检索结果-内蒙古大学图书馆

International Conference on Devices, Circuits and Systems (ICDCS)

作者： D. Malathi S. Gautham M. Dineshkumar K. Balakrishnan Department of Electronics and Communication Engineering Kongu Engineering College Erode India

ISBN: (数字)9798350350470

ISBN: (纸本)9798350350487

Crack is an important factor to consider when assessing the quality of concrete structures since it impacts the structure's longevity, application, and safety. Convolutional neural networks are increasingly the best option to replace manual crack detection because of the advancement of methods for deep learning. Machine learning algorithms known as artificial neural networks (ANNs) imitate how the human brain functions. These neural networks can be implemented in software. However, these neural networks require large computations. Hardware implementation of these neural networks has higher processing speeds than their software implementations. CNN is a particular kind of artificial neural network that is used to interpret pixel data and is utilised in image detection and processing. Computer Vision applications including object identification, image segmentation, and image classification work well with convolutional neural networks. employed for categorization The proposed method uses a configurable convolution neural network system for crack detection. An accuracy of 97.5% is achieved over 200 images. By detecting the crack effectively using the method, the quality of the concrete structures will be ensured using dedicated hardware shortly.

关键词： Accuracy Convolution Software Hardware Safety Convolutional neural networks Object recognition

来源：评论

学校读者我要写书评

暂无评论

EPT-Net: Edge Perception Transformer for 3D Medical image Segmentation

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2023年第11期42卷 3229-3243页

作者： Yang, Jingyi Jiao, Licheng Shang, Ronghua Liu, Xu Li, Ruiyang Xu, Longchang Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ China Xian 710071 Peoples R China Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China

The convolutional neural network has achieved remarkable results in most medical image seg- mentation applications. However, the intrinsic locality of convolution operation has limitations in modeling the long-range dependency. Although the Transformer designed for sequence-to-sequence global prediction was born to solve this problem, it may lead to limited positioning capability due to insufficient low-level detail features. Moreover, low-level features have rich fine-grained information, which greatly impacts edge segmentation decisions of different organs. However, a simple CNN module is difficult to capture the edge information in fine-grained features, and the computational power and memory consumed in processing high-resolution 3D features are costly. This paper proposes an encoder-decoder network that effectively combines edge perception and Transformer structure to segment medical images accurately, called EPT-Net. Under this framework, this paper proposes a Dual Position Transformer to enhance the 3D spatial positioning ability effectively. In addition, as low-level features contain detailed information, we conduct an Edge Weight Guidance module to extract edge information by minimizing the edge information function without adding network parameters. Furthermore, we verified the effectiveness of the proposed method on three datasets, including SegTHOR 2019, Multi-Atlas Labeling Beyond the Cranial Vault and the re-labeled KiTS19 dataset called KiTS19-M by us. The experimental results show that EPT-Net has significantly improved compared with the state-of-the-art medical image segmentation method.

关键词： Medical image segmentation convolu-tional neural networks transformer attention mechanism

来源：评论

学校读者我要写书评

暂无评论

An Arabic Manuscript Regions Detection, Recognition and Its applications for OCRing

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION processing 2023年第1期22卷 1-28页

作者： Al-Barhamtoshy, Hassanin M. Jambi, Kamal M. Rashwan, Mohsen A. Abdou, Sherif M. King Abdulaziz Univ Fac Comp & Amp Informat Technol Informat Technol Dept Jeddah Saudi Arabia King Abdulaziz Univ Fac Comp & Amp Informat Technol Comp Sci Dept Jeddah Saudi Arabia Cairo Univ Fac Engn Elect & Commun Dept Giza Egypt Cairo Univ Fac Artificial Intelligence Informat Technol Dept Giza Egypt

The problem of Region of Interest (RoI) in document layout analysis and document recognition has recently become an essential topic in OCRing systems. Arabic manuscript layout analysis and OCRing recognition using language detection, document category, and RoI with Keras and TensorFlow are terms of the state-ofthe-art that should be investigated. This article investigates the problem of Arabic manuscript recognition problems with respect to in OCRing-based recognition. A new framework architecture, which integrates Fast Gradient Sign Method (FGSM) using Keras and TensorFlow with adversarial image generation during training procedure is proposed. Also, the article tries to improve the OCRing accuracy of the image enhancement, alignment, layout analysis, and recognition using deep learning in multilingual system. RoIs detections will be performed using a custom trained deep learning model using bounding box regression with Keras and TensorFlow. This topic investigates an extension of Page Segmentation Method (PSM) to enhance OCRing parameter modes and enhances Arabic OCRing system accuracy from reinforcement strategy. Therefore, the article achieves a significant improvement of OCRing results due to the three parameters: language identification, document category, and RoI types (Table, Title, Paragraph, figure, and list). This model is based on "region proposal algorithm" as a basis ofCNN object detectors to find the number of the RoIs. Therefore, the proposed framework performs three distinctive tasks: (1) CNN architecture for adversarial training, (2) an implementation of the FGSM with Keras and TensorFlow, and (3) an adversarial training script implementation with the CNN and the FGSM method. The experiments on Arabic manuscript dataset including Arabic text, English/Arabic documents, and Latin digits' datasets, demonstrate the accuracy of the proposed method. Moreover, the proposed framework performs well and succeeded in defending against adversarial attacks or a

关键词： Arabic OCR layout analysis Convolution neural networks (CNN) Deep Learning RoIs (Bounded Box)

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Learning for HAR Using 3D Siamese Network 15

A Few-Shot Learning for HAR Using 3D Siamese Network

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Guanghui, Hua Kumar, G. Hemantha Aradhya, V.N. Manjunath Punithavalli University of Mysore Dept. of studies in Computer Science Mysuru India Jss Science and Technology University Dept. of Computer Applications Mysuru India Bharathiar University Department of Computer Applications Coimbatore India

ISBN: (纸本)9798350370249

In artificial intelligence, deep learning techniques were applied in a wide field due to their ability to automatically learn complex patterns from raw data, such as image classification, object detection, image generation, and video analysis in computer vision. These applications are just the tip of a substantial iceberg. With the development of deep techniques to achieve state-of-art accuracy, learn precisely relevant features from raw data, and improve the robustness of models to make them versatile solutions. The traditional deep learning techniques require vast computational resources, including high-performance computer GPUs or TPUs, and can be expensive in terms of hardware. In Human Activity Recognition Systems (HARs). The video needs more computational resources than image processing. In this paper, we proposed a few-shot learning approach based on a 3D Siamese Network with depth video sequences to address the action video similarity or dissimilar problem. Convolutional neural networks (CNNs) are well-suited for images and spatial data processing. The 3DCNN is an extension of CNNs to incorporate an additional temporal dimension to capture the temporal pattern. From the 3D Siamese network, we extract more effective features with spatial-temporal action information from raw data. We employed the 3DCNNs Siamese Network (3DCNNs+SN) with shared weight to recognize or classify a new class of data without new sample data only based on learning training existing sample constructed model. In addition, we divided the benchmark dataset MSR Action 3D dataset into sub-dataset1 (SD-1), sub-dataset2 (SD-2) and sub-dataset3(SD-3) to train and validate our proposed method. For dissimilar sub-dataset 2 we got a 98.1% accuracy, 33% on high-similar sub-dataset 3 and 63.5% on merged sub-dataset SD-4 from sub-dataset2 (SD-2) and sub-dataset3(SD-3). © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Inducing Inductive Bias in Vision Transformer for EEG Classification 49

Inducing Inductive Bias in Vision Transformer for EEG Classi...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Khadka, Rabindra Lind, Pedro G. Mello, Gustavo Riegler, Michael A. Yazidi, Anis Simula Metropolitan Ctr Digital Engn Oslo Norway Nord Ctr Sustainable & Trustworthy Artificial Int Oslo Norway

ISBN: (纸本)9798350344868;9798350344851

Human brain signals are highly complex and dynamic in nature. Electroencephalogram (EEG) devices capture some of this complexity, both in space and in time, with a certain resolution. Recently, transformer-based models have been explored in various applications with different modalities of data. In this work, we introduce a transformer-based model for the classification of EEG signals, inspired by the recent success of the Vision Transformer (ViT) in image classification. Driven by the distinctive characteristics of the EEG data, we design a module that enables us to (1) extract spatio-temporal tokens inherent in the EEG signals and (2) integrate additional non-linearities to capture intricate and non-linear patterns in EEG signals. To that end, we introduce a new lightweight architectural component that combines our proposed attention model with convolution. This convolutional tokenization module forms the basis of our vision backbone referred to as Brain Signal Vision Transformer (BSVT). This architecture takes into account the spatial and temporal features in EEG datasets, leading to token embeddings that effectively capture the fusion of spatial-temporal information. Moreover, while transformer-based models typically perform well when provided with large datasets, here we show that our combination of the inherent inductive bias of Convolutional neural networks (CNN) with the transformer enables efficient training from scratch using relatively small datasets, with as few as 0.75M parameters. On the publicly available EEG dataset from Temple University Hospital (TUH Abnormal), our model achieves results comparable or superior to its counterpart ViT model with patchify stem. The implementation is available at https://***/IamRabin/***

关键词： EEG CNN ViT Tokenization Inductive bias

来源：评论

学校读者我要写书评

暂无评论

Detection of Polycystic Ovary Syndrome Using VGG-16 and Inception-V3 2

Detection of Polycystic Ovary Syndrome Using VGG-16 and Ince...

引用

2nd IEEE International Conference on Communication, Security and artificial Intelligence, ICCSAI 2023

作者： Castelino, Karen Bagoriya, Sachin Gaikwad, Pankaj Kurhade, Swapnali Bhavathankar, Prasenjit Sardar Patel Institute of Technology Information Technology Mumbai India

ISBN: (纸本)9798350369960

Polycystic Ovary Syndrome (PCOS) is a major health concern amongst a majority of women. Many issues, including infertility, acne, hirsutism, irregular menstrual cycles, and obesity, may result from it. It could also result in type 2 diabetes, endometrial cancer, heart problems, and high blood pressure. Early diagnosis of PCOS may help prevent and treat such health concerns. This paper proposes using ultrasound imaging of the follicles to extract vital details about the ovary, such as the kind of cyst, the variety of follicles present, and how the size of the follicle reacts to hormonal imbalance. Using image processing techniques, morphological operations, and machine learning, the models identify the valuable characteristics in the ultrasound pictures, highlight them, and then build a suitable classification model for the same. On using transfer learning models such as VGG-16 and Inception-V3, an accuracy of 100% each is obtained. © 2023 IEEE.

关键词： Convolutional neural networks Deep Learning Feature Extraction image Classification Machine Learning Polycystic Ovary Syndrome

来源：评论

学校读者我要写书评

暂无评论

RSNN: A Software/Hardware Co-Optimized Framework for Sparse Convolutional neural networks on FPGAs

引用

IEEE ACCESS 2021年 9卷 949-960页

作者： You, Weijie Wu, Chang Fudan Univ Sch Microelect State Key Lab ASIC & Syst Shanghai 200433 Peoples R China

Convolutional neural networks (CNNs) have been shown to be very useful in image recognition and other artificial Intelligence (AI) applications, however, at the expense of intensive computation requirement. To address the challenge of overwhelming calculation requirements, researchers have proposed various network pruning techniques. But, due to the irregular sparse patterns, unstructured sparse networks are difficult to compute efficiently on either Graphic processing units (GPUs) or Field Programmable Gate Arrays (FPGAs). In this paper, we propose a software/hardware co-optimized Reconfigurable Sparse convolutional neural Network accelerator design (RSNN) on FPGAs. A novel sparse convolution dataflow is proposed with simpler control logic than existing mux-based selection logic. To balance the computation load on different processing Units (PUs), we propose a software-based load-balance aware pruning technique as well as a kernel merging method. Experimental results show that RSNN is 2.41x-7.91x better on Digital Signal Processor (DSP) efficiency than previous dense CNN FPGA accelerators, and 1.23x-2.93x better than previous sparse CNN FPGA accelerators.

关键词： Kernel Field programmable gate arrays Hardware Convolutional neural networks Sparse matrices Optimization Digital signal processors Accelerator convolutional neural network FPGA sparse neural network

来源：评论

学校读者我要写书评

暂无评论

An evaluation of EfficientDet for object detection used for indoor robots assistance navigation

引用

JOURNAL OF REAL-TIME image processing 2022年第3期19卷 651-661页

作者： Afif, Mouna Ayachi, Riadh Said, Yahia Atri, Mohamed Univ Monastir Lab Elect & Microelect EuE Fac Sci Monastir Monastir Tunisia Northern Border Univ Coll Engn Elect Engn Dept Ar Ar Saudi Arabia King Khalid Univ Coll Comp Sci Abha Saudi Arabia

Indoor object detection and recognition present one of the most crucial tasks for computer vision and robotic systems. Developing new intelligent autonomous robots is required in various applications including blind and visually impaired people assistance navigation and smart healthcare. Intelligent robots navigation is still a very challenging problem as it involves various aspects including indoor objects detection, recognition and scene understanding. We propose in this work to develop an indoor object detection system that can be used for intelligent vision of robotics applications. We ensure in this paper a lightweight implementation of the system using EfficientDet neural network. The proposed work presents a vision-based detection system able to work on real mobile robots by studying and considering their limited resources implementations. To ensure a lightweight implementation of the proposed indoor objects detection system and to design a deployable system in mobile robots application, we applied the weights pruning technique. To contribute for an embedded implementation of the proposed system, we used a pruning method which successfully reduced the network size, complexity and computation resources. Experimental results have demonstrated the robustness of the proposed indoor object detection system that can be deployed for indoor robotics assistance navigation systems. Based on the obtained results, we note that the proposed system achieved very competitive results in terms of detection precision as well as processing time. The proposed system can runs in low-end devices as we succeeded to reduce the parameters and FLOPs number, we achieved 89% on the testing set of the proposed indoor data set for EfficientDet D2. We achieved 31 FPS for the basic EfficientDet model and 38 FPS for the pruned model.

关键词： Indoor robot navigation Indoor object detection Deep learning Pruning neural networks artificial intelligence Blind and visually impaired

来源：评论

学校读者我要写书评

暂无评论

3D-CNN for Breast Cancer Detection on Angular IR images 3rd

3D-CNN for Breast Cancer Detection on Angular IR Images

引用

3rd International Conference on artificial Intelligence over Infrared images for Medical applications, AIIIMA 2024

作者： de Freitas Oliveira Baffa, Matheus Neves, Thamiris Gire Zine Tulha, Carinna Nunes Conci, Aura SP Ribeirão Preto Brazil SP Santo André Brazil SP Campinas Brazil RJ Niterói Brazil

ISBN: (纸本)9783031765834

Breast cancer detection depends on accurate imaging techniques that capture the full complexity of the breast tissue. Angular breast images, particularly the mediolateral oblique and mediolateral projections, play a vital role in traditional mammography, offering comprehensive views that include difficult-to-visualize areas. However, infrared imaging, which measures surface temperature distribution, provides a complementary approach by highlighting thermal anomalies that may indicate underlying malignancies. While frontal infrared images are commonly used, they often fail to capture the entire thermal profile of the breast, particularly in areas obscured from the frontal view. To address this limitation, angular infrared images can be integrated to provide a more complete analysis, although this approach introduces challenges in image processing and interpretation. In this paper, we present a model to address the problem of breast cancer detection specifically on angular images, consisting of a 3D convolutional neural network (CNN) that integrates lateral and oblique views into a single volumetric representation, allowing for comprehensive analysis of the breast. The results of our ablation experiment demonstrates an architecture that effectively classifies breast cancer, achieving 93.82% accuracy, 93.82% sensitivity, and an area under the receiver operating characteristic curve of 97.22%, which highlights the model’s efficacy in distinguishing between healthy and cancerous cases. The use of a 3D CNN for this problem is well-suited given the volumetric nature of the data, making it a promising approach for further exploration in medical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The Review of image processing Based on Graph neural Network 14th

The Review of Image Processing Based on Graph Neural Network

引用

14th International Conference on Intelligent Robotics and applications (ICIRA)

作者： Nie, Jinji Xu, You Huang, Yichuan Li, Jiehao Guangdong Polytech Normal Univ Guangzhou 51000 Guangdong Peoples R China South China Univ Technol Sch Elect Power Engn Guangzhou 510640 Peoples R China Beijing Inst Technol State Key Lab Intelligent Control & Decis Complex Beijing 100081 Peoples R China

ISBN: (纸本)9783030890926;9783030890919

Convolutional neural networks have ushered in significant advancements in the field of image processing. Convolutional neural networks, on the other hand, operate well with European geographic data, whereas graph neural networks function better with non-European geographical data. This paper summarizes the application of image processing based on graph neural network. First, this article introduces the development history of graphs and graph neural networks and then explains the graphs' concept and structure. Secondly, it focuses on the graph convolutional neural network, and details the graph convolutional neural network of spectrum and space. Finally, for graph convolutional neural network application in image processing, three processing methods are concluded.

关键词： image processing Graph neural network Convolutional neural network

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：