检索结果-内蒙古大学图书馆

1st International Conference on Recent Developments in Electronics and Communication systems, RDECS 2022

作者： Devi, Terli v. Satyanarayana, v. Singh, Mahesh K. Department of ECE Aditya Engineering College Surampalem India Department of ECE Aditya Engineering College A.P. Surampalem India

ISBN: (纸本)9781643683607

Automatic License Plate Recognition (ALPR) is an embedded real-time technology that automatically recognizes a vehicle's license plate. There are numerous uses, ranging from complex security to shared spaces, parking to acceleration. The ALPR is used to control the traffic and to take hold for those who violate the traffic rules. Automatic recognition of vehicle license plate numbers has become critical in our daily lives due to the rapid expansion of autos and transportation systems, which makes it difficult for the general public to keep up with and monitor. A license plate identification system uses image processing theory and soft computing technology to identify cars based on their number plates. Using fewer and simpler algorithms can reduce both calculation time and execution time needed by most number plate localization approaches. This is because most of these techniques require several operations. License plate recognition is the most used approach in traffic-related applications. various approaches, tactics, and algorithms have been developed for the identification and recognition of license plates. In the context of Indian license plate identification, only a few research have looked at the topic. Character segmentation and character recognition are two of the three key steps in identifying a license plate. © 2023 The authors and IOS Press.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

FPGA-based methods for high-speed processing of video images with large brightness scatter

Applied Physics

引用

Applied Physics 2022年第1期 34-41页

作者： Sorokin, D.v. Dragunov, D.E. Lyapustin, M.Y. Semenchenko, N.A. Sharganov, K.A. Orion R&P Association JSC 9 Kosinskaya str. Moscow111538 Russia FSBI «RF MD MHC» 13 Komarova st.Mytischi region Moscow141006 Russia

The task of detecting and identifying low contrast objects by thermal imaging optoelectronic systems in a scene with a large dynamic range requires the use of special brightness conversion algorithms. However, the most popular and high-quality methods, such as Digital Detail Enhancement (DDE), introduce large frame delays and require significant hardware resources. This article presents a review of dynamic range enhancement algorithms, among which algorithms that do not require a large number of FPGA logic elements and allow for minimal frame delay. Based on them, developed mathematical models of gradational transformation of brightness, which can detect low-contrast details of the image. The results of their implementation on FPGA as a part of domestic optoelectronic module are given. © 2022 Federal Informational-Analytical Center of the Defense Industry. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Personalized Skincare Recommendations 3

AI-Driven Personalized Skincare Recommendations

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Perumal, Iyyanar Kalaivani, P. Naveenkumar, A. Saran, v. Sriram, K. Suruthi, N. Sona College of Technology Department of Information Technology Salem India Kongu Engineering College Department of Cse Perundurai India

ISBN: (纸本)9798331509675

This study investigates the utilization of artificial intelligence (AI) to transform skincare product recommendations and the formulation of individualized routines through the analysis of user inputs and characteristics. The system utilizes data including skin type, acne count, oiliness level, and Uv exposure, using KNearest Neighbors (KNN) for personalized product suggestions. Natural Language processing (NLP) approaches are utilized to develop tailored 7-day skincare regimen recommendations by examining product and user problems, converting unstructured data into actionable insights. Moreover, deep learning algorithms are employed for real-time image-based assessments of skin conditions, facilitating precise acne diagnosis and oiliness evaluation. The system integrates visual data with textual analysis, continually adapting through user feedback to improve accuracy and relevance. This article highlights the capacity of AI-driven methods to automate routine generation and provide tailored product recommendations, fostering innovation in the cosmetics sector through a thorough, data-oriented strategy. © 2025 IEEE.

关键词： k-nearest neighbors

来源：评论

学校读者我要写书评

暂无评论

Enhanced Camouflage Detection Using Advanced image processing Techniques for Real-Time Object Recognition and Pattern Differentiation 5

Enhanced Camouflage Detection Using Advanced Image Processin...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Manikandan, G. Deepa, R. Jayalakshmi, v. Thilakavathy, P. Surendran, R. St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

The identification of objects that blend in with their surroundings has long been a concern in fields including defence, wildlife monitoring, and surveillance due to the difficulty of detecting such objects. This finding is significant because it could greatly enhance our capacity to detect camouflaged objects, transforming the field of real-time object detection. Existing image processing methods often fail miserably when adequately capturing this aspect. This dissertation's primary focus is identifying devices with complicated patterns, legacy interference, and inadequate contrast;nonetheless, in disguised scenarios, all of these features cause identification to be unsuccessful. This research often suggests a new approach called the Linear Edge Detecting Scheme for Camouflaged Object Detection (LEDS-COD) in these difficult cases. The LEDS-COD system can enhance item visibility in low-comparison settings by highlighting critical edges and descriptions. Pattern differentiation methodologies and modern facility-side recognition techniques are combined to accomplish this goal. The approach successfully differentiated items because it zeroed in on texture and comparative details that would otherwise go unnoticed by humans or advanced algorithms. LEDS-COD is useful in many areas, including the Navy, autonomous surveillance systems, and animal protection, where the real-time identification of hidden devices is essential. Results from a simulation study using various datasets, including concealed objects, show that LEDS-COD surpasses conventional detection methods in recognition accuracy, processing speed, and perseverance. The recommended technique exceeded the requirements for obtaining improved object detection estimates for challenging conditions like those with complex backdrops and changing illumination. According to this study, LEDS-COD can be devastating in improving real-time camouflage detection. © 2024 IEEE.

关键词： Accuracy image processing Surveillance image edge detection Wildlife Lighting Object detection Real-time systems Object recognition Protection

来源：评论

学校读者我要写书评

暂无评论

Development of Lane and Zebra Crossing Marker Detection algorithms

Development of Lane and Zebra Crossing Marker Detection Algo...

引用

2023 IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Chamoli, vivek Gowri, R. Dubey, v.P. Kandpal, Jyoti Joshi, Jyoti Kumar, Divesh Graphic Era Hill University Dept. of Electronics and Communication Engineering Dehradun India Graphic Era Hill University Dept. of Comupter Science and Engineering Dehradun India

ISBN: (纸本)9781665474924

This research involves using an object recognition system and an ancillary image sensor to detect lane markers and zebra crossings on a roadway in a vehicle. To perform this detection, these steps have been followed: take a picture of the scene, digitize it, normalize it, define a search area within it, look for lane and zebra markers within it. The Lane Tracking for Driving System was created to assist drivers in making lane departure decisions, to lessen concentration breaks, and to avoid accidents while driving. To offer a way to detect a specific traffic violation - namely, stopping on a zebra crossing at a traffic signal rather than following behind it - and to offer a workaround. In the proposed work, systems are implemented and improved using adaptive algorithms. MATLAB's image processing toolbox is used to design and implement the proposed algorithm. © 2023 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

A MobileUnet++-based Abnormality Segmentation and Multi-scale Network Approach for Brain Tumor Classification

A MobileUnet++-based Abnormality Segmentation and Multi-scal...

引用

2024 International Conference on Intelligent algorithms for Computational Intelligence systems, IACIS 2024

作者： Kumar, veesam Pavan Pattanaik, Satya Ranjan Kumar, v Sunil Dept of Computer Science and Engineering Rourkela India Dept of Computer Science and Engineering Bhubaneswar India Pbr Visvodaya Institute of Technology & Science Dept of Computer Science and Engineering Kavali India

ISBN: (纸本)9798350360660

Tumors are a pervasive concern in modern life, driven by cellular irregularities that disrupt the orderly division necessary for healthy cell growth. However, brain tumors present unique challenges compared to tumors in other regions due to the intricacies of brain structure and function. A brain tumor occurs when cells in the cerebral cortex undergo uncontrolled proliferation. Diagnosing brain tumors, especially in their early stages is a formidable task that often relies on manual examination of medical images by radiologists or healthcare professionals. Despite various approaches to brain tumor classification, precision remains paramount while ensuring practical utility in segmentation and classification tasks. Traditional methods are often manual, time-consuming and lacking in automated classification capabilities, hampering efficient decision-making. The advent of deep learning technology has revolutionized medical image processing, particularly in the realm of brain tumor analysis. Deep learning algorithms, powered by vast datasets and computational prowess, offer remarkable capabilities in automating segmentation and classification tasks, thereby enhancing accuracy and efficiency in diagnosing brain tumors. Consequently, this study introduces a method for smart brain tumor segmentation and classification leveraging deep learning techniques. The process begins with acquiring essential images through established benchmarking techniques. These images are then processed in the abnormality segmentation phase, utilizing Mobile-Unet++ (MUnet++) for segmentation. Following segmentation, the images undergo a classification phase, where brain tumors are classified using Multi-scale Mobilenet (MMNet). To validate effectiveness of proposed technique, an efficacy study is conducted, comparing it against traditional methodologies for segmentation and classification of brain. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Attention-Based Convolutional Neural Networks for Fresh-Cut Flower Classification

引用

IEEE ACCESS 2023年 11卷 17283-17293页

作者： Fei, Yeqi Li, Zhenye Zhu, Tingting Ni, Chao Nanjing Univ Sci Technol ZiJin Coll Sch Intelligent Mfg Nanjing 210046 Peoples R China Nanjing Forestry Univ Coll Mech & Elect Engn Nanjing 210037 Jiangsu Peoples R China

In the process of classifying fresh-cut flowers, the classification accuracy of the algorithm plays a vital role in the control of quality stability, uniformity, and price of fresh-cut flowers, while the classification speed of an algorithm determines the possibility of industrial application. Currently, research on fresh-cut flower classification focuses on the breakthrough of classification accuracy, ignoring the real-time processing speed of the terminal, which seriously affects the use of fresh-cut flower online classification technology. In this study, RGB images and depth information data of 434 rose flowers were collected using a binocular stereo depth camera. Combined with the actual production line classification environment, a set of data argumentation solutions was developed under the condition of limited samples. The architecture was established and optimized based on the ShuffleNet v2 network backbone unit, transfer learning was performed, and an appropriate attention mechanism was invoked to classify flowers of five specifications. The experimental results showed that the proposed network structure had a competitive advantage in terms of parameter quantity, classification speed, and accuracy compared with traditional networks without an attention mechanism and other lightweight networks. The classification accuracy on the 3-channel (RGB channel) flower dataset and the 4-channel (RGB and depth channel) flower datasets were 98.891% and 99.915%, respectively, and the overall prediction classification speed can reach 0.020 seconds per flower. Compared to the fresh-cut flower classification machines currently on the market, the speed of the proposed method has a great advantage. These advantages are of great significance for the design and development of fresh-cut flower classification and grading systems, and the proposed method is instructive for the identification and application of multichannel data in the future.

关键词： Feature extraction Production Classification algorithms image segmentation Plants Data visualization Computer architecture Fresh-cut flower grading lightweight network attention mechanism image augmentation model parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Abuse Reporting System 6

Abuse Reporting System

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational systems, RAICS 2024

作者： Sivadasan, Sreeram Mohamed Jisar, C. Rasmina Murshida Farsana, v. Shijaz, K. Mea Engineering College Department of Computer Science and Engineering India

ISBN: (数字)9798350381689

ISBN: (纸本)9798350381689

This project embarks on the development of an abuse reporting system designed to maintain user anonymity and employ advanced machine learning algorithms for genuineness assessment and fraud detection. In the contemporary digital landscape, safeguarding user privacy and ensuring the reliability of abuse reports are paramount. Our project addresses this challenge by integrating state-of-the-art machine learning techniques, enhancing the accuracy and efficiency of abuse reporting process, and mitigating false or malicious reporting. The technical underpinnings of the system involve the creation of a distributed, scalable, and fault-tolerant architecture capable of handling a wide range of abuse reports from diverse sources. We implement advanced natural language processing (NLP) models for textbased report analysis, while image and multimedia reports undergo deep learning-based content analysis. Anonymity preser-vation is achieved through advanced encryption techniques and decentralized data storage. Furthermore, we integrate adaptive machine learning algorithms that continuously evolve to detect novel abuse patterns and emerging fraud strategies, ensuring the system's adaptability to evolving threats. The project includes a comprehensive evaluation of the abuse reporting app's performance, precision, and scalability in handling a large volume of reports while preserving user anonymity. This project represents a significant advancement in the field of abuse reporting systems, offering a technologically robust and privacy-centric solution for contemporary society's increasing demand for secure and effective reporting mechanisms. © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Exploration of neural network approaches in tasks of the face liveness detection in biometrical video monitoring systems 10

Exploration of neural network approaches in tasks of the fac...

引用

Optoelectronic Imaging and Multimedia Technology X 2023

作者： Mudrich, A.B. Ezhova, K.v. Mazanov, I.A. ITMO University 49 Kronverksky av. St. Petersburg197101 Russia

ISBN: (纸本)9781510667839

One of the most actively developing areas of digital image processing algorithms and complex technical vision systems is security systems. The focus of this research is video surveillance systems with biometrical face recognition algorithms. Intelligent analysis of an object (visitor's face) in such a system can be divided into sequential stages - detection (band of the ROI on the image from video), recognition (comparison with a reference photo in a database), and additional functions (for example, tracking, emotion recognition, etc.). At the same time, the rapid development of image and video falsification technologies emphasized the need to protect the system from attempts to fake biometric data used for verification. The techniques of face spoofing include statistically and dynamic two- and three-dimensional attacks, attacks using doubles and avatars, and more. The methods of detecting spoofing are studied in the area of face liveness problems. Neural network architectures and libraries were used as the main methods during research. This research concentrated on the software development for biometrical video monitoring system, which is more secure against face spoofing attacks. For testing algorithms for detecting face liveness, a small real-time video surveillance system prototype consisting of several cameras and providing monitoring of one room was designed. One of the requirements for our system was the use of conventional 2D cameras. For this reason, face liveness detection methods that require the use of 3D cameras or additional sensors were excluded from the field of view at the stage of choosing research methods. This paper presents an analysis of existing approaches to identify face spoofing attacks and compares them with the neural networks-based approach. © 2023 SPIE. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Crop Selection and Yield Prediction using Machine Learning algorithms 2

Crop Selection and Yield Prediction using Machine Learning A...

引用

2nd International Conference on Augmented Intelligence and Sustainable systems, ICAISS 2023

作者： Kumar, J. Ashok Parimala, N. Pitchai, R. B v Raju Institute of Technology Narsapur India

ISBN: (纸本)9798350325799

Agriculture monitoring, particularly in developing nations, can assist prevent famine and aid human efforts. Estimating crop yields before harvest, often known as yield estimation, is difficult. Our technique predicts agricultural yields using publicly available remote sensing data in a scalable manner. Accurate, and economical manner. This strategy might assist all farmers use the least amount of fertilizer feasible, thereby maintaining soil health, while also giving them with the option to make the greatest money from the same piece of land through government-established soil health centers. As a result, it would be a win-win situation for all parties involved. This can be accomplished using machine learning algorithm KNN and image processing. Based on the results of the prediction analysis, machine learning algorithms are utilized to anticipate the best crop as well as the related bio-fertilizer. image processing could be utilized to further improve automated drones or tractors because it generates the shortest number of turns through the field. A predictive study is performed to recommend the top three most suitable crops based on soil nutrient levels, temperature, and possible revenue that this crop could generate. The outcomes can be applied in two ways. The first option is the automatic method, in which the farmer just selects their area and a suitable crop is selected based on prior experiments completed nearby. Second, you can manually enter soil information and get a crop recommendation based on the value you enter. © 2023 IEEE.

关键词： Crops

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

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

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：