangzhou Peoples R China Macau Univ Sci & Technol Fac Humanities & Arts Macau Peoples R China

In the field of scientific visualization, the upscaling of time-varying volume is meaningful. It can be used in in situ visualization to help scientists overcome the limitations of I/O speed and storage capacity when analysing and visualizing large-scale, time-varying simulation data. This paper proposes self-attention residual network-based spatial super-resolution (SARN-SSR), a spatial super-resolution model based on self-attention residual networks that can generate time-varying data with temporal coherence. SARN-SSR consists of two components: a generator and a discriminator. The generator takes the low-resolution volume sequences as the input and gives the corresponding high-resolution volume sequences as the output. The discriminator takes both synthesized and real high-resolution volume sequence as the input and gives a matrix to predict the realness as the output. To verify the validity of SARN-SSR, four sets of time-varying volume datasets are applied from scientific simulation. In addition, SARN-SSR is compared on these datasets, both qualitatively and quantitatively, with two deep learning-based techniques and one traditional technique. The experimental results show that by using this method, the closest time-varying data to the ground truth can be obtained. This paper proposes a novel self-attention residual network-based spatial super-resolution (SARN-SSR) framework for upscaling time-varying volume data in scientific visualization. It utilizes a generator and discriminator based on generative adversarial networks to generate high-resolution volume sequences. Comparative evaluations demonstrate that SARN-SSR outperforms state-of-the-art techniques in generating accurate time-varying volume datasets. image

关键词： computer graphics data visualisation image processing

来源：评论

学校读者我要写书评

暂无评论

Layered Convolutional Neural Networks for Multi-Class image Classification

Layered Convolutional Neural Networks for Multi-Class Image ...

引用

Conference on real-time image processing and deep learning

作者： Kasinets, Dzmitry Saeed, Amir K. Johnson, Benjamin A. Rodriguez, Benjamin M. Johns Hopkins Univ Whiting Sch Engn 3400 N Charles St Baltimore MD 21218 USA

ISBN: (纸本)9781510673878;9781510673861

In the context of the advancing digital landscape, there is a discernible demand for robust and defensible methodologies in addressing the challenges in multi-class image classification. The evolution of intelligent systems mandates swift evaluations of environmental variables to facilitate decision-making within an authorized workflow. Recognizing the imperative role of ensemble models, this paper undertakes an exploration into the efficacy of layered Convolutional Neural Network (CNN) architectures for the nuanced task of multi-class image classification, specifically applied to traffic signage recognition in the dynamic context of a moving vehicle. The research methodology employs a YOLO (You Only Look Once) model to establish a comprehensive training and testing dataset. Subsequently, a stratified approach is adopted, leveraging layered CNN architectures to categorize clusters of objects and, ultimately, extrapolate the pertinent speed limit values. Our endeavor aims to elucidate the procedural framework for integrating CNN models, providing insights into their accuracy within the application domain.

关键词： convolutional neural networks transforms architectures modeling classification

来源：评论

学校读者我要写书评

暂无评论

Affordable intraoral camera integrated with deep learning for at-home monitoring and detection of oral soft and hard tissue conditions 10

Affordable intraoral camera integrated with deep learning fo...

引用

Conference on Optics and Biophotonics in Low-Resource Settings X

作者： Jain, Vrinda Jana, Ananya Oliveira, Abmael H. Livecchi, Thomas T. Jacques, Steven L. Pierce, Mark C. Subhash, Hrebesh M. Rutgers State Univ Dept Biomed Engn 599 Taylor Rd Piscataway NJ 08854 USA Univ Washington Dept Bioengn 5720 15th Ave NE Seattle WA 98195 USA Colgate Palmol Co Global Technol & Design Ctr 909 River Rd Piscataway NJ 08854 USA

ISBN: (纸本)9781510669246;9781510669239

To address an increasing demand for accessible and affordable tools for at-home oral health assessment, this paper presents the development of a low-cost intraoral camera integrated with a deep learning approach for image analysis. The camera captures and analyzes images of soft and hard oral tissues, enabling real-time feedback on potential tooth staining and empowering users to proactively manage their oral health. The system utilizes an Azdent intraoral USB camera with the Raspberry Pi 400 computer and Intel (R) Neural Computing Stick for real-time image acquisition and processing. A neural network was trained on a dataset comprising 102,062 CIELAB and RGB values from the VITA classical shade guide. Ground truth annotations were generated through manual labeling, encompassing tooth number and stain levels. The deep learning approach demonstrated high accuracy in tooth stain identification with a testing accuracy exceeding 0.6. This study demonstrates the capacity of low-cost camera hardware and deep learning algorithms to effectively categorize tooth stain levels with high accuracy. By bridging the gap between professional care and homebased oral health monitoring, the development of this low-cost platform holds promise in facilitating early detection and monitoring of oral health issues.

关键词： Oral care machine learning convolutional neural network image processing bioimaging camera artificial intelligence intraoral diagnostics

来源：评论

学校读者我要写书评

暂无评论

Research on Multimodal Biomedical Signal Recognition 7

Research on Multimodal Biomedical Signal Recognition

引用

7th International Conference on Automation Electronics and Electrical Engineering

作者： Liu, Zhaoyu South China Univ Technol Dept Elect Business Guangzhou 510006 Peoples R China

ISBN: (纸本)9798350377040;9798350377033

This study proposes a multimodal biomedical signal recognition algorithm that aims to fuse image data and biosignal data to improve the accuracy and real-time performance of medical data analysis. The algorithm employs a deep learning model to independently recognize the two data types and introduces a cross-attention mechanism to assess the correlation between image and biosignal features. The mechanism dynamically adjusts the attention weights so as to effectively suppress irrelevant features and promote the fusion of image and signal features. Specifically, the biosignal features are extracted by the temporal Kolmogorov-Arnold network (TKAN), while the image data are processed by the YOLOv11 network. These two feature vectors are aligned and fused through the cross-attention mechanism, and finally the fused feature vectors are generated and classified through the fully connected layer to obtain the final diagnosis results. This paper also explores pre-processing techniques for image and signal data, including methods for denoising, signal enhancement, data normalization and image alignment. These preprocessing steps effectively improve the quality of the raw data and provide clearer and more accurate inputs for subsequent deep learning models. Through experimental verification, the proposed algorithm outperforms traditional methods in a simulated environment, especially in real-time data analysis and multimodal fusion accuracy.

关键词： multimodal medical biosignal cross-attention feature fusion deep learning

来源：评论

学校读者我要写书评

暂无评论

A High-Performance learning-Based Framework for Monocular 3-D Point Cloud Reconstruction

IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION

引用

IEEE JOURNAL OF RADIO FREQUENCY IDENTIFICATION 2024年 8卷 695-712页

作者： Zamani, AmirHossein Ghaffari, Kamran Aghdam, Amir G. Concordia Univ Elect & Comp Engn Montreal PQ H3G1M8 Canada Traxara Robot Inc Res & Dev Montreal PQ H3J 1M6 Canada

An essential yet challenging step in the 3D reconstruction problem is to train a machine or a robot to model 3D objects. Many 3D reconstruction applications depend on real-time data processing, so computational efficiency is a fundamental requirement in such systems. Despite considerable progress in 3D reconstruction techniques in recent years, developing efficient algorithms for real-time implementation remains an open problem. The present study addresses current issues in the high-precision reconstruction of objects displayed in a single-view image with sufficiently high accuracy and computational efficiency. To this end, we propose two neural frameworks: a CNN-based autoencoder architecture called Fast-image2Point (FI2P) and a transformer-based network called TransCNN3D. These frameworks consist of two stages: perception and construction. The perception stage addresses the understanding and extraction process of the underlying contexts and features of the image. The construction stage, on the other hand, is responsible for recovering the 3D geometry of an object by using the knowledge and contexts extracted in the perception stage. The FI2P is a simple yet powerful architecture to reconstruct 3D objects from images faster (in real-time) without losing accuracy. Then, the TransCNN3D framework provides a more accurate 3D reconstruction without losing computational efficiency. The output of the reconstruction framework is represented in the point cloud format. The ShapeNet dataset is utilized to compare the proposed method with the existing ones in terms of computation time and accuracy. Simulations demonstrate the superior performance of the proposed strategy. Our dataset and code are available on IEEE DataPort website and first author's GitHub repository respectively.

关键词： Three-dimensional displays Transformers Feature extraction image reconstruction Point cloud compression Accuracy Solid modeling Monocular 3D reconstruction transformers image representation learning supervised learning deep neural network

来源：评论

学校读者我要写书评

暂无评论

Unified and real-time image Geo-Localization via Fine-Grained Overlap Estimation

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 5060-5072页

作者： Song, Ze Kang, Xudong Wei, Xiaohui Li, Shutao Liu, Haibo Hunan Univ Coll Elect & Informat Engn Key Lab Visual Percept & Artificial Intelligence Changsha 410082 Peoples R China Hunan Univ Key Lab Visual Percept & Artificial Intelligence H Changsha 410082 Peoples R China Hunan Univ Sch Robot Changsha 410082 Peoples R China Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China

image geo-localization aims to locate a query image from source platform (e.g., drones, street vehicle) by matching it with Geo-tagged reference images from the target platforms (e.g., different satellites). Achieving cross-modal or cross-view real-time (>30fps) image localization with the guaranteed accuracy in a unified framework remains a challenge due to the huge differences in modalities and views between the two platforms. In order to solve this problem, a novel fine-grained overlap estimation based image geo-localization method is proposed in this paper, the core of which is to estimate the salient and subtle overlapping regions in image pairs to ensure correct matching. Specifically, the high-level semantic features of input images are extracted by a deep convolutional neural network. Then, a novel overlap scanning module (OSM) is presented to mine the long-range spatial and channel dependencies of semantic features in various subspaces, thereby identifying fine-grained overlapping regions. Finally, we adopt the triplet ranking loss to guide the proposed network optimization so that the matching regions are as close as possible and the most mismatched regions are as far away as possible. To demonstrate the effectiveness of our FOENet, comprehensive experiments are conducted on three cross-view benchmarks and one cross-modal benchmark. Our FOENet yields better performance in various metrics and the recall accuracy at top 1 (R@1) is significantly improved, with a maximum improvement of 70.6%. In addition, the proposed model runs fast on a single RTX 6000, reaching real-time inference speed on all datasets, with the fastest being 82.3 FPS.

关键词： real-time systems Feature extraction Semantics Accuracy Satellites Location awareness Estimation image geo-localization cross-modal image retrieval cross-view image retrieval real-time

来源：评论

学校读者我要写书评

暂无评论

Mish-CNN: An Enhanced deep learning Model with Mish Activation Function for Potato Leaf Disease Detection

引用

POTATO RESEARCH 2025年 1-10页

作者： Chaibi, Nesrine Nhidi, Wiem Zaied, Mourad Natl Engn Sch Gabes Gabes Tunisia Res Team Intelligent Machines RTIM Gabes Tunisia

Potatoes are among the most widely cultivated crops globally but are highly vulnerable to bacterial and fungal diseases, particularly early and late blight, which can severely impact yield. Early detection during the budding stage is essential for mitigating losses and improving productivity. To address this challenge, computer vision and machine learning techniques have been extensively explored for automated disease detection. This paper presents a deep learning model that integrates image processing and convolutional neural networks (CNN) to classify potato leaves into three categories: early blight, late blight, and healthy. To enhance feature extraction and model performance, we incorporate the Mish activation function, which improves the learning capacity of the network. Our experiments utilize a dataset of over 1500 labeled images of healthy and diseased potato leaves from the publicly available Plant Village database. The results demonstrate that our CNN model, enhanced with Mish activation, achieves a classification accuracy of 98%, outperforming conventional models. These findings highlight the effectiveness and reliability of our approach, contributing to the development of an automated system for real-time potato leaf disease detection.

关键词： Convolutional neural networks Early blight Late blight Mish activation function Plant Village dataset Potato leaf

来源：评论

学校读者我要写书评

暂无评论

HybNet: A hybrid deep models for medicinal plant species identification

引用

METHODSX 2025年 14卷 103126页

作者： Pushpa, B. R. Jyothsna, S. Lasya, S. Amrita Vishwa Vidyapeetham Sch Comp Dept Comp Sci Mysuru India

real-time plant species detection plays an important role in fields ranging from medicine to biodiversity conservation. images captured under unconstrained environments, scale variations, different lighting conditions, leaf orientation, complicated backdrops, and leaflet structure make plant species recognition rigorous and time-consuming. Our study addresses this challenge by introducing three pioneering hybrid models, seamlessly integrating the strengths of convolution neural networks. In the first model, two deep learning models such as VGG16 and MobileNet are fused to extract features. Then, the extracted features are subjected to KNN classifier achieving an impressive 85.85 % accuracy, while the second model adopts MobileNet in conjunction with ResNet50 for feature extraction which is further classified using a deep learning classifier to achieve 88 % accuracy. The third model incorporates MobileNetV2 with the Squeeze and Excitation (SE) layers for the classification tasks. Our research highlights the immense potential of modern image processing techniques and deep learning models in comprehending and safeguarding the earth's diverse plant species. The experiments are carried out on self-created medicinal plant datasets captured in real-time conditions. From the experimentations, it is observed that hybrid model 3 reflects an improved performance of 94.24 % by utilizing recalibration efforts compared with the other two hybrid models.

关键词： Medicinal Plant species Convolutional neural network Hybrid deep architectures Recalibration Classification Transfer learning Squeeze and excitation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hierarchical Similarity Metric learning With Noisy Labels

引用

IEEE TRANSACTIONS ON image processing 2023年 32卷 1245-1256页

作者： Yan, Jiexi Luo, Lei Deng, Cheng Huang, Heng Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China JD Finance Amer Corp Mountain View CA 94043 USA Xidian Univ Sch Elect Engn Xian 710071 Peoples R China Univ Pittsburgh Dept Elect & Comp Engn Pittsburgh PA 15261 USA

deep Metric learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since these noisy labels often cause a severe performance degradation, it is crucial to enhance the robustness and generalization ability of DML. In this paper, we propose an Adaptive Hierarchical Similarity Metric learning method. It considers two noise-insensitive information, i.e., class-wise divergence and sample-wise consistency. Specifically, class-wise divergence can effectively excavate richer similarity information beyond binary in modeling by taking advantage of Hyperbolic metric learning, while sample-wise consistency can further improve the generalization ability of the model using contrastive augmentation. More importantly, we design an adaptive strategy to integrate this information in a unified view. It is noteworthy that the new method can be extended to any pair-based metric loss. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current deep metric learning approaches.

关键词： deep metric learning deep metric learning noisy labels noisy labels hierarchical similarity hierarchical similarity hyperbolic geometry hyperbolic geometry contrastive augmentation contrastive augmentation

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient LC-SCS deep learning model for breast cancer classification using thermal imaging

引用

Neural Computing and Applications 2024年第26期36卷 16233-16250页

作者： Nissar, Iqra Alam, Shahzad Masood, Sarfaraz Department of Computer Engineering Jamia Millia Islamia New Delhi110025 India

deep learning applications have witnessed significant advancements across diverse domains, revolutionizing tasks such as image recognition, disease classification, cancer detection, natural language processing, and autonomous decision-making. However, striking a balance between performance and cost remains a fundamental challenge. Performance, which encompasses accuracy, efficiency, and effectiveness, is crucial for the real-world applicability of deep learning models. Attaining high performance often involves using resource-intensive models with intricate architectures, extensive datasets, and hyperparameter tuning. While these factors lead to improved performance, they also result in increased costs, including computational resources, time, and energy consumption. This research addresses this challenge by proposing a novel low-cost deep learning model based on Sharpened Cosine Similarity (LC-SCS) for breast cancer classification using thermal images. In our study on a DMR-IR dataset, we also utilized pre-trained models: ResNet-101, VGG-16, Inception-V3, ResNet-50, VGG-19, and Xception. The proposed LC-SCS model achieved an impressive accuracy of 94%, trailing just 4% behind the leading VGG-19 model, while maintaining a low computational cost. It achieved recall and precision scores of 0.95 each, with an F1-score of 0.94. The LC-SCS model excels in computational efficiency, demanding only 1.85 GFLOPs and 1.2 million parameters. The memory requirement is minimal at 865.35 MB, and it exhibits a latency of just 0.003 s. Additionally, the CPU execution time for prediction is 3.59 s. Comparatively, the best-performing pre-trained VGG-19 model achieved 98% accuracy but incurred significantly higher costs. The proposed LC-SCS model showcases a remarkable 298.63 times reduction in GFLOPs, a 116.31 times reduction in total parameters, a 4.57 times reduction in memory requirements for model weights, a 5 times reduction in latency, and a 3.33 times reduction in CPU execution

关键词： image recognition

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：