检索结果-内蒙古大学图书馆

deep learning for real-time image steganalysis: a survey

JOURNAL OF real-time image processing 2020年第1期17卷 149-160页

作者： Ruan, Feng Zhang, Xing Zhu, Dawei Xu, Zhanyang Wan, Shaohua Qi, Lianyong Nanjing Univ Informat Sci & Technol Sch Automat Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Jiangsu Peoples R China Zhongnan Univ Econ & Law Sch Informat & Safety Engn Wuhan Hubei Peoples R China Qufu Normal Univ Sch Informat Sci & Engn Shandong Peoples R China

Steganography is a technique that transmits secret data or message in an appropriate multimedia carrier, e.g., image, audio, and video files. It comes under the assumption that if the feature is visible, the point of attack is evident. However, such technology is always used by criminals who do not want to be easily discovered to hide harmful information in various media, especially in images. Massive spreading of those harmful information will increase the difficulty of social security management. In this case, excellent image steganalysis should be developed and applied. Specially, real-time image steganalysis is necessary when information timelines need to be protected. If detection scene has large amounts of users, deep learning can be applied to improve performance of image steganalysis benefiting from its powerful processing capability. Using deep learning, real-time image steganalysis system gets higher accuracy and efficiency. In this paper, we give an account of preliminary knowledge first. A brief overview of the deep neural networks (DNN) is also presented. The combination of DNN and real-time image steganalysis is introduced. Then, we import the concept of CNN in DNN, and expound theory as well as advantages of combining CNN and image steganalysis. For multi-user scenarios, we analyze a practical real-time image steganalysis application based on outlier detection methods. At last, we prospect the future issues of real-time image steganalysis.

关键词： deep learning Steganography image steganalysis CNN DNN

来源：评论

学校读者我要写书评

暂无评论

An Ensemble deep learning Approach Combining Phenotypic Data and fMRI for ADHD Diagnosis

引用

JOURNAL OF SIGNAL processing SYSTEMS FOR SIGNAL image AND VIDEO TECHNOLOGY 2022年第11期94卷 1269-1281页

作者： Qin, Yuanze Lou, Yiwei Huang, Yu Chen, Rigao Yue, Weihua Peking Univ Natl Engn Res Ctr Software Engn Beijing 100871 Peoples R China Peking Univ Sch Software & Microelect Beijing 100871 Peoples R China Peking Univ Sch Comp Sci Key Lab High Confidence Software Technol Beijing 100871 Peoples R China Hosp Chengdu Univ Tradit Chinese Med Dept Spine Surg Chengdu 610041 Peoples R China Peking Univ Hosp 6 Inst Mental Hlth Beijing 100191 Peoples R China Peking Univ Minist Hlth Key Lab Mental Hlth Beijing 100191 Peoples R China Peking Univ Natl Clin Res Ctr Mental Disorders Beijing 100191 Peoples R China

As a common neurological disorder in early childhood and adolescence, an efficient and accurate diagnosis of Attention-Defect/Hyperactivity Disorder (ADHD) has always been one of the important goals in the field of psychiatry. However, most of the current diagnostic methods are based on a single table or fMRI images, which may result in the loss of much complementary information useful for diagnosis. Therefore, this paper presents a strategy for multimodal data fusion and an ensemble learning model (Trans3D-ensemble) to classify the ADHDs and typicals. The base classifiers of Trans3D-ensemble include two parts, Trans3D (Transformer for 3D images) to extract spatio-temporal features from fMRI images and random forest to extract clinical features from phenotypic data. Specifically, Trans3D utilizes 3D-CNN to capture volumetric spatial information and convert the 3D images into patch embeddings. Meanwhile, temporal pooling operation fuses the images tokens output by Transformer encoders across time and obtains the representative features of fMRI samples. Existing methods basically only build the above independent models, and few consider the effective combination of the those for diagnosis and treatment. Looking into this issue, we use stacking, one of ensemble learning methods, on multimodal data by merging the outputs from the two base classifiers. The proposed method reaches excellent results compared to most methods based on single modality and gets the accuracy of 74.5% on ADHD-200 data set, demonstrating the potential of the combination of phenotypic data and fMRI for ADHD diagnosis. Our strategy of multimodal data fusion provides a novel comprehensive diagnosis mode and the above results show that the proposed Trans3D-ensemble can effectively improve the auxiliary diagnosis of ADHD.

关键词： Ensemble approach Transformer fMRI Phenotypic data

来源：评论

学校读者我要写书评

暂无评论

TransCGAN-based Parameter Extraction Framework for SAR image Simulation

TransCGAN-based Parameter Extraction Framework for SAR Image...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Sidan Deng Jingfei He Yongfei Mao Liangbo Zhao Liang Chen Hao Shi National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing & Chongqing Innovation Center Beijing Institute of Technology Chongqing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing & Chongqing Innovation Center Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Synthetic Aperture Radar (SAR) images have a wide range of applications due to their all-weather and all-day working conditions. However, SAR images with different scenarios and imaging conditions are insufficient or even rare, which is required in specific SAR image tasks. Fortunately, SAR image simulation technology can provide ample simulated images under these conditions at a low cost, addressing the scarcity of specific real SAR data. Accurate parameters are crucial for obtaining high-quality simulated images. However, it is time-consuming and labour-intensive to adjust parameters manually, and it often fails to achieve accurate simulation parameters. To tackle this problem, this paper proposes a TransCGAN-based SAR image simulation method that combines deep learning with traditional methods. By training TransCGAN, a conditional generative adversarial network (CGAN) integrated with Transformer architecture, a mapping between SAR images and simulation parameters is established. This enables the extraction of simulation parameters directly from the real SAR image, guided by the corresponding real SAR image. Ultimately, the parameters are subsequently converted into simulated SAR images via simulation software. Experimental results demonstrate that our TransCGAN-based method can effectively extract accurate simulation parameters from real SAR images, resulting in simulated images holding high similarity to real images.

关键词： Training Accuracy Imaging Radar imaging Transformers Generative adversarial networks Radar polarimetry Software Synthetic aperture radar Parameter extraction

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in 3D Human Pose Estimation: From Optimization to Implementation and Beyond

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2022年第2期36卷

作者： Yan, Jielu Zhou, Mingliang Pan, Jinli Yin, Meng Fang, Bin Univ Macau State Key Lab Internet Things Smart City Taipa 999078 Macao Peoples R China Chongqing Univ Sch Comp Sci Chongqing 400044 Peoples R China TMS Measurement & Control Technol Co Ltd Wuhan Peoples R China Chongqing Pharmaceut Data Informat Technol Co Ltd Adm Ctr Bldg 3Block B Chongqing Peoples R China

3D human pose estimation describes estimating 3D articulation structure of a person from an image or a video. The technology has massive potential because it can enable tracking people and analyzing motion in real time. Recently, much research has been conducted to optimize human pose estimation, but few works have focused on reviewing 3D human pose estimation. In this paper, we offer a comprehensive survey of the state-of-the-art methods for 3D human pose estimation, referred to as pose estimation solutions, implementations on images or videos that contain different numbers of people and advanced 3D human pose estimation techniques. Furthermore, different kinds of algorithms are further subdivided into sub-categories and compared in light of different methodologies. To the best of our knowledge, this is the first such comprehensive survey of the recent progress of 3D human pose estimation and will hopefully facilitate the completion, refinement and applications of 3D human pose estimation.

关键词： 3D human pose estimation deep learning multi-person pictorial structure unsupervised

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Healthcare Intelligence Multisensory Data Fusion with Cutting-Edge Machine learning and deep learning for Patients’ Cognitive Knowledge

Revolutionizing Healthcare Intelligence Multisensory Data Fu...

引用

Knowledge Engineering and Communication Systems (ICKECS), International Conference on

作者： Samatha R Swamy K S Nandini Prasad Dept. of ISE RV Institute of Technology & Management(RVITM) Bengaluru India Dept. of ISE Dayananda Sagar Academy of Technology & Management(DSATM) Bengaluru India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

The study explores the recent advancements in healthcare that have witnessed an unprecedented integration of multisensory data, ranging from wearable devices to medical imaging and electronic health records. This paper explores the transformative impact of cutting-edge machine learning algorithms and deep learning algorithms in processing and interpreting this multisensory data, offering unparalleled insights into patients’ cognitive well-being. The review delves into the types and challenges of multisensory data, evaluating performance of supervised and supervised machine learning models for disease detection and pattern recognition respectively. Additionally, it scrutinizes the importance of deep learning applications that are based on convolutional neural networks as well as recurrent neural networks for medical image classification. The paper also mentions the importance of the integration of multisensor data fusion with these advanced algorithms, emphasizing real-time monitoring systems and ethical considerations. Summaries from research data shows effectiveness of remote patient care and predictive analysis and personalized treatment plans. The exploration of future directions and opportunities underscores the prime importance for further advancements in explainable AI, collaborative learning, and edge computing, consolidating the vision of a healthcare paradigm revolutionized by intelligent data fusion and cutting-edge technologies.

关键词： deep learning Knowledge engineering Ethics Machine learning algorithms Data integration Medical services Data models

来源：评论

学校读者我要写书评

暂无评论

Insulator Fault Detection in Aerial images based on the Mixed-grouped Fire Single-shot Multibox Detector

引用

JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY 2021年第3期65卷 1-10页

作者： Chen, Songbo Su, Chao Kuang, Zhenxing Ouyang, Ye Gong, Xiang Guangdong Power Grid Corp Qingyuan Guangdong Peoples R China Zhejiang Univ Hangzhou Peoples R China

In a complex background, insulator fault is the main factor behind transmission accidents. With the wide application of unmanned aerial vehicle (UAV) photography, digital image recognition technology has been further developed to detect the position and fault of insulators. There are two mainstream methods based on deep learning: the first is the "two-stage" example for a region convolutional neural network and the second is the "one-stage" example such as a single-shot multibox detector (SSD), both of which pose many difficulties and challenges. However, due to the complex background and various types of insulators, few researchers apply the "two-stage" method for the detection of insulator faults in aerial images. Moreover, the detection performance of "one-stage" methods is poor for small targets because of the smaller scope of vision and lower accuracy in target detection. In this article, the authors propose an accurate and real-time method for small object detection, an example for insulator location, and its fault inspection based on a mixed-grouped fire single-shot multibox detector (MGFSSD). Based on SSD and deconvolutional single-shot detector (DSSD) networks, the MGFSSD algorithm solves the problems of inaccurate recognition in small objects of the SSD and complex structure and long running time of the DSSD. To resolve the problems of some target repeated detection and small-target missing detection of the original SSD, the authors describe how to design an effective and lightweight feature fusion module to improve the performance of traditional SSDs so that the classifier network can take full advantage of the relationship between the pyramid layer features without changing the base network closest to the input data. The data processing results show that the method can effectively detect insulator faults. The average detection accuracy of insulator faults is 92.4% and the average recall rate is 91.2%. (C) 2021 Society for Imaging Science and Technology.

关键词： Fire detectors deep learning Electric fault location Detectors Problem solving image recognition (Computer vision) Convolutional neural networks Low vision

来源：评论

学校读者我要写书评

暂无评论

deep Residual Attention Network for Hyperspectral image Reconstruction 25

Deep Residual Attention Network for Hyperspectral Image Reco...

引用

25th International Conference on Pattern Recognition (ICPR)

作者： Kohei, Yorimoto Han, Xian-Hua Yamaguchi Univ Grad Sch Sci & Technol Innovat Yamaguchi Japan

ISBN: (纸本)9781728188089

Coded aperture snapshot spectral imaging (CASSI) captures a full frame spectral image as a single compressive image and is mandatory to reconstruct the underlying hyperspectral image (HSI) from the snapshot as the post-processing, which is a challenge inverse problem due to its ill-posed nature. Existing methods for HSI reconstruction from a snapshot usually employs optimization for solving the formulated i mage degradation model regularized with the empirically designed priors, and still cannot achieve enough reconstruction accuracy for real HS image analysis systems. Motivated by the recent advances of deep learning for different inverse problems, deep learning based HSI reconstruction method has attracted a lot of attention and can boost the reconstruction performance. This study proposes a novel deep convolutional neural network (DCNN) based framework for effectively learning the spatial structure and spectral attribute in the underlying HSI with the reciprocal spatial and spectral modules. Further, to adaptively leverage the useful learned feature for better HSI i mage reconstruction, we integrate residual attention modules into our DCNN via exploring both spatial and spectral attention maps. Experimental results on two benchmark HSI datasets show that our method outperforms state-of-the-art methods in both quantitative values and visual effects.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A novel locality-sensitive hashing relational graph matching network for semantic textual similarity measurement

引用

EXPERT SYSTEMS WITH APPLICATIONS 2022年 207卷

作者： Li, Haozhe Wang, Wenhai Liu, Zhaoran Niu, Yunlong Wang, Hao Zhao, Shunping Liao, Yilin Yang, Weigeng Liu, Xinggao Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou 310012 Peoples R China Minist Ecol & Environm Radiat Environm Monitoring Technol Ctr Hangzhou 310012 Peoples R China

Recent efforts adopt interaction-based models to construct the interaction of words between sentences, which aim to predict whether two sentences are semantically equivalent or not in semantic textual similarity (STS) task. However, these methods lack the global semantic awareness, which make it difficult to distinguish syntactic differences and also suffer from the inference time cost, primarily due to the calculation of the pair-interactions of words. A novel model called Locality-Sensitive Hashing Relational Graph Matching Network (LSHRGMN) is therefore proposed, which tackles these problems by syntactic dependency graph and locality-sensitive hashing (LSH). Specifically, syntactic dependency graph is aware of the global semantic information via rooting in each word to construct several trees and merging all the trees into one graph. LSH mechanism is introduced into pair -interactions of words for the inference efficiency problem. Extensive experiments are conducted on three real -world datasets, and the result shows that the proposed approach acquires higher accuracy and intriguing inference speed.

关键词： Semantic textual similarity Graph neural network Natural language processing deep learning

来源：评论

学校读者我要写书评

暂无评论

Swarm-Optimized deep Convolutional Networks for Precise Detection and Grading of Diabetic Retinopathy

Swarm-Optimized Deep Convolutional Networks for Precise Dete...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： U Sadhana Tripty Singh Beena. B. M Dept. of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364736

Diabetic Retinopathy (DR) is a very critical problem of diabetes that can lead to blindness if not detected and treated in the early stage. This research was conducted on this difficult disease based on image processing and Machine intelligence. In this research, our model detects and classifies the DR using the swarm-optimized deep convolutional networks. The proposed model integrated the convolutional neural networks (CNNs) along with Particle Swarm Optimization (PSO) to enrich the performance of the model execution and results with fine-tuned hyperparameters. This custom-optimized CNN model, designed for image classification, was evaluated on the Kaggle diabetic retinopathy dataset. The swarm-optimized deep CNN model presented balanced performance across all DR classes and achieved a precision of 0.93, recall of 0.97, and F1-score of 0.95 for all classes. The model's overall accuracy reached 0.84 on the selected dataset.

关键词： Diabetic retinopathy Accuracy Machine learning Retina Robustness real-time systems Convolutional neural networks Particle swarm optimization Machine intelligence image classification

来源：评论

学校读者我要写书评

暂无评论

real-time deep Recognition of Standardized Liver Ultrasound Scan Locations

引用

SENSORS 2023年第10期23卷 4850-4850页

作者： Shin, Jonghwan Lee, Sukhan Yi, Juneho Sungkyunkwan Univ Dept Elect & Comp Engn Suwon 16419 South Korea Sungkyunkwan Univ Artificial Intelligence Dept Suwon 16419 South Korea

Liver ultrasound (US) plays a critical role in diagnosing liver diseases. However, it is often difficult for examiners to accurately identify the liver segments captured in US images due to patient variability and the complexity of US images. Our study aim is automatic, real-time recognition of standardized US scans coordinated with reference liver segments to guide examiners. We propose a novel deep hierarchical architecture for classifying liver US images into 11 standardized US scans, which has yet to be properly established due to excessive variability and complexity. We address this problem based on a hierarchical classification of 11 US scans with different features applied to individual hierarchies as well as a novel feature space proximity analysis for handling ambiguous US images. Experiments were performed using US image datasets obtained from a hospital setting. To evaluate the performance under patient variability, we separated the training and testing datasets into distinct patient groups. The experimental results show that the proposed method achieved an F1-score of more than 93%, which is more than sufficient for a tool to guide examiners. The superior performance of the proposed hierarchical architecture was demonstrated by comparing its performance with that of non-hierarchical architecture.

关键词： ultrasound image liver scan deep learning hierarchical classification

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：