检索结果-内蒙古大学图书馆

2024 International Conference on image processing

作者： Longobardi, Francesco Riccio, Daniel Univ Naples Federico II Via Claudio 21 I-80125 Naples Italy

ISBN: (纸本)9798350349405;9798350349399

The need for automated systems to aid law enforcement during densely packed events arises from the inherent danger of large crowds, evidenced by historical instances of stampedes and crushes. Existing methods vary from basic crowd statistics extraction to detailed anomaly detection in behavior classification, but often focus on single, pre-segmented scenes. Our work addresses classifying crowd behaviors in environments where multiple behaviors coexist within a single scene, defined as a multi-class crowd motion characterization challenge. We use a microscopic approach for scenes captured by drones at varying altitudes, without prior manipulation. This approach combines graph-based representations of individuals and flow images, facilitating classification of diverse crowd behaviors in unsegmented scenes. Tested on a public dataset, our method shows promising results in analyzing complex crowd dynamics.

关键词： Crowd behaviour classification Graph neural networks Drone video analysis

来源：评论

学校读者我要写书评

暂无评论

Color image encryption based on lite dense-ResNet and bit-XOR diffusion

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第5期83卷 12819-12848页

作者： Bao, Zhenjie Xue, Ru Hu, Jingyun Liu, Yue Xizang Minzu Univ Sch Informat Engn Xianyang Shaanxi Peoples R China

images contain a wealth of information and are frequently targeted by malicious attackers when transmitted over public networks. Fortunately, image encryption prevents confidential information from being acquired by illegal attackers. Deep learning-based image encryption is a relatively new research area, but recently proposed methods have not achieved satisfactory levels of generalization, security, and efficiency. To address these limitations, we employ a lite dense residual network (Dense-ResNet) to rearrange image pixels, thereby reducing the computation amounts. In addition, we design a weight-adjustable loss function model, which combines the encryption loss function, decryption loss function, and total variational loss function. And then we adopt bit-XOR diffusion to further encrypt the intermedia ciphertext image obtained by the encryption network. We trained and tested encryption and decryption neural networks in a dataset of no fixed category images. Experiments declare our method can complete the image encryption/ decryption tasks in various scenarios. Additionally, the proposed approach exhibits broad generalization abilities with high encryption and decryption quality aided by the decryption total variation loss function. Compared to recently proposed deep learning-based image encryption approaches, our method demonstrates faster processing times for both image encryption and decryption, with at least a 2.7% and 7.5% increase in efficiency, respectively. Furthermore, our method improves decryption performance by at least 1.0% and 0.5% in Peak signal-to-ratio (PSNR) as well as structural similarity (SSIM) indicators while maintaining a high level of security. What is more, our method enhances traceability of data loss or noise attacks since such attacks leave a noticeable trail on decrypted images produced by our method.

关键词： Color image encryption Lite dense-ResNet Bit-XOR diffusion Deep learning

来源：评论

学校读者我要写书评

暂无评论

Model-informed deep learning-based compressive sensing for resampling and recovering 2D SHM vision data

引用

AUTOMATION IN CONSTRUCTION 2024年 160卷

作者： Cai, Enjian Zhang, Yi Lu, Xinzheng Guo, Wei Natl Engn Res Ctr High Speed Railway Construct Tec Changsha 410075 Peoples R China Tsinghua Univ Dept Civil Engn Beijing 100084 Peoples R China

Long-term structural health monitoring (SHM) using vision -based methods may encounter challenges of data storage, low -sampling resolution, and data loss. Compressive sensing (CS) offers the possibility for alleviating these problems, by using less than half of the complete signal to recover the signal based on the sparsity. This paper proposed a model -informed deep learning -based CS method, named variable splitting scalable convolutional neural network (VSSNet). VSSNet includes a single block sampling convolution network, plus a hierarchical recovery network that contains one base layer (BL) and multiple enhancement layers (ELs). In each BL and EL, different data loss problems are solved using the variable splitting recovery network, by integrating optimization theories with deep learning -based CS methods. Then recoveries are refined by initial and deep recovery networks. Additionally, the greedy technique is used to select important sample bases, enabling resampling and recovery at different sampling rates using one model. The superiority of VSSNet was demonstrated through static and dynamic examples, showcasing its high accuracy and robustness in image recovery, structural motion estimation, and structural modal identification.

关键词： Structural health monitoring Video processing Compressive sensing Model-informed deep learning

来源：评论

学校读者我要写书评

暂无评论

FREQUENCY-AWARE RE-PARAMETERIZATION FOR OVER-FITTING BASED image COMPRESSION 30

FREQUENCY-AWARE RE-PARAMETERIZATION FOR OVER-FITTING BASED I...

引用

30th IEEE International Conference on image processing (ICIP)

作者： Ye, Yun Pan, Yanjie Jiang, Qually Lu, Ming Fang, Xiaoran Xu, Beryl Intel Corp Shanghai Peoples R China

ISBN: (纸本)9781728198354

Over-fitting-based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural networks (CNNs) based methods. This paper presents a simple re-parameterization method to train CNNs with reduced weights storage and accelerated convergence. The convolution kernels are re-parameterized as a weighted sum of discrete cosine transform (DCT) kernels enabling direct optimization in the frequency domain. Combined with L1 regularization, the proposed method surpasses vanilla convolutions by achieving a significantly improved rate-distortion with low computational cost. The proposed method is verified with extensive experiments of over-fitting-based image restoration on various datasets, achieving up to -46.12% BD-rate on top of HEIF with only 200 iterations.

关键词： image Compression Over-fitting based Compression Convolutional neural Networks Rate-Distortion

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-Tree Based Model for Enhanced image Classification Performance 32

A Hybrid CNN-Tree Based Model for Enhanced Image Classificat...

引用

32nd IEEE signal processing and Communications Applications Conference (SIU)

作者： Aydin, Musa Kus, Zeki Akcelik, Zeliha Kaya Fatih Sultan Mehmet Vakif Univ Bilgisayar Muhendisligi Istanbul Turkiye

ISBN: (纸本)9798350388978;9798350388961

Blood cells play an essential role in various bodily functions, such as protection against infections and the body's defense. The accurate classification of blood cells, generally grouped as red, white, and platelets is important for clinical diagnosis and hematological analysis. However, identifying these cells is a specialized and time-consuming process. Therefore, there is a hot-topic for high-precision automatic blood cell classification methods. Convolutional neural networks (CNNs) are a deep learning model used for visual data analysis and are very powerful in extracting features from data. In this study, we propose a hybrid classification model that combines the feature extraction power of CNNs with the ensemble-based prediction capabilities of Random Forest and XGBoost algorithms. The proposed hybrid model is compared with different methods on the BloodMNIST dataset in terms of classification performance and inference time. The results show that the tree-based methods outperform CNN by up to 8.49 and 11.62 points and achieve up to 82.9 times better inference times than other methods.

关键词： CNN feature extraction Random forest XGBoost Blood cell classification

来源：评论

学校读者我要写书评

暂无评论

stochasticWindow Transformer for image Restoration 36

StochasticWindow Transformer for Image Restoration

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Xiao, Jie Fu, Xueyang Wu, Feng Zha, Zheng-Jun Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781713871088

Thanks to the powerful representation capabilities, transformers have made impressive progress in image restoration. However, existing transformers-based methods do not carefully consider the particularities of image restoration. In general, image restoration requires that an ideal approach should be translation-invariant to the degradation, i.e., the undesirable degradation should be removed irrespective of its position within the image. Furthermore, the local relationships also play a vital role, which should be faithfully exploited for recovering clean images. Nevertheless, most transformers either adopt local attention with the fixed local window strategy or global attention, which unfortunately breaks the translation invariance and causes huge loss of local relationships. To address these issues, we propose an elegant stochastic window strategy for transformers. Specifically, we first introduce the window partition with stochastic shift to replace the original fixed window partition for training. Then, we design a new layer expectation propagation algorithm to efficiently approximate the expectation of the induced stochastic transformer for testing. Our stochastic window transformer not only enjoys powerful representation but also maintains the desired property of translation invariance and locality. Experiments validate the stochastic window strategy consistently improves performance on various image restoration tasks (deraining, denoising and deblurring) by significant margins. The code is available at https://***/jiexiaou/Stoformer.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian deep neural network fostered sentiment analysis approach on product reviews

引用

signal image AND VIDEO processing 2024年第4期18卷 3483-3494页

作者： Ajmeera, Narahari Kamakshi, P. JNTUH Univ Coll Engn Dept Comp Sci & Engn Manthani Telangana India Kakatiya Inst Technol & Sci Dept Informat Technol Warangal Telangana India

In recent times, online shopping has become commonly used method for consumers to make purchases and engage in consumption with the rapid advancement of Internet technology. Enhancing user satisfaction is achievable through sentiment analysis (SA) of the enormous user evaluations found on e-commerce platforms. However, accurately predicting the sentiment orientations of these user reviews remains a challenge due to varying sequence lengths, text arrangements, and intricate logic. Nowadays, sentiment analysis is widely employed to assess customer feedback, which holds great significance in determining a product's success. In the past, people relied on word-of-mouth reviews to judge a product's quality. This practice of sentiment analysis is extensively applied in social media. Natural language processing (NLP) plays a crucial role in deciphering sentiment, also referred to as opinion mining or emotion AI, as it encompasses the collective perception of customers. In this manuscript, a Hamiltonian Deep neural Networks-based Sentiment Analysis on Product Recommendation System (HDNN-SCOA-SA-PR) is proposed. First, the data are gathered from Amazon Product Reviews dataset. Then the data are pre-processed utilizing adaptive self-guided filtering for space tokenization, Gensim lemmatization, and Snowball stemming. By using Structured Optimal Graph-Based Sparse Feature Extraction, the features are extracted. Extracted features are selected using Single Candidate Optimization Algorithm. Finally, the classification process is done using Hamiltonian deep neural network and classified sentiment analysis as positive, negative, neutral. The proposed HDNN-SCOA-SA-PR method is activated in Python, and the efficiency of the proposed method is analyzed with different metrics, such as accuracy, sensitivity, RoC, precision, error rate, F1-score,computation time. ROC is evaluated and compared to the existing methods, such as sentiment analysis based upon machine learning of online produc

关键词： Hamiltonian deep neural network Adaptive self-guided filtering Structured Optimal Graph-Based Sparse Feature Extraction Sentiment analysis Product reviews Single Candidate Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic analysis of three-dimensional cardiac tagged magnetic resonance images using neural networks trained on synthetic data

引用

JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE 2025年第1期27卷 101869-101869页

作者： Buoso, Stefano Stoeck, Christian T. Kozerke, Sebastian Swiss Fed Inst Technol Inst Biomed Engn Zurich Switzerland Univ Zurich Zurich Switzerland Univ Hosp Zurich Ctr Preclin Dev Zurich Switzerland

Background: Three-dimensional (3D) tagged magnetic resonance (MR) imaging enables in-vivo quantification of cardiac motion. While deep learning methods have been developed to analyze these images, they have been restricted to two-dimensional datasets. We present a deep learning approach specifically designed for displacement analysis of 3D cardiac tagged MR images. methods: We developed two neural networks to predict left-ventricular motion throughout the cardiac cycle. Networks were trained using synthetic 3D tagged MR images, generated by combining a biophysical left-ventricular model with an analytical MR signal model. Network performance was initially validated on synthetic data, including assessment of signal-to-noise ratio sensitivity. The networks were then retrospectively evaluated on an in-vivo external validation human dataset and an in-vivo porcine study. Results: For the external validation dataset, predicted displacements deviated from manual tracking by median (interquartile range) values of 0.72 (1.17), 0.81 (1.64), and 1.12 (4.17) mm in x, y, and z directions, respectively. In the porcine dataset, strain measurements showed median (interquartile range) differences from manual annotations of 0.01 (0.04), 0.01 (0.06), and -0.01 (0.18) for circumferential, longitudinal, and radial components, respectively. These strain values are within physiological ranges and demonstrate superior performance of the network approach compared to existing 3D tagged image analysis methods. Conclusion: The method enables rapid analysis times of approximately 10 s per cardiac phase, making it suitable for large cohort investigations.

关键词： Cardiac magnetic resonance 3D tagged MRI neural networks Cardiac motion Strains image processing

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Parkinson's Disease Based on Hybrid Fusion Approach of Offline Handwriting images

引用

IEEE signal processing LETTERS 2024年 31卷 3179-3183页

作者： Dong, Shanyu Liu, Jin Wang, Jianxin Cent South Univ Sch Comp Sci & Engn Hunan Prov Key Lab Bioinformat Changsha 410083 Peoples R China

Handwriting images are commonly used to diagnose Parkinson's disease due to their intuitive nature and easy accessibility. However, existing methods have not explored the potential of the fusion of different handwriting image sources for diagnosis. To address this issue, this study proposes a hybrid fusion approach that makes use of the visual information derived from different handwriting images and handwriting templates, significantly enhancing the performance in diagnosing Parkinson's disease. The proposed method involves several key steps. Initially, different preprocessed handwriting images undergo pixel-level fusion using Laplacian transformation. Subsequently, the fused and original images are fed into a pre-trained CNN separately to extract visual features. Finally, feature-level fusion is performed by concatenating the feature vectors extracted from the flatten layer, and the fused feature vectors are input into SVM to obtain classification results. Our experimental results validate that the proposed method achieves excellent performance by only utilizing visual features from images, with 95.45% accuracy on the NewHandPD. Furthermore, the results obtained on our dataset verify the strong generalizability of the proposed approach.

关键词： Feature extraction Diseases Visualization Vectors image color analysis Convolutional neural networks Accuracy image edge detection Writing Transforms Handwriting images hybrid fusion approach Laplacian transformation Parkinson's disease pre-trained CNN

来源：评论

学校读者我要写书评

暂无评论

HorSR: High-order spatial interactions and residual global filter for efficient image super-resolution

引用

signal processing-image COMMUNICATION 2024年 127卷

作者： Wang, Fengsui Chu, Xi Anhui Polytech Univ Sch Elect Engn Wuhu 241000 Peoples R China Anhui Key Lab Detect Technol & Energy Saving Devic Wuhu 241000 Peoples R China Minist Educ Key Lab Adv Percept & Intelligent Controlof High e Wuhu 241000 Peoples R China

Recent advances in efficient image super-resolution (EISR) include convolutional neural networks, which exploit distillation and aggregation strategies with copious channel split and concatenation operations to fully exploit limited hierarchical features. In contrast, the Transformer network presents a challenge for EISR because multiheaded self-attention is a computationally demanding process. To respond to this challenge, this paper proposes replacing multiheaded self-attention in the Transformer network with global filtering and recursive gated convolution. This strategy allows us to design a high-order spatial interaction and residual global filter network for efficient image super-resolution (HorSR), which comprises three components: a shallow feature extraction module, a deep feature extraction module, and a high-quality image-reconstruction module. In particular, the deep feature extraction module comprises residual global filtering and recursive gated convolution blocks. The experimental results show that the HorSR network provides state-of-the-art performance with the lowest FLOPs of existing EISR methods.

关键词： Super-resolution Lightweight Recursive gated convolution Residual global filtering

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：