检索结果-内蒙古大学图书馆

29th IEEE International conference on parallel and distributed Systems, ICPADS 2023

作者： Wang, Xinhui Tian, Xuedong Hebei University School of Cyber Security and Computer Baoding071002 China Hebei University Institute of Intelligent Image and Document Information Processing Baoding071002 China

ISBN: (纸本)9798350330717

The complex glyph structures and diverse writing styles of ancient Chinese character images lead to suboptimal performance when existing image retrieval methods are directly applied to datasets of these images. Addressing the impact on retrieval caused by the complex glyph structure and rich detail information characteristic of ancient Chinese character images, a multi-layer feature adaptive fusion model for ancient Chinese character image retrieval is designed. Firstly, a local feature extraction module is constructed to obtain low-level feature maps with different spatial receptive fields. Secondly, to better fuse features of varying scales, an improved ASFF(Adaptively Spatial Feature Fusion) method is employed to build the PSASFF(Pixel Shuffle Adaptively Spatial Feature Fusion) module for adaptive fusion of multi-layer features extracted by the designed network. Finally, in order to reduce the influence of the writing style of ancient Chinese characters on retrieval, the cosine similarity scores of image retrieval before and after fine processing are weighted and used as the ultimate similarity scores. The retrieval method proposed achieves an average retrieval accuracy of mAP@50 and mAP@30 of 0.8537 and 0.9576 respectively on the ancient Chinese character image dataset. Experimental results demonstrate the effectiveness of this method for ancient Chinese character image retrieval. © 2023 IEEE.

关键词： adaptively feature fusion ancient Chinese character image retrieval local feature extraction weighted similarity scores

来源：评论

学校读者我要写书评

暂无评论

MDFD: STUDY OF distributed NON-IID SCENARIOS AND FRECHET DISTANCE-BASED EVALUATION 30

MDFD: STUDY OF DISTRIBUTED NON-IID SCENARIOS AND FRECHET DIS...

引用

30th IEEE International conference on image processing (ICIP)

作者： Wang, Wei Zhang, Mingwei Wu, Ziwen Chen, Qianxi Li, Yue Nankai Univ Trusted AI Lab Coll Comp Sci Coll Comp Sci Tianjin Peoples R China Tianjin Key Lab Network & Data Secur Technol Tianjin Peoples R China

ISBN: (纸本)9781728198354

With the development of distributed machine learning and federated learning, the solution to the data island problem is promoted. People use computer clusters to train machine learning models on data distributed in different regions. In the early stage of research, researchers usually assume that the data sets of each node are independent identically distribution (IID), but this is a strong assumption, which is challenging to meet in practical applications. Therefore, research on non-IID has become a hot spot in recent years. However, there is no uniform standard for designing and evaluating non-IID scenarios. This paper proposes a Frechet distance-independent non-IID distribution dataset metric MDFD. And we conducted experiments on different types of distributed machine-learning methods in different non-IID scenarios to verify the effectiveness of MDFD.

关键词： Machine learning federal learning non-IID generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Improving Visual Question Answering by image Captioning

引用

IEEE ACCESS 2025年 13卷 46299-46311页

作者： Shao, Xiangjun Dong, Hongsong Wu, Guangsheng Hunan Univ Arts & Sci Sch Comp & Elect Engn Changde 415000 Peoples R China Key Lab Hunan Prov Control Technol Distributed Ele Changde 415000 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Lyuliang Univ Dept Comp Sci Luliang 033000 Peoples R China Xinyu Univ Sch Math & Comp Sci Xinyu 338004 Peoples R China

Visual Question Answering (VQA) is a challenging task that bridges the computer vision and natural language processing communities. It provide natural language answers to questions related to an associated image. Most existing VQA methods focus on the fusion and inference of visual features with the textual question. However, visual features often lack the necessary semantic information required to answer the questions accurately. To address this limitation, we propose a novel approach called Question-Guided parallel Attention (QGPA), which effectively leverages the semantic information provided by an embedded image captioning model to answer related questions. First, we introduce an Attention-Aware (AA) mechanism that extends the traditional attention mechanism, helping to filter out incorrect or irrelevant information during answer prediction. Second, QGPA incorporates AA, which simultaneously utilizes visual features and semantic information from the embedded image captioning model to answer questions. Experiments results demonstrate that the accuracy of "Overall" of our proposed model delivers 72.57% and 72.55% on the test-dev and test-std split set of VQA-v2.0 dataset, respectively, which outperforms most existing VQA methods. The experiment results and ablation studies demonstrate that the proposed method has good performance.

关键词： Visualization Semantics Long short term memory Question answering (information retrieval) Predictive models Accuracy Knowledge based systems Feature extraction Information filters Context modeling Deep learning image captioning multimodal learning visual question answering

来源：评论

学校读者我要写书评

暂无评论

BuRnSNet: BURN REGION SEGMENTATION NETWORK FROM COLOR imageS WITH TWO-WAY CNN 31

BuRnSNet: BURN REGION SEGMENTATION NETWORK FROM COLOR IMAGES...

引用

2024 International conference on image processing

作者： Chauhan, Joohi Rosin, Paul L. Goyal, Puneet Motilal Nehru Natl Inst Technol Allahabad Allahabad Uttar Pradesh India Cardiff Univ Cardiff Wales Indian Inst Technol Ropar Bara Phool Punjab India NIMS Univ NIET Jaipur Rajasthan India

ISBN: (纸本)9798350349405;9798350349399

Burn injury is a serious health issue leading to several thousands of annual fatalities. The color image-based automated burns diagnostic and assessment methods hold the potential for timely diagnosis and treatment. However, the research is limited in this domain which remains a major challenge. In this work, we explore and address the complex task of burn region segmentation in color images of burn patients. We present a semantic segmentation network that has two parallel sub-networks: a spatial-stream network for extracting low-level features and a contextual-stream network for generating a larger receptive field. Our network utilizes the pre-trained ResNet101 network, global average pooling, and instance normalization for better encoding and fusion of the network outputs. This dual-stream approach optimizes the performance in situations where data scarcity poses a challenge, facilitating robust semantic segmentation despite limited training samples. We prepared a pixel-wise labeled dataset for burn region segmentation and the experimental results on this dataset show that our proposed network outperforms several state-of-the-art semantic segmentation methods. Our method achieved mIOU and Matthews' correlation coefficient (MCC) of 74.3% and 81.7%, respectively, approximately 4.5% higher than the second-best performing method. The Extended Burn image Segmentation (EBIS) dataset and our model are available at https://***/VEDAs-Lab/EBIS

关键词： Burn injury Semantic image segmentation Convolutional neural network Instance Normalization Matthews' correlation coefficient

来源：评论

学校读者我要写书评

暂无评论

RAMMM: A Rapid Attention-Based Multimodal Modification Model for Massive image Generation 29

RAMMM: A Rapid Attention-Based Multimodal Modification Model...

引用

29th IEEE International conference on parallel and distributed Systems, ICPADS 2023

作者： Xu, Zhenyuan Chen, Xuewen Wang, Taotao Quan, Wei Zhu, Yi Nanjing Audit University Nanjing211815 China

ISBN: (纸本)9798350330717

Nowadays, deep learning (DL) techniques have found extensive applications in the Internet of Things (IoT) community, such as autonomous driving and medical diagnosis. Despite these successful implementations, elevated data collection expenses, data confidentiality concerns, and privacy issues all contribute to the complexity and costliness of data acquisition in DL-based image processing. image modification methods based on diffusion models can subtly modify images to generate new images with similar content to the original image but with unique differences, providing a powerful tool for data augmentation. Nonetheless, diffusion models exhibit constraints in cross-modal image modification, such as sensitivity to prompt, model complexity, and user-friendliness. To address these issues, this paper proposes a rapid attention-based multimodal modification model (RAMMM) to facilitate straightforward and efficient text-guided image modification. Our proposed RAMMM primarily enhances the text processing and image generation procedures via an attention mechanism, thus improving the ability in capturing semantic and contextual information within the text. Consequently, RAMMM excels in generating high-quality sample images aligned with the description provided for the modified text. In addition, by utilizing text-guided image modification, RAMMM is capable of generating batches of image samples systematically to augment the dataset size. Evaluation results demonstrate that RAMMM can improve the performance and generalization capabilities of diffusion models by enhancing both the quality and quantity of the dataset. When employed for data augmentation on the CIFAR10 dataset, RAMMM achieves a 1.5% increase in target recognition accuracy. © 2023 IEEE.

关键词： attention mechanism data augmentation deep learning image modification

来源：评论

学校读者我要写书评

暂无评论

CONTOUR-WEIGHTED LOSS FOR CLASS-IMBALANCED image SEGMENTATION 31

CONTOUR-WEIGHTED LOSS FOR CLASS-IMBALANCED IMAGE SEGMENTATIO...

引用

2024 International conference on image processing

作者： Huang, Zhengyong Sui, Yao Peking Univ Natl Inst Hlth Data Sci Beijing Peoples R China Peking Univ Inst Med Technol Beijing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

image segmentation is critically important in almost all medical image analysis for automatic interpretations and processing. However, it is often challenging to perform image segmentation due to data imbalance between intra- and inter-class, resulting in over- or under-segmentation. Consequently, we proposed a new methodology to address the above issue, with a compact yet effective contour-weighted loss function. Our new loss function incorporates a contour-weighted cross-entropy loss and separable dice loss. The former loss extracts the contour of target regions via morphological erosion and generates a weight map for the cross-entropy criterion, whereas the latter divides the target regions into contour and non-contour components through the extracted contour map, calculates dice loss separately, and combines them to update the network. We carried out abdominal organ segmentation and brain tumor segmentation on two public datasets to assess our approach. Experimental results demonstrated that our approach offered superior segmentation, as compared to several state-of-the-art methods, while in parallel improving the robustness of those popular state-of-the-art deep models through our new loss function. The code is available at https://***/huangzyong/Contour-weighted-Loss-Seg.

关键词： image segmentation medical image computing contour weighting map deep learning loss function

来源：评论

学校读者我要写书评

暂无评论

Classification Assistance Based image Inpainting for BR code 5

Classification Assistance Based Image Inpainting for BR code

引用

5th International conference on Information Science, parallel and distributed Systems, ISPDS 2024

作者： Yang, Yuting Li, Jinfeng Liang, Naifeng Li, Man Cai, Xiangyun Zheng, Ziyao City College of Huizhou China

ISBN: (纸本)9798350352719

Recently, many image inpainting methods have achieved promising performance in recovering damaged natural images in various scenes. Different from natural images, blur-readable (BR) 2D barcode images have distinct structural characteristics, such as finder patterns (represent the version information) and data bits. Version information is crucial for decoding BR code. The problem of missing data bits can be solved by image inpainting methods and error correction codes. However, when the finder patterns are damaged, they may not be correctly repaired through the inpainting technology, resulting in the failure of barcode recognition. The limitation of existing image inpainting algorithms is that the version information of BR code cannot be obtained while generating repaired result. In this paper, we innovatively introduce the classification task into the inpainting network and propose a classification assistance based inpainting model for BR code (CAII). Experiment results show that our method can efficiently enhance the readability of damaged BR code images. © 2024 IEEE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

A New Exact State Reconstruction Strategy for Conjugate Gradient methods with Arbitrary Preconditioners

A New Exact State Reconstruction Strategy for Conjugate Grad...

引用

1st International conference on Smart Energy Systems and Artificial Intelligence (SESAI)

作者： Mayer, Viktoria Gansterer, Wilfried N. Univ Vienna Fac Comp Sci UniVie Doctoral Sch Comp Sci DoCS Vienna Austria Univ Vienna Fac Comp Sci Vienna Austria

The likelihood of unanticipated node failures in large-scale parallel computers increases with growing numbers of nodes. Furthermore, global reduction operations become major bottlenecks due to their limited parallel ... 详细信息

ISBN: (纸本)9798350364613;9798350364606

关键词： communication-hiding algorithms pipelined conjugate gradient algorithms extreme-scale parallel computing algorithmic fault tolerance exact state reconstruction

来源：评论

学校读者我要写书评

暂无评论

Exploration on Facial image Recognition and processing Algorithms under Hadoop

Exploration on Facial Image Recognition and Processing Algor...

引用

2023 International conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Gu, Meifang Tang, Hailin Li, Lili Guangdong Baiyun University Institutional Research Center Guangdong Guangzhou China Guangdong Baiyun University Faculty of Intelligent Manufacturing Engineering Guangdong Guangzhou China Guangdong Baiyun University Faculty of Megadata and Computing Guangdong Guangzhou China

ISBN: (纸本)9798350315455

Face recognition is an important technology in the field of digital image processing, which has a crucial impact on subsequent work. This article introduced an example of facial recognition based on the combination of Hadoop algorithm and facial feature extraction. The experimental results were validated in the MATLAB environment and trained using neural networks to improve system performance and adaptability. The test results indicated that the processing speed was between 0.84 and 0.97;the highest resource utilization rate was 0.06, and the lowest was 0.02;the throughput range of facial data was between 13598 and 15479, and the throughput range of user data was between 5037 and 5879. This indicated that the system had fast recognition speed and high-precision image output, and exhibited good fault tolerance and robustness compared to other methods. Exploring facial image recognition and processing algorithms in the Hadoop environment can utilize Hadoop's distributed computing capabilities to accelerate the processing of large-scale facial image data, achieve fast and efficient processing of large-scale facial image data, accelerate algorithm operation, and possess distributed computing capabilities. Multiple computing nodes can be used for parallel processing to improve algorithm performance. © 2023 IEEE.

关键词： algorithm research facial recognition Hadoop algorithm image processing

来源：评论

学校读者我要写书评

暂无评论

Plant Diseases Detection Using Machine Learning and image processing: Review 4

Plant Diseases Detection Using Machine Learning and Image Pr...

引用

4th International conference on Embedded and distributed Systems, EDiS 2024

作者： Touati, Fatima Zohra Loukil, Lakhdar Amrane, Bakhta University of Oran 1 Ahmed Ben Bella Department of Computer Science Oran Algeria

ISBN: (纸本)9798331519872

An agricultural productivity boost that is sustainable requires the early and accurate identification of plant diseases. Traditionally, human experts have been used to diagnose plant diseases. But it is expensive, time consuming, and in some cases impractical. Currently, machine learning (ML) and deep learning (DL) methods based on image processing techniques have been introduced to classify leaf lesions caused by diseases. Thus, research applying image processing and machine learning techniques for plant diseases has become a hot research topic. In this report, we propose a review of a set of studies carried out in the field of plant disease detection using machine learning and image processing techniques such as segmentation and feature extraction. The aim of this review is to provide useful knowledge and recommendations to researchers and practitioners to develop reliable and efficient methods for detecting plant diseases by processing images using deep learning techniques in particular. To this end, we have conducted an empirical evaluation of select educational curricula focused on the detection of plant diseases. © 2024 IEEE.

关键词： CNN Deep learning image processing Machine learning Plant diseases detection

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：