检索结果-内蒙古大学图书馆

48th IEEE International conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Granger, Eric East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing China Shanghai Jiao Tong University School of Automation China Ets Lab. d'Imagerie de Vision et d'Intelligence Artificielle Dept. of Systems Eng. Canada

ISBN: (纸本)9781728163277

Given the recent advances with image-generating algorithms, deep image completion methods have made significant progress. However, state-of-art methods typically provide poor cross-scene generalization, and generated masked areas often contain blurry artifacts. Predictive filtering is a method for restoring images, which predicts the most effective kernels based on the input scene. Motivated by this approach, we address image completion as a filtering problem. Deep feature-level semantic filtering is introduced to fill in missing information, while preserving local structure and generating visually realistic content. In particular, a Dual-path Cooperative Filtering (DCF) model is proposed, where one path predicts dynamic kernels, and the other path extracts multi-level features by using Fast Fourier Convolution to yield semantically coherent reconstructions. Experiments on three challenging image completion datasets show that our proposed DCF outperforms state-of-art methods. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Lightweight DL-based Drone image Classification for Surveillance Applications 21

Lightweight DL-based Drone Image Classification for Surveill...

引用

21st International System-on-Chip Design conference, ISOCC 2024

作者： Yadav, Abhishek Fujita, Masahiro Kumar, Binod Indian Institute of Technology Jodhpur India University of Tokyo Japan

ISBN: (纸本)9798350377088

With the extensive use of surveillance-based systems in the present age, it is recommended to employ lightweight deep neural networks (DNNs) that not only have small silicon footprints and low latency but also provide enhanced security. In this paper, we incorporate a lightweight Attention-CNN algorithm on drones for image classification in smart city surveillance systems. By processing data directly on the drone, our approach significantly reduces the delay associated with data transmission to centralized servers, enhancing the effectiveness of surveillance operations. We ensure that our algorithms maintain high accuracy while operating within the constraints of the hardware resources. Additionally, we evaluate the resilience of these DL models against adversarial attacks, considering the security implications of deploying in real-life applications. To address the demands of latency-sensitive applications that require rapid analysis of high-resolution images, we also explore the implementation on a field-programmable gate array board. The experimental results show a maximum reduction factor of 9.56 in the memory size along with a 2.92% drop in the accuracy in the software implementation and the total power consumption on the ZCU104 FPGA board is 10 W. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

An Analysis of image Features Extracted by CNNs to Design Classification Models for COVID-19 and Non-COVID-19

引用

JOURNAL OF SIGNAL processing systems FOR SIGNAL image AND VIDEO TECHNOLOGY 2023年第2-3期95卷 101-113页

作者： Teodoro, Arthur A. M. Silva, Douglas H. Saadi, Muhammad Okey, Ogobuchi D. Rosa, Renata L. Al Otaibi, Sattam Rodriguez, Demostenes Z. Univ Fed Lavras Dept Comp Sci Lavras MG Brazil Univ Cent Punjab Dept Elect Engn Lahore 54000 Pakistan Univ Fed Lavras Dept Syst Engn & Automat Lavras MG Brazil Taif Univ Coll Engn Dept Elect Engn At Taif 21944 Saudi Arabia

The SARS-CoV-2 virus causes a respiratory disease in humans, known as COVID-19. The confirmatory diagnostic of this disease occurs through the real-time reverse transcription and polymerase chain reaction test (RT-qPCR). However, the period of obtaining the results limits the application of the mass test. Thus, chest X-ray computed tomography (CT) images are analyzed to help diagnose the disease. However, during an outbreak of a disease that causes respiratory problems, radiologists may be overwhelmed with analyzing medical images. In the literature, some studies used feature extraction techniques based on CNNs, with classification models to identify COVID-19 and non-COVID-19. This work compare the performance of applying pre-trained CNNs in conjunction with classification methods based on machine learning algorithms. The main objective is to analyze the impact of the features extracted by CNNs, in the construction of models to classify COVID-19 and non-COVID-19. A SARS-CoV-2 CT data-set is used in experimental tests. The CNNs implemented are visual geometry group (VGG-16 and VGG-19), inception V3 (iv3), and EfficientNet-B0 (EB0). The classification methods were k-nearest neighbor (KNN), support vector machine (SVM), and explainable deep neural networks (xDNN). In the experiments, the best results were obtained by the EfficientNet model used to extract data and the SVM with an RBF kernel. This approach achieved an average performance of 0.9856 in the precision macro, 0.9853 in the sensitivity macro, 0.9853 in the specificity macro, and 0.9853 in the F1 score macro.

关键词： COVID-19 non-COVID-19 Computed tomography images Transfer learning Convolutional neural networks Machine learning

来源：评论

学校读者我要写书评

暂无评论

Detection and Correction of image Distortions Induced by Parasitic Light Sensitivity using Deep Learning Methods 15

Detection and Correction of Image Distortions Induced by Par...

引用

15th International conference on Machine Vision (ICMV)

作者： Azmi, Sara Esam Bartels, Chris Hussnain, Zille Guelen, J. A. P. Bondarev, Egor Eindhoven Univ Technol VCA Grp Eindhoven Netherlands Cyclomedia BV Zaltbommel Netherlands

ISBN: (纸本)9781510666184;9781510666191

images captured by mobile camera systems are subject to distortions that can be irreversible. Sources of these distortions vary and can be attributed to sensor imperfections, lens defects, or shutter inefficiency. One form of image distortion is associated with high Parasitic-Light-Sensitivity (PLS) in CMOS image Sensors when combined with Global Shutters (GS-CIS) in a moving camera system. The resulting distortion appears as widespread semi-transparent purple artifacts, or a complex purple fringe, covering a large area in the scene around high-intensity regions. Most of the earlier approaches addressing the purple fringing problems have been directed towards the simplest forms of this distortion and rely on heuristic image processing algorithms. Recently, machine learning methods have shown remarkable success in many image restoration and object detection problems. Nevertheless, they have not been applied for the complex purple fringing detection or correction. In this paper, we present our exploration and deployment of deep learning algorithms in a pipeline for the detection and correction of the purple fringing induced by high-PLS GS-CIS sensors. Experiments show that the proposed methods outperform state-of-the-art approaches for both problems of detection and color restoration. We achieve a final MS-SSIM of 0.966 on synthetic data, and a distortion classification accuracy of 96.97%. We further discuss the limitations and possible improvements over the proposed methods.

关键词： purple fringing deep learning image restoration image distortion distortion correction PLS factor synthetic data generation

来源：评论

学校读者我要写书评

暂无评论

Identification of Salt Applying image processing and Machine Learning Techniques 15

Identification of Salt Applying Image Processing and Machine...

引用

15th IEEE International conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management, HNICEM 2023

作者： Cadorna, Jerome Francis G. Cervantes, John Patrick M. iv, Carlos C. Hortinela Fausto, Janette C. School of Electrical Electronics and Computer Engineering Mapúa University 658 Muralla St. Intramuros Manila Philippines

ISBN: (纸本)9798350381177

Salt is essential today due to its numerous applications in food, healthcare, and other industries. Several varieties of salt are available on the market, and each has distinct physical features that are recognized based on its size, shape, color, and texture. Despite these claims, a system that could distinguish salt is still non-existent. Furthermore, carrying out this study could provide solution to the salt industry's need for more technology and innovation. In addition, using image processing and machine learning techniques, this study created a system to identify five distinct types of salt: Pink Himalayan, Black Himalayan, Black Lava, Kosher, and Sea salts. The researchers utilized different image processing algorithms such as the K-means, CLAHE, Grayscale, Gaussian Blur, Dilation, Morphology, and Erosion to enhance salt images. The Canny Edge Detection (CED) was utilized for feature extraction, while the SVM was used to identify five distinct kinds of salt. The system developed is implemented using a Raspberry Pi 4 microcontroller for hardware development. The researchers also used a microscopic camera to capture salt samples. Overall, the researchers obtained an accuracy of 96.218% while implementing the algorithm. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Secure image Retrieval in an Untrusted Cloud Environment 4th

Secure Image Retrieval in an Untrusted Cloud Environment

引用

4th International conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Prakash, Vijay Khandelwal, Kavya Gupta, Disha Garg, Lalit University of Malta Msida Malta School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Computer Science & Engineering Graphics Era Hill University Dehradun India

ISBN: (纸本)9789819994410

image processing in the scrambled area has received increasing attention for its many anticipated uses, such as providing efficient and safe solutions for protection-saving applications in untrustworthy environments. The high degree of ciphertext development caused by the existing homomorphic encryptions is one barrier to the widespread use of these algorithms. This paper considers the problem of managing images in scrambled space. We develop an image encryption scheme that limits ciphertext expansion while preserving the homomorphic characteristic using image design elements. The proposed encryption scheme first uses a probabilistic homomorphic cryptosystem to jumble the image’s pixels, then packs the complete scrambled image to conserve space. Our approach offers a significantly lower ciphertext development factor while maintaining the homomorphic characteristic than the component-wise encryption scheme. It is unnecessary to demand additional intuitive norms when using secure sign-handling tools on the compressed encoded image. We provide a rapid calculation for the encryption and pressure of the proposed image encryption plot, which expedites the computation and significantly increases the effectiveness of our strategy. The security, ciphertext extension percentage, and computing complexity are also being examined. Our validation and testing approach shows that the proposed computations are valid. The proposed algorithms for image encryption make sense as an image encryption scheme for safe picture management applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Advances in Artificial Intelligence, Big Data and algorithms - Proceedings of the 3rd International conference on Artificial Intelligence, Big Data and algorithms, CAIBDA 2023

Advances in Artificial Intelligence, Big Data and Algorithms...

引用

3rd International conference on Artificial Intelligence, Big Data and algorithms, CAIBDA 2023

ISBN: (纸本)9781643684444

The proceedings contain 149 papers. The topics discussed include: effects of AI on smart agriculture: a case study of digital agriculture base;image retrieval-based product identification for automatic checkout systems;application of lightweight emotion recognition model in intelligent construction site monitoring;research on the application of smart wearable in the emotional management of the elderly;artificial intelligence technology in the field of broadcasting and hosting;intelligent inspection method for photovoltaic modules based on image processing and deep learning;application of AI algorithms in power system load forecasting under the new situation;research on the intelligent operation and maintenance control system of power distribution network based on big data technology;research progress of intelligent rail transit train control system;and design and implementation of intelligent potted plant management system based on Internet of Things.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preserving Legacies, Pioneering Frontiers: Multi-Sensor image Fusion, from Medieval Manuscripts to UAS-based Sensing 30

Preserving Legacies, Pioneering Frontiers: Multi-Sensor Imag...

引用

conference on algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXX

作者： Hassanzadeh, Amirhossein Macalintal, Jose N. G. M. Messinger, David Rochester Inst Technol Rochester NY 14623 USA

ISBN: (纸本)9781510673816;9781510673809

Data fusion, which involves integrating data from multiple sources, is increasingly valuable across various fields due to its ability to enhance information quality, accuracy, and reliability. This process enables a more comprehensive understanding of complex phenomena by merging diverse datasets, providing insights that are otherwise unattainable. In the realm of remote sensing, where precise data acquisition is critical, fusion techniques have become indispensable, benefiting applications such as object detection, classification, and change detection. While much emphasis has been placed on spatial sharpening techniques in published studies, there remains a notable gap in establishing robust workflows for both lab-based and UAS-based remote sensing data fusion, particularly in the near-infrared (VNIR) and short-wave infrared (SWIR) regions. This study aims to investigate VNIR-SWIR fusion using data sourced from a medieval manuscript in a controlled laboratory environment and from UAS-based sensors in a real-world setting, addressing differences in system parameters and processing workflows. Despite challenges such as image registration issues, our analysis has yielded promising results, underscoring the importance of ongoing refinement in fusion methodologies to ensure comprehensive data interpretation and analysis across diverse datasets and environments.

关键词： data fusion visible to near infrared (VNIR) shortwave infrared (SWIR) Unamnned Aerial systems (UAS)

来源：评论

学校读者我要写书评

暂无评论

Acceleration of image processing algorithms based on a Single Board Computer and FPGA co-design 11

Acceleration of image processing algorithms based on a Singl...

引用

11th International conference on Modern Circuits and systems Technologies (MOCAST)

作者： Kokotis, Petros Vourvoulakis, John Int Hellen Univ Dept Comp Informat & Telecommun Engn Serres Greece

ISBN: (数字)9781665467179

ISBN: (纸本)9781665467179

During recent years, various hardware platforms were developed, each one suitable for use in different kind of applications. Platforms based on FPGAs, DSPs, GPUs, Single Board Computers, microcontrollers extend processing capabilities and functionality in comparison with traditional personal computers based on a single CPU. Furthermore, co-design combines advantages from different types of processing units, rendering such architectures more attractive to researchers. In this paper, we achieve acceleration of image processing algorithms using a hardware platform based on a Raspberry Pi Single Board Computer and a custom designed FPGA HAT (Hardware Attached on Top) for RPi. The FPGA HAT consists of a Cyclone 10LP device The FPGA undertakes a computationally demanding load such as robotic vision algorithms exploiting parallelism, while the RPi can apply higher level operations such as running ROS (Robot Operating System). In order to overcome bottleneck in exchanging data between RPi and FPGA, a 16-bit parallel customized protocol was developed from scratch. The achieved transfer rate was about 50 Mbytes/sec when multi threaded software was implemented for the RPi. An image edge detector was implemented in order to verify the system performance. When only the RPi was used the processing rate was 48fps for images with resolution 512x512 pixels. RPi and FPGA co-design achieved processing rate 170fps for the same resolution images, which means an acceleration of about 350%. The proposed system was also evaluated in terms of power consumption.

关键词： fpga accelerator raspberry pi

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis for Trichoscopy and Trichogram Using Deep Learning and image processing—A Survey 8th

Performance Analysis for Trichoscopy and Trichogram Using De...

引用

8th International conference on Information and Communication Technology for Competitive Strategies, ICTCS 2023

作者： Jain, Divyanshu Masurkar, Purva Kakde, Shreyash Khot, Mohammed Siddique Waghmare, Aditya Gohil, Unnati Pawar, Rahul Patel, Dhananjay Patil, Pradeep Vidyalankar Institute of Technology Wadala Mumbai India Srihtvak Skin Hair Laser STD Leprosy Pharma and Wellness Center Baner Pune India

ISBN: (纸本)9789819994854

Hair-related diseases are pervasive and can significantly impact individuals’ confidence and emotional well-being. Accurate diagnosis of these conditions poses challenges even for experienced professionals. However, the integration of technology, particularly deep learning and artificial intelligence (AI), has been showing bright results in the field of Trichology. This paper presents a comprehensive review of the techniques and technologies developed in Trichology. We begin by delineating common hair diseases, trichoscopy image acquisition methods, and available datasets. We also examine existing frameworks and tools that facilitate the creation of trichoscopy-based algorithms, along with frequently used evaluation metrics. The techniques studied in this paper involve hair loss detection using Mask R-CNN, Kaggle network, DEX-IMDB-WIKI and DEX-ChaLearn networks, deep learning-based scalp image analysis using limited data through ResNet, ResNeXt, DenseNet, and XceptionNet, image processing using grid line selection method, machine learning using SVN and KNN, and hair and scalp disease recognition using deep learning and image processing. The different algorithms used in all the mentioned techniques are analyzed, giving us a brief knowledge of how Trichology is applied with the help of technology to benefit professionals in accurately diagnosing different hair loss parameters and diseases. This review offers an overview of recent advancements in hair disease diagnosis using trichoscopy and Trichogram, emphasizing opportunities for further enhancement in this rapidly evolving field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

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：