检索结果-内蒙古大学图书馆

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

作者： M varshana Devi K A Jai Surya E Meethashree v S Keerthivasan S Saraswathy Computer Science and Engineering K. S. Rangasamy College of Technology Tiruchengode India Computer Science and Business Systems Sri Sai Ram Engineering College Chennai India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

This research presents a novel method for monitoring attendance by creating an online system that combines facial recognition technology with machine learning algorithms to detect masks. The main objective of this project is to provide a streamlined attendance management system that can be accessed through web browsers, removing the requirement for the installation of specialised software. The technology utilises facial biometrics to identify users, storing profiles with facial picture samples in a centralised online database. Before implementing facial recognition, the system goes through a model training phase where Support vector Machines (SvM) are used to create a strong recognition model. Moreover, synthetic data is utilised to train the algorithm in recognising individuals who are wearing facial masks. The server-side application is developed using Python and utilises the OpenCv library for image processing. The web interfaces are managed through PHP, while the database is handled using MySQL. The combination of Python and PHP scripting enables immediate processing on web servers, guaranteeing availability from any device through a web browser. The experimental findings indicate that the face recognition system achieved an accuracy rate of around $81.8 \%$, while the mask detection system achieved an accuracy rate of $80 \%$. These results were obtained using a pre-trained model. In summary, this system provides a whole solution for effective and safe online attendance management in many fields.

关键词： Support vector machines Training Accuracy Databases Face recognition Biological system modeling Web servers

来源：评论

学校读者我要写书评

暂无评论

Double Stochastic Filtration of Spatially Inhomogeneous images

引用

JOURNAL OF COMMUNICATIONS TECHNOLOGY AND ELECTRONICS 2020年第5期65卷 524-531页

作者： vasiliev, K. K. Dementyev, v. E. Ulyanovsk State Tech Univ Ulyanovsk 432027 Russia

The representation of spatially inhomogeneous images using double stochastic autoregressive models is considered. The possibility of synthesizing semicausal double stochastic image filtering algorithms based on such models is shown. variants for reducing the computational costs required to implement double stochastic filters using cascades of moving windows are considered. A comparative analysis of the proposed algorithms with well-known counterparts is carried out, confirming the practical possibility of using double stochastic filters for processing real two-dimensional images.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Estimating the measurement error of the coordinates of markers on images recorded with a stereoscopic system

引用

JOURNAL OF OPTICAL TECHNOLOGY 2020年第5期87卷 266-275页

作者： Gorevoi, A., v Kolyuchkin, v. Ya Machikhin, A. S. Russian Acad Sci Sci & Technol Ctr Unique Instrumentat Moscow Russia NE Bauman Moscow State Tech Univ Moscow Russia Natl Res Univ MEI Moscow Russia

This paper proposes a method of estimating the error of measuring the coordinates of markers (corners of cells) on images recorded by a stereoscopic system. This problem needs to be solved in order to determine the error of the three-dimensional geometrical measurements made with such systems. At the design stage, the method is applied to segments of an image synthesized on the basis of the aberrational characteristics of the optical system. At the operating stage, the method is supplemented by an estimate of the parameters describing the noise on the recorded images. The efficiency of t he proposed approach is confirmed by computer simulation and experiments. The results of this paper make it possible to connect the design of the optical system and the development of data-processing algorithms into a single procedure when stereoscopic measurement devices are being created, as well as to estimate the errors of three-dimensional geometrical measurements when these devices are being operated. (C) 2020 Optical Society of America

关键词： Computer simulation image processing image quality Imaging noise Segmentation Three dimensional measurement

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection Mammogram imagesusing Convolution Neural Network

Breast Cancer Detection Mammogram Imagesusing Convolution Ne...

引用

Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF), International Conference on

作者： Swetha v G. vadivu SRM Institute of Science and Technology Kattankulathur

One in eight women globally develop breast cancer. By identifying the cancer of the breast tissue cells, it is *** various algorithms and methodologies, modern medical image processing systems examine histopathology images that have been recorded by a *** imaging and pathology tools are being processed using machine learning ***-aided methods are used to achieve better outcomes than manual pathological detection systems since manually identifying a cancer cell is a laborious operation and entails human mistake. Transfer learning and fine-tuning can also be used to get the most out of a CNN that has already been trained. The first is to develop simple models or adapt existing ones to reduce the time investment and the number of training *** deep learning, this is typically accomplished by first extracting features with the assistance of a convolutional neural network (CNN), and then categorizing data with the assistance of a fully connected network. The field of medical imaging makes extensive use of the technique of deep learning because it does not necessitate prior knowledge in a field that is related to it. Within the scope of this investigation, we trained a convolutional neural network to generate forecasts that had an accuracy of up to 88.86%.

关键词： Deep learning Machine learning algorithms Cross-site scripting Neurons Transfer learning Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Realtime Detection of Humps and Potholes

Realtime Detection of Humps and Potholes

引用

Smart systems for applications in Electrical Sciences (ICSSES), International Conference on

作者： Tejas B S v Pavan Rohith H Pranam J veena N. Hegde Dept. Of Electronics and Instrumentation Engineering BMS College of Engineering Bengaluru India

Hump and pothole detection is essential for ensuring road safety and preventing damage to vehicles. In recent years, there has been a growing interest in developing automated methods for hump and pothole detection. This paper presents the detection of humps and potholes using techniques of image processing, machine learning and sensor-based approach. The proposed method involves the use of cameras and sensors to collect data on road conditions, analyze the data and identify areas with humps or potholes. Machine learning algorithms are applied learn to recognize patterns in the data and make accurate predictions. The solution provided is robust with an accuracy of 90% approximately in achieving the objective under different lighting and weather conditions. The proposed solution is implemented in real time and tested for different conditions. The analysis is carried out in terms of improved road safety and reduced maintenance costs using the proposed solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for the Diagnosis of Photovoltaic systems Using Thermography : Inteligencia Artificial para el Diagnóstico de Sistemas Fotovoltaicos mediante Termografías

Artificial Intelligence for the Diagnosis of Photovoltaic Sy...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), v Congreso Internacional en

作者： Pincay-Lozada Jorge Luis Jimenez-Castillo Gabino Mulcue-Nieto Luis Fernando Lopez-Sotelo Jesus Alfonso Muñoz-Rodriguez Francisco Departamento CyTI Universidad de San Buenaventura Universidad de Jaén Universidad Autónoma de Occidente Cali Colombia Departamento de Ingeniería Electrónica y Automática Universidad de Jaén Jaén España Departamento de Física y Matemática Universidad de Manizales Manizales Colombia Departamento de Automática y Electrónica Universidad Autónoma de Occidente Cali Colombia José Ingeniería Electrónica y Automática Universidad de Jaén Jaén Colombia

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

This predoctoral research project is carried out in the framework of an international co-tutelage between the University of Jaén and the Universidad Autónoma de Occidente in Cali, Colombia with the participation of the CyTI Department of the Universidad de San Buenaventura. Its main objective is to systematize the processes of maintenance and diagnosis of modules in Photovoltaic systems (PvS) using computational tools based on Artificial Intelligence (AI). The project seeks to reduce operating costs, minimize human errors and detect possible failures early, in order to extend the operating hours of the Pv systems and reduce the time spent on preventive maintenance. To achieve these objectives, deep learning algorithms are used in infrared (IR) image processing. These algorithms make it possible to evaluate the state of the photovoltaic modules by analyzing variations in surface temperatures, detecting anomalous situations and failures in each photovoltaic (Pv) collector module. The implementation of these techniques will contribute to the development of effective methodologies that will significantly improve Pv maintenance. This advance represents significant progress in the efficiency and sustainability of solar photovoltaic energy, with applications of great relevance in both the scientific and technological *** proyecto de investigación predoctoral se lleva a cabo en el marco de una cotutela internacional entre la Universidad de Jaén y la Universidad Autónoma de Occidente en Cali, Colombia con la participación del Departamento de CyTI de la Universidad de San Buenaventura. Su objetivo principal es sistematizar los procesos de mantenimiento y diagnóstico de módulos en Sistemas Fotovoltaicos (SFv) mediante el uso de herramientas computacionales basadas en Inteligencia Artificial (IA). El proyecto busca reducir costos operativos, minimizar errores humanos y detectar tempranamente posibles fallos, con el fin de prolongar las horas de funcionamiento de los SFv

关键词： Deep learning image processing Infrared imaging Software Maintenance Solar panels Artificial intelligence Sustainable development Surface treatment Preventive maintenance

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Disease Detection Using EfficientNet Asynchronous Propagation Penalized Neural Network with Planet Optimization Algorithm

Plant Leaf Disease Detection Using EfficientNet Asynchronous...

引用

Machine Learning and Autonomous systems (ICMLAS), International Conference on

作者： G. Sasikala Suneetha Rikhari Sadhana R Gavali v. S G. Indra Mamatha N. P Department of Mathematics SRM Valliammai Engineering College Kattankulathur Chennai Tamil Nadu India Department of Computer Science and Engineering Malla Reddy University Hyderabad Telangana India Department of Computer Science and Engineering Sri Sairam College of Engineering Bengaluru Karnataka India Department of Artificial Intelligence and Machine Learning New Institute of Technology Kolhapur Maharashtra India Department of Computer Science and Engineering R M K College of Engineering and Technology Pudhuvoyal Tamil Nadu India Department of Electronics and Communication Engineering Brindavan College of Engineering Bangalore Karnataka India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Unpredictability in illumination conditions, similar illness symptoms, skewed datasets, processing expense, and the challenge of determining infections at their onset are some of the challenges in plant leaf disease diagnosis. Model accuracy, reliability, and generalization across different types of plant species are also influenced by environmental factors, occlusions, and image noise. Using Plantvillage database, this paper confirms the superiority of the EfficientNet Asynchronous Propagation Penalized Neural Network with Planet Optimization Algorithm (ENet-APPNNet-POA) in plant leaf disease detection. image quality is initially enhanced by the Adaptive Tri-Plateau Limit Tri-Histogram Algorithm (ATP-LTH) approach. ENet-UNet (EfficientNet-based U-Net) divides the affected areas of plant leaves according to distinct regions. Asynchronous Propagation Penalized Neural Network (APPNNet) serves as the classifier responsible for extracting features before performing their category identification. The Planet Optimization Algorithm (POA) delivers improved results and accuracy in classifying plant leaf diseases by evaluating various classifications affecting different leaf areas. Plantvillage dataset is employed in the Python test script. Test results indicate that ENet-APPNNet-POA outperforms existing methods to detect plant leaf disease classes at 99.9% efficiency and 99.8% sensitivity, an indication that computerized systems are likely to supersede manual diagnosis.

关键词： Accuracy Sensitivity Planets Neural networks Noise Manuals Classification algorithms Reliability Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

Determining Optimal Frame processing Strategies for Real-Time Document Recognition systems 16th

Determining Optimal Frame Processing Strategies for Real-Tim...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Bulatov, Konstantin Arlazarov, vladimir v. Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia Smart Engines Serv LLC Moscow Russia

ISBN: (纸本)9783030863319

Mobile document analysis technologies became widespread and important, and growing reliance on the performance of critical processes, such as identity document data extraction and verification, lead to increasing speed and accuracy requirements. Camera-based documents recognition on mobile devices using video stream allows to achieve higher accuracy, however in real time systems the actual time of individual image processing needs to be taken into account, which it rarely is in the works on this subject. In this paper, a model of real-time document recognition system is described, and three frame processing strategies are evaluated, each consisting of a per-frame recognition results combination method and a dynamic stopping rule. The experimental evaluation shows that while full combination of all input results is preferable if the frame recognition time is comparable with frame acquisition time, the selection of one best frame based on an input quality predictor, or a combination of several best frames, with the corresponding stopping rule, allows to achieve higher mean recognition results accuracy if the cost of recognizing a frame is significantly higher than skipping it.

关键词： Mobile recognition Real-time recognition video stream Anytime algorithms Document recognition

来源：评论

学校读者我要写书评

暂无评论

Robotic Manipulator Software and Hardware Development Using Recognition algorithms

Robotic Manipulator Software and Hardware Development Using ...

引用

IEEE NW Russia Young Researchers in Electrical and Electronic Engineering Conference (EIConRusNW)

作者： Grigoriy S. Borovkov Karina v. Martirosyan Yakov A. Protasov Department of “System Analysis and Control” Saint Petersburg Mining University Saint Petersburg Russia Control Systems and Information Technologies Department North-Caucasus Federal University branch in Pyatigorsk Pyatigorsk Russia

The enterprises digitalization determines the development trends of the industrial sector. There is a need to reduce the percent of human participation in processes associated with conveyor production, which requires the high-tech solutions integration. Due to the lack of quality control on the assembly line, enterprises produce a large percentage of defective products. The article discusses a possible solution to the problem of image processing for monitoring defects in products moving along a conveyor belt. The use of neural network technologies allows us to identify defects in production in real time, and the use of a robotic arm allows us to immediately remove such products from the assembly line. As a result of the research, it is planned to implement a software and hardware complex of a robotic manipulator using computer vision technologies that can distinguish objects and mechanically influence them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Light Control System Using image processing

Smart Traffic Light Control System Using Image Processing

引用

Augmented Intelligence and Sustainable systems (ICAISS), International Conference on

作者： Asha S.M Banu Soundarya A S Lakchida v S Shanthini S L Stinsha Dept of ECE Sri Krishna College of Engineering and Technology

ISBN: (纸本)9781665489638

Crossing the road is one of the major problems, due to the increase of fast-moving vehicles on the road. The challenges in the existing techniques utilized for traffic control can be overcome by using the Smart Traffic Light Control System using image processing, proposed in this paper and allowing pedestrians to walk on busy roads conveniently. It is found that the Canny Edge Detection Technique is a very effective method among the various edge detection algorithms. The suggested method reduces the waiting time in zebra crossing by immediately controlling the traffic light and gives more time for elderly and handicapped pedestrians to cross the roads safely even during heavy traffic. When compared to all the traditional techniques, image processing is an efficient method for traffic control. This technique removes the usage of unwanted hardware like sensors which are used to sense noises. This prevents the wastage of time for vehicles which is more essential for emergency vehicles. The output of the code is obtained by image matching. The results are shown in three scenarios: less traffic, moderate traffic, and more traffic.

关键词： Codes Roads image processing image edge detection image matching Process control Traffic control

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：