检索结果-内蒙古大学图书馆

international conference on Computational Vision and Bio-Inspired computing (ICCVBIC)

作者： Shubha, P. Meenakshi, M. Dr Ambedkar Inst Technol Dept Elect & Instrumentat Engn Bangalore 560056 Karnataka India

ISBN: (纸本)9783030372187;9783030372170

A real time face recognition using LBP algorithm and image processing techniques are proposed. Face image is represented by utilizing information about shape and texture. In order to represent the face effectively, area of the face is split into minute sections, then histograms of Local Binary pattern (LBP) are extorted which are then united into a single histogram. Secondly, the recognition is carried out on computed feature space using nearest neighbor classifier. The developed algorithm is validated in real time by developing a prototype model using Raspberry Pi single board computer and also in simulation mode using MATLAB software. The above obtained results match with each other. On comparing both the results, recognition time taken by the prototype model is more than that of the simulation results because of hardware limitations. The real time experimental results demonstrated that the face recognition rate of LBP algorithm is 89%.

关键词： Local Binary pattern (LBP) Matlab Histogram Classifier Raspberry Pi Real time face recognition

来源：评论

学校读者我要写书评

暂无评论

Combining Attention Mechanism and Local-Global Features Association Network for Vehicle Re-identification 22

Combining Attention Mechanism and Local-Global Features Asso...

引用

Proceedings of the 2022 11th international conference on computing and pattern recognition

作者： Cai-Xia Li Xia Du Yun Wu Da-Han Wang Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Vehicle re-identification (Re-ID) aims to retrieve the target vehicle from a large dataset composed of vehicle images captured by multiple cameras. Most vehicles are difficult to recognize in the environment of low resolution, occlusion, and viewpoint change, which brings challenges to vehicle Re-ID. Existing work usually uses additional attribute information to distinguish different vehicles, such as color, viewpoint, and model. However, this requires expensive manual annotation. Therefore, we propose a three-branch network based on attention mechanism and local-global feature association (AM-LGFA) to improve the accuracy of vehicle Re-ID. In the global branch, the global features of the vehicle are extracted. A multi-scale channel attention module is introduced into the attention branch to suppress irrelevant information and extract important channel features. The features extracted from the backbone are divided into different stripe features in the horizontal direction in the local branch. Then connect each stripe feature with the global information to enhance the context between features. Finally, the features extracted from the three branches are concatenated as the feature representation of the test phase. The experimental results show that the features extracted by the AM-LGFA network are complementary. The effectiveness of this method is verified on two challenging public datasets, VehicleID and VeRi-776.

关键词： Attention mechanism Vehicle re-identification Local-global feature association

来源：评论

学校读者我要写书评

暂无评论

international conference "Marchuk Scientific Readings 2020", MSR 2020, Dedicated to the 95th Anniversary of the Birthday of RAS Academician Guri. I. Marchuk

International Conference "Marchuk Scientific Readings 2020",...

引用

international conference on Marchuk Scientific Readings 2020, MSR 2020

The proceedings contain 73 papers. The topics discussed include: numerical modeling of non-stationary heat problems in a two-phase medium;nested alternating - triangular incomplete factorization methods;two-level iterative methods for solving the saddle point problems;zero and first-degree spline multiwavelets and parallel computing;a computer system for the leukocytes classification in medical images;sign language recognition through leap motion controller and input prediction algorithm;a modified algorithm of the latent semantic analysis for text processing in the Russian language;evolutionary synthesis of nonlinear models based on metaheuristic programming and templates;some properties of the classification algorithms using ensemble kernels;the development of a system for automated ontology building based on heterogeneous ontology design patterns;and numerical research of the influence of wall heating on the turbulent flow pattern in an idealized street canyon.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PProCRC: Probabilistic Collaboration of Image Patches for Fine-grained Classification 35

PProCRC: Probabilistic Collaboration of Image Patches for Fi...

引用

35th international conference on Image and Vision computing New Zealand (IVCNZ)

作者： Chakraborti, Tapabrata McCane, Brendan Mills, Steven Pal, Umapada Univ Otago Dept Comp Sci Dunedin New Zealand Indian Stat Inst Comp Vis & Pattern Recognit Unit Bengaluru India

ISBN: (纸本)9781728185798

We present a conditional probabilistic framework for collaborative representation of image patches. It incorporates background compensation and outlier patch suppression into the main formulation itself, thus doing away with the need for preprocessing steps to handle the same. A closed form non-iterative solution of the cost function is derived. The proposed method (PProCRC) outperforms earlier CRC formulations: patch based (PCRC, GP-CRC) as well as the state-of-the-art probabilistic (ProCRC and EProCRC) on three fine-grained species recognition datasets (Oxford Flowers, Oxford-IIIT Pets and CUB Birds) using two CNN backbones (Vgg-19 and ResNet-50).

关键词： Fine-grained visual categorization (FGVC) collaborative representation classifiers (CRC) species recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging Human Knowledge in Large Language Model for Obfuscation-Resisted Phishing URL Detection

Leveraging Human Knowledge in Large Language Model for Obfus...

引用

conference on Mobile and Secure Services (MOBISECSERV)

作者： Zhiwei Fu Sudipta Acharya Steven H. H. Ding Yifan Zhu Jia Fu Chen Xu School of Information Studies McGill University Montreal Quebec Canada School of Computing Queen's University Kingston Ontario Canada University of Illinois Urbana-Champaign Illinois United States

ISBN: (数字)9798350390896

ISBN: (纸本)9798350390902

Phishing is a significant and growing threat on the Internet. There is a growing trend of using deep learning techniques for phishing URL detection due to their capability to recognize a wide range of patterns. However, URL obfuscations have been a popular approach for adversaries to escape the detection mechanism. Existing deep learning solutions are limited to the patterns presented in the training set and suffer from robustness issues. Unlike traditional machine learning solutions, we present the first novel approach to phishing URL detection based on pre-trained large-scale language models (LLMs). Leveraging the general human knowledge embedded in the language model, our solution can accurately detect obfuscated phishing URLs without explicitly training them. We are the first to simulate real-world scenarios of obfuscated phishing URLs in testing procedures, using two prevalent techniques: Domain Obfuscation and Redirects. Our model achieves over 92% and 83% in accuracy in two obfuscation test benchmarks, significantly outperforming baseline models. This study offers a robust and adaptable solution to evolving phishing threats.

关键词： Uniform resource locators Training Deep learning Adaptation models Phishing Large language models Feature extraction Market research Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Low Cloud Type Classification System Using Convolutional Neural Network Algorithm

Low Cloud Type Classification System Using Convolutional Neu...

引用

international conference on Informatics and computing (ICIC)

作者： Muhammad Naufal Fikriansyah Hapsoro Agung Nugroho Marzuki Sinambela MCG Instrumentation Study Program State Collage of Meteorology Climatology and Geophysics South Tangerang Indonesia

ISBN: (纸本)9798350345728

Clouds are one of the most important parameters in doing weather observations. Meteorologist and atmospheric experts are able to determine short-term and long-term weather conditions by observing atmospheric parameters, one of which is cloud types. The goal of this research is to develop a system which is able to recognize cloud patterns through imagery to determine the types so that the subjective factor in cloud observations can be decreased and help observers to observe cloud types more easily. This system was built by implementing the Python programming language and one of the deep learning models, named as Convolutional Neural Network (CNN). The data used in the system are low cloud image data which are divided into 5 (five) classes, namely Cumulunimbus, Cumulus, Stratus, Stratocumulus, and Nombostratus. The result shows that the accuracy achieved the number of 92.22% in the training process with the total loss of 0.20%.

关键词： Training Clouds Observers Libraries Classification algorithms pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

5th international conference on Intelligent computing and Applications, ICICA 2019

5th International Conference on Intelligent Computing and Ap...

引用

5th international conference on Intelligent computing and Applications, ICICA 2019

ISBN: (纸本)9789811555657

The proceedings contain 71 papers. The special focus in this conference is on Intelligent computing and Applications. The topics include: Performance Estimation and Analysis Over the Supervised Learning Approaches for Motor Imagery EEG Signals Classification;fully Automated Digital Mammogram Segmentation;empirical Study of Computational Intelligence Approaches for the Early Detection of Autism Spectrum Disorder;Intelligent Monitoring of Bearings Using Node MCU Module;image Denoising Using Various Image Enhancement Techniques;energy Consumption Analysis and Proposed Power-Aware Scheduling Algorithm in Cloud computing;relationship Between Community Structure and Clustering Coefficient;digital Image Forensics-Image Verification Techniques;energy Efficient Data Centre Selection Using Service Broker Policy;using Automated Predictive Analytics in an Online Shopping Ecosystem;design and Development of Home Automation System;performance Analysis Study of Stochastic computing Based Neuron;Scheduling of Parallel Tasks in Cloud Environment Using DAG MODEL;GREENIE—Smart Home with Smart Power Transmission;ANAVI: Advanced Navigation Assistance for Visually Impaired;THIRD EYE—Shopfloor Data Processing and Visualization Using Image recognition;A Hybrid Search Group Algorithm and pattern Search Optimized PIDA Controller for Automatic Generation Control of Interconnected Power System;Fractional Order PID Controlled PV Fed Quadratic Boost Converter TZ Source Inverter Fed Permanent Magnet Brushless Motor Drive;co-ordinate Measurement of Roll-Cage Using Digital Image Processing;peformance Analysis of Joysticks Used in Infotainment Control System in Automobiles;Probabilistic Principal Component Analysis (PPCA) Based Dimensionality Reduction and Deep Learning for Cancer Classification;blockchain Technology for Data Sharing in Decentralized Storage System;Understanding Concepts of Blockchain Technology for Building the DApps;chennai Water Crisis—Data Analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying traffic of same keys in cryptographic communications using fuzzy decision criteria and bit-plane measures

引用

international JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2020年第2期11卷 466-480页

作者： Arvind Ratan, Ram Univ Delhi Hansraj Coll Delhi India Def Res & Dev Org Sci Anal Grp Delhi India

The use of same keys for different messages is not safe in cryptography to secure cryptographic communications even if encryption algorithm is strong enough and possesses good cryptographic properties. Such communications can be analyzed to find meaningful information by cryptanalysts or adversaries. Use of same keys may happens if keys are not managed in cipher systems appropriately by customers. One should evaluate ciphers thoroughly and assure for non-repetition of keys prior to its usage for secure communications. The paper presents a methodology to identify and segregate traffic of cryptographic communications of images encrypted with same keys by exploiting bit-plane image characteristics and applying Fuzzy decision criteria. Results presented in the paper shows that the proposed Fuzzy classification method is able to identify images encrypted with same keys successfully and it seems very useful to consider for various pattern recognition and image analysis problems.

关键词： Bit-plane measures Classification Cryptography Fuzzy criteria pattern recognition Secure communication soft computing Traffic analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Crime pattern recognition: A Study of Crime Hot Spots and High-Risk Areas

Deep Learning for Crime Pattern Recognition: A Study of Crim...

引用

Recent Advances in Science and Engineering Technology (ICRASET), international conference on

作者： Rahul Harikumar A Tanay Grover M. Kanchana Department of Computing Technologies SRM Institute of Science & Technology Chennai India

Crime is a global problem that affects individuals, communities, and societies at large. There are many different types of crime, and the rates at which they occur vary widely from country to country. While the need to be able to detect crime as it is happening is a very important part of safety and security, systems that can predict and analyze crimes are just as vital to a safer world. Understanding crime patterns and trends is crucial for effectively addressing the issue. One way to gain insights into crime is through the use of crime data analysis systems. These systems can help law enforcement agencies, policymakers, and researchers to identify patterns and trends in crime, as well as evaluate the effectiveness of different crime-prevention strategies. In our research we used four distinguished approaches: eXtreme Gradient Boosting (XGBoost), CatBoost, Tabnet, and a hybrid model 1 Dimensional Convolution Neural Network through three individual datasets to compare the results of each approach as well as a comparison between the three datasets. Our results demonstrated a very significant advantage of utilizing feature oriented datasets over a large sample size such as the Chicago dataset. We observed XGBoost provides the best results for Chicago and San Francisco 96.51% and 26.50% respectively. And as for Boston, we obtained best accuracy (20.80%) using the Bagging classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Pediatric Pneumonia Diagnosis with Chest X-Ray using Deep Attention Mechanism

Enhanced Pediatric Pneumonia Diagnosis with Chest X-Ray usin...

引用

IEEE/ACM international Symposium on Big Data computing (BDC)

作者： Muhammad Zaman Tahseen Fatima Sana Hameed Shahzeb Haider Adnan Akhunzada Muhammad Azeem Faculty of Computer Science University of Lahore Sargodha Pakistan School of Engineering University of Saint Thomas Saint Paul MN USA Department of Data and Cybersecurity University of Doha for Science and Technology Doha Qatar

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

Development of deep learning technologies has resulted in a major revolution in the field of medical diagnostics in recent years. The purpose of this research is to examine the usage of Convolutional Neural Networks (CNNs) in combination with an integrated attention mechanism known as CoATNet to improve the accuracy and responsiveness of paediatric pneumonia diagnosis using chest X-ray analysis. The major goal of this research project is to build and verify a powerful deep learning model capable of detecting mild pneumonia symptoms in children’s chest X-rays. CoATNet’s innovative attention approach allows it to provide more weight to areas deemed to be extremely important. This is in addition to its ability to recognise major patterns in images. Furthermore, the paper considers the issues posed by class imbalances in medical imaging datasets and undertakes an in-depth assessment of how effectively CoATNet works across a large dataset of paediatric chest X-rays. CoATNet’s remarkable performance was shown by its ability to achieve a Micro Average of 98.2%, a Weighted Average of 98.7%, and an Accuracy of 99.7%. These measures show that the model can distinguish between instances of pneumonia and those do not have the illness, and that it is resilient when faced with class imbalances. F1 Score of 98.9% reflects a well-balanced trade-off between Precision 98.7% and Recall 98.2%. The integration of deep learning technologies with attention processes in CoATNet has resulted in a big step forward in the development of diagnostic models that are more visible and useful.

关键词： Deep learning Pediatrics Pneumonia Attention mechanisms Accuracy Sensitivity Predictive models pattern recognition X-ray imaging Medical diagnostic imaging

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：