检索结果-内蒙古大学图书馆

Copy-Move Detection in Optical Microscopy: A Segmentation Network and a dataset

IEEE signal processing LETTERS 2025年 32卷 1106-1110页

作者： Shao, Hao-Chiang Liao, Yuan-Rong Tseng, Tse-Yu Chuo, Yen-Liang Lin, Fong-Yi Natl Chung Hsing Univ Inst Data Sci & Informat Comp Taichung 402202 Taiwan SOE Technol Inc Taipei 106 Taiwan IGrp Asia Pacific Ltd Taipei 104 Taiwan

With increasing revelations of academic fraud, detecting forged experimental images in the biomedical field has become a public concern. The challenge lies in the fact that copy-move targets can include background tissue, small foreground objects, or both, which may be out of the training domain and subject to unseen attacks, rendering standard object-detection-based approaches less effective. To address this, we reformulate the problem of detecting biomedical copy-move forgery regions as an intra-image co-saliency detection task and propose CMSeg-Net, a copy-move forgery segmentation network capable of identifying unseen duplicated areas. Built on a multi-resolution encoder-decoder architecture, CMSeg-Net incorporates self-correlation and correlation-assisted spatial-attention modules to detect intra-image regional similarities within feature tensors at each observation scale. This design helps distinguish even small copy-move targets in complex microscopic images from other similar objects. Furthermore, we created a copy-move forgery dataset of optical microscopic images, named FakeParaEgg, using open data from the ICIP 2022 Challenge to support CMSeg-Net's development and verify its performance. Extensive experiments demonstrate that our approach outperforms previous state-of-the-art methods on the FakeParaEgg dataset and other open copy-move detection datasets, including CASIA-CMFD, CoMoFoD, and CMF.

关键词： Forgery Feature extraction Tensors Microscopy Image segmentation Optical microscopy Correlation Decoding Fraud Optical imaging Copy-move forgery detection attention multiresolution optical microscopy images co-saliency

来源：评论

学校读者我要写书评

暂无评论

An NN Framework for Target Number Detection in FMCW Radar Systems via Hankelization: A Low-Dimensional data Representation Perspective

引用

IEEE ACCESS 2025年 13卷 58823-58834页

作者： Kim, Jung-Hwan Kim, Gyung-Eun Lee, Woong-Hee Dongguk Univ Seoul Div Elect & Elect Engn Seoul 04620 South Korea

In this paper, we introduce a novel neural network (NN)-based algorithm that significantly improves the target number detection in frequency modulated continuous wave (FMCW) radar systems. By integrating the mathematical processes of Hankelization and singular value extraction, we can perform input data manipulation for effective target number detection, resulting in constructing an efficient NN framework. This is based on the following mathematical properties: 1) A sequence obtained by uniform sampling of the superposition of K radio waves can be represented as a superposition of K geometric sequences;2) A Hankelized matrix formed by the superposition of K geometric sequences exhibits low-rank characteristics;and 3) In an FMCW radar system with K targets, if the received signal, which is represented as a matrix, is ideal, the vectors obtained by extracting this matrix in row, column, diagonal, and anti-diagonal patterns can all be modeled as a superposition of K geometric sequences. The proposed NN framework showcases remarkable improvements in accuracy and efficiency for target number detection, leveraging a small sized dataset and a compact NN design to achieve unprecedented performance levels. Numerical results validate the superiority of our method across various scenarios, establishing a new benchmark for low-dimensional data representation in radar systems.

关键词： Radar Estimation Accuracy Heuristic algorithms Radar detection Radar antennas Artificial neural networks Vectors signal processing algorithms data visualization Hankelization singular value extraction neural networks radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Robust Range Super-Resolution Imaging With Multicriteria Joint Constraints via Double Smoothed l0-Norm Under Limited Resources

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 5145-5165页

作者： Liu, Zhexian Shao, Shuai Liu, Hongwei Su, Tao Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

The radar's high-resolution range profile (HRRP) contains rich physical structural features of targets, making it of great value for target recognition and classification. However, in practical applications, the effective bandwidth of radar signals is limited due to the nonideal factors such as spectrum control, limited hardware equipment capabilities, and spectrum electromagnetic interference. Thus, it is difficult to reach the requirement of high-resolution and accurate target characterization in range profiles under limited resources, which will reduce subsequent detection, imaging, and recognition performance. To address the problem, this article proposes a robust range profile super-resolution method with multicriteria joint constraints of sparsity, low-rank, and Doppler under a multiple measurement vector model. In this technique, based on compressed sensing theory and adaptive filtering framework, a sparse reconstruction algorithm via double smoothed l(0)-norm is proposed, which constructs a continuously differentiable Gaussian class function to approximate the l(0)-norm. It combines accelerated gradient algorithm and zero attractor to optimize the multicriteria cost function and iteratively reconstruct the super-resolution range profile. The algorithm improves the super-resolution performance of range profiles, enhances the robustness against noise and complex range profile configurations, and can obtain high-precision HRRP of targets with limited radar resources. Extensive simulation and real data experiments demonstrate that it not only improves the average reconstruction accuracy of super-resolution range profile sequence, but effectively reduces the fluctuation of reconstruction errors. In addition, it does not require high azimuth resolution, and is also highly effective with a small number of sequence echoes.

关键词： Image reconstruction Superresolution Radar Accuracy Target recognition signal processing algorithms Scattering Radar imaging Vectors Doppler effect Compressed sensing (CS) double smoothed l(0) -norm (DSL0) high-resolution range profile (HRRP) limited resource multicriteria joint constraints super-resolution imaging

来源：评论

学校读者我要写书评

暂无评论

Study on the application of transfer learning in small sample image classification of military equipment 5

Study on the application of transfer learning in small sampl...

引用

5th International conference on signal processing and Computer Science, SPCS 2024

作者： Lu, Leiji Yu, Hongxia Xiao, Hongju Bao, Lei Department of Information Engineering Army Academy of Artillery and Air Defense Hefei China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

To address the issue of insufficient military equipment sample data, which cannot meet the training requirements of deep neural networks and tends to cause overfitting, this paper introduces transfer learning technology to solve the small-sample classification problem for military equipment. By constructing a multi-type sample training set and fine-tuning the convolutional layers of pre-trained models, specific target classifiers are trained. Practice has proven that the application of transfer learning in small-sample classification tasks saves model training time, resolves issues related to model overfitting and strong dependence on data labels, and effectively improves the accuracy of image classification based on deep learning for small samples of military equipment. © 2025 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ICBSP 2024 - Proceedings of the 2024 9th International conference on Biomedical Imaging, signal processing

ICBSP 2024 - Proceedings of the 2024 9th International Confe...

引用

2024 9th International conference on Biomedical Imaging, signal processing, ICBSP 2024

ISBN: (纸本)9798400717499

The proceedings contain 24 papers. The topics discussed include: an integrated deep learning model to analyze CT scans for minimally invasive accurate classification of T1a small renal masses;tissue type classification for whole slide histological images with graph convolutional neural network;classifying skin diseases using convolutional neural networks;comparative analysis of YOLO architectures for automated detection of liver disease in histopathological images;bibliometric analysis and research trends in artificial intelligence for medical imaging in Alzheimer’s disease;personalized federated learning using client clustering for medical image classification;data augmentation of domain learning in optic nerve combined cup-disc segmentation with a few labeled data;and a coronary plaque detection and identification method based on medical prior knowledge and hybrid attention unit.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pattern Recognition Methods for GPR-Based Detection of Subsurface Drainage Pipes 24

Pattern Recognition Methods for GPR-Based Detection of Subsu...

引用

8th International conference on Electronic Information Technology and Computer Engineering, EITCE 2024

作者： Bai, Hao Jiang, Lifeng Li, Xiongwei College of Information Engineering Hainan Vocational University of Science and Technology Hainan Haikou China School of Intelligent Manufacturing Changzhou Vocational Institute of Engineering Jiangsu Changzhou China Technology and Development CO. LTD. Hainan Haikou China

ISBN: (纸本)9798400710094

This paper presents the development and application of pattern recognition techniques to identify hyperbolic shapes in Ground Penetrating Radar (GPR) data, which are characteristic signatures of underpavement drainage pipes. The proposed method involves several stages of image processing. It begins with the removal of background noise and enhancement of signal contrast through vertical data selection and background noise subtraction. The signal contrast is further enhanced by squaring the data values, culminating in the conversion of the enhanced images into a binary format to facilitate the detection of hyperbolic patterns. By leveraging improved background reduction methods, the study pre-selects potential target areas, thereby limiting the analysis to regions of interest and enhancing computational efficiency. Field tests conducted on highway surveys demonstrate the effectiveness of this method, successfully identifying known drainage pipes and detecting additional potential targets for further investigation. The results indicate that while the presence of a hyperbolic return strongly suggests a detection, the absence of such a return does not conclusively indicate a false alarm. This underscores the importance of thoroughly investigating all potential target zones identified. The study concludes that integrating pattern recognition into an automated data processing system can significantly improve the accuracy and efficiency of GPR-based detection. Such integration would aid in rapidly identifying clear targets and focusing field investigations on uncertain zones, thereby enhancing the overall effectiveness of subsurface drainage pipe detection. © 2024 Copyright held by the owner/author(s).

关键词： data integration

来源：评论

学校读者我要写书评

暂无评论

Infrared small Target Detection with Feature Refinement and Context Enhancement 31st

Infrared Small Target Detection with Feature Refinement and...

引用

31st International conference on Multimedia Modeling, MMM 2025

作者： Li, Xiuhong Zhu, Xinyue Li, Boyuan Li, Songlin Wang, Luyao Jia, Zhenhong School of Computer Science and Technology Xinjiang University Urumgi China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi China College of Mathematics and System Science Xinjiang University Urumqi China

ISBN: (纸本)9789819620609

Infrared small target detection has received widespread application and attention in both civilian and military fields. However, due to the very small size and lack of unique features of these targets, existing methods often suffer from inaccurate edge localization, and the targets are easily overwhelmed by complex backgrounds. To effectively address these issues, we designed a Feature Refinement and Context Enhancement Network (FCNet). The network consists of a multi-branch feature extraction module (MFEM), which integrates ordinary convolution and center difference convolution for diversified feature extraction, and further refines features through attention mechanism to enhance feature expression ability. In addition, in order to better capture the contextual information of the target, we have introduced the Context Enhancement Module (CEM). The CEM improves the robustness and detection accuracy of the network in complex backgrounds by preserving and enhancing important information in the image. Especially when processing infrared images with complex backgrounds and low signal-to-noise ratios, CEM can effectively highlight the target area and reduce false positives and false negatives. The experimental results on the SIRST dataset show that our FCNet performs well on multiple evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

FBI-Net: Frequency Band Integration Network for Infrared small Target Segmentation

FBI-Net: Frequency Band Integration Network for Infrared Sma...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Biqiao Xin Qiang Li Qianchen Mao Jinbao Wang Bingshu Wang School of Software Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

small targets in infrared imagery exhibit challenging characteristics due to their minimal semantic information and the extremely imbalanced distribution between the targets and the background. In this paper, we propose a frequency band integration network to extract salient features of infrared small targets in both the spatial and frequency domains. To excavate the high-frequency features of the small targets, we propose a frequency decoupling-fusion module. To decrease the semantic loss that occurs in deep networks, we propose a semantic injection mechanism to assist in retaining critical information from shallow layers. Experimental results show that our proposed method reaches higher prediction accuracy and robustness in the infrared small target segmentation task compared with other state-of-the-art approaches.

关键词： Wavelet transforms Frequency-domain analysis Semantics signal processing Feature extraction Excavation Robustness Real-time systems Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

FBI-Net: Frequency Band Integration Network for Infrared small Target Segmentation

FBI-Net: Frequency Band Integration Network for Infrared Sma...

引用

2025 IEEE International conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Xin, Biqiao Li, Qiang Mao, Qianchen Wang, Jinbao Wang, Bingshu School of Software Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)9798350368741

关键词： Feature Fusion Infrared small Target Segmentation Semantic Injection Wavelet Transformation

来源：评论

学校读者我要写书评

暂无评论

A particle belief propagation algorithm based on track-before-detect for tracking low-observable and maneuvering targets using multiple sensor 16

A particle belief propagation algorithm based on track-befor...

引用

16th International conference on signal processing Systems, ICSPS 2024

作者： Cao, Chenghu Huang, Haisheng Zhao, Yongbo Li, Xin Hui, Peiyuan Xi’an University of Posts and Communications Xi’an710121 China National Key Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Xi’an Innovation College of Yan’an University Xi’an710100 China

ISBN: (纸本)9781510689251

It is notoriously challenging work to track an unknown number of low-observable maneuvering targets. In this paper, a sequential Bayesian inference method based on multiple-model dynamic model and track-before-detect measurement (TBD) model is proposed for tracking low-observable maneuvering targets using multiple sensors. Our proposed method is based on a new multi-sensor statistical model that allows targets to interact and contribute to more than one data cell for pixeled image TBD approach. Based on the factor graph representing multi-sensor statistical model, the marginal posterior densities are derived by performing the message passing equations of the proposed belief propagation (BP) algorithm for target detection and target state estimation. The simulation results validate that the computational complexity of our proposed multi-sensor BP-TBD algorithm scales in the number of sensor nodes and demonstrate that its performance is superior among the state-of-the-art multi-sensor TBD methods. © 2025 SPIE.

关键词： Sensor nodes

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：