检索结果-内蒙古大学图书馆

Algorithm Unrolling: Interpretable, Efficient deep learning for Signal and image processing

IEEE SIGNAL processing MAGAZINE 2021年第2期38卷 18-44页

作者： Monga, Vishal Li, Yuelong Eldar, Yonina C. Penn State Univ Sch Elect Engn University Pk PA 16802 USA Penn State Univ Elect Engn & Comp Sci Fac University Pk PA 16802 USA Amazon Lab 126 San Jose CA 94089 USA Weizmann Inst Sci Dept Math & Comp Sci IL-7610001 Rehovot Israel Weizmann Inst Sci Ctr Biomed Engn & Signal Proc IL-7610001 Rehovot Israel MIT Cambridge MA 02139 USA Broad Inst Cambridge MA USA Duke Univ Durham NC 27706 USA Israel Acad Sci & Humanities Jerusalem Israel

deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets. An emerging technique called algorithm unrolling, or unfolding, offers promise in eliminating these issues by providing a concrete and systematic connection between iterative algorithms that are widely used in signal processing and deep neural networks. Unrolling methods were first proposed to develop fast neural network approximations for sparse coding. More recently, this direction has attracted enormous attention, and it is rapidly growing in both theoretic investigations and practical applications. The increasing popularity of unrolled deep networks is due, in part, to their potential in developing efficient, high-performance (yet interpretable) network architectures from reasonably sized training sets.

关键词： Training data Systematics Neural networks Signal processing algorithms Performance gain Network architecture deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Dental Periapical Lesion Detection with Retinex image processing and an Efficient deep learning Model

Dental Periapical Lesion Detection with Retinex Image Proces...

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： C.A. Aslin Christo Julia Punitha Malar Dhas Deva Priya Computer Science and Engineering Karunya University Coimbatore India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Dental periapical lesions help doctors understand your oral health needs and must be found accurately to deliver proper treatment. The research introduces a new way to find dental periapical lesions by combining Retinex image processing with YOLOv8 object detection. The Retinex method lets the model detect periapical lesions more accurately because it enhances image details while removing picture noise. Test outcomes show enhanced lesion detection that performs well with precise accuracy in tough image scenarios. The research demonstrates how advanced image processing helps medical imaging deep learning systems work better. The Objective of this work is to improve visibility of periapical lesions by Retinex based enhancement and fast detection through YOLOv8.

关键词： deep learning Radiography Visualization Object detection real-time systems Skin Dentistry Lesions X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Using deep learning and Advanced image processing for the Automated Estimation of Tornado-Induced Treefall

引用

REMOTE SENSING 2024年第7期16卷 1130页

作者： Nasimi, Mitra Wood, Richard L. Univ Nebraska Dept Civil & Environm Engn Lincoln NE 68588 USA

Each year, numerous tornadoes occur in forested regions of the United States. Due to the substantial number of fallen trees and accessibility issues, many of these tornadoes remain poorly documented and evaluated. The process of documenting tree damage to assess tornado intensity is known as the treefall method, an established and reliable technique for estimating near-surface wind speed. Consequently, the demand for documenting fallen trees has increased in recent years. However, the treefall method proves to be extremely expensive and time-consuming, requiring a laborious assessment of each treefall instance. This research proposes a novel approach to evaluating treefall in large, forested regions using deep learning-based automated detection and advanced image processing techniques. The developed treefall method relies on high-resolution aerial imagery from a damaged forest and involves three main steps: (1) instance segmentation detection, (2) estimating tree taper and predicting fallen tree directions, and (3) obtaining subsampled treefall vector results indicating the predominant flow direction in geospatial coordinates. To demonstrate the method's effectiveness, the algorithm was applied to a tornado track rated EF-4, which occurred on 10 December 2021, cutting through the Land Between the Lakes National Recreation Area in Kentucky. Upon observation of the predicted results, the model is demonstrated to accurately predict the predominant treefall angles. This deep-learning-based treefall algorithm has the potential to speed up data processing and facilitate the application of treefall methods in tornado evaluation.

关键词： tornado damage treefall damage assessment deep learning aerial imagery

来源：评论

学校读者我要写书评

暂无评论

A mechatronics data collection, image processing, and deep learning platform for clinical posture analysis: a technical note

引用

PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE 2021年第3期44卷 901-910页

作者： Salahzadeh, Zahra Rezaei-Hachesu, Peyman Gheibi, Yousef Aghamali, Ali Pakzad, Hamed Foladlou, Saeideh Samad-Soltani, Taha Tabriz Univ Med Sci Fac Rehabil Physiotherapy Dept 29 Bahman St Tabriz Iran Tabriz Univ Med Sci Sch Management & Med Informat Dept Hlth Informat Technol Tabriz Iran Univ Tabriz Fac Comp Engn Dept Artificial Intelligence Tabriz Iran Sanam Sahand Hlth Promot Ind Dept Res & Dev Tabriz Iran Islamic Azad Univ Tabriz Dept Biomed Engn Tabriz Iran

Static and dynamic posture analysis was a critical clinical examination in physiotherapy and rehabilitation. It was a time-consuming task for clinicians, so a semi-automatic method can facilitate this process as well as provide well-documented medical records and strong infrastructure for deep learning scenarios. The current research presents a mechatronics platform for static and real-time dynamic posture analysis, which consisted of hybrid computational modules. Our study was a developmental and applied research according to a system development life cycle. The designed modules are as follows: (1) a mechanical structure includes patient place, 360-degree engine, mirror, laser, distance meter, and cams;(2) a software module includes data collection, electronic medical record, semi-automatic image analysis, annotation, and reporting, and (3) a network to exchange raw data with deep learning server. Patients were informed about the research by their healthcare provider and all data were transformed into a Fourier format, in which the patients remained autonomous without a bit of information. The results show acceptable reliability and validity of the instruments. Also, a telerehabilitation application was designed to cover the patients after diagnosis. We suggest a longer time for data acquisition. It will lead to a more accurate and fully automated dynamic posture analysis. The result of this study suggest that the designed mechatronics device used in conjunction with smartphone application is a valid tool that can be used to obtain reliable measurements.

关键词： Posture image processing Telerehabilitation Decision support system

来源：评论

学校读者我要写书评

暂无评论

License Plate reader with PUC Details using image processing and deep learning 2

License Plate reader with PUC Details using Image Processing...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Patil, R.S. Deshpande, Sakshi Khan, Hassan Mhatre, Prajakta Bharati Vidyapeeth College of Engineering Department of Electronics and Telecommunication Engineering Maharashtra Mumbai India

ISBN: (纸本)9798350348002

As each vehicle is uniquely acknowledged by its license plate, the Transport System places a high priority on finding and recognizing of license plates. The news is constantly reporting on accidents and missing cars. Authorities must acknowledge all of these unlawful acts. As a result, research into the identification and recognition of vehicle number plates is ongoing. However, identifying a vehicle's number plate has always been difficult for a number of reasons, such as brightness changes, shadows cast by moving vehicles, erratic license plate character types, different plate styles, and color effects caused by the surroundings. In this system, Number plate of vehicle is detected from a live video or an image. There is image preprocessing and segmentation done on the live video or number plate image. deep learning model methods are used, the characters from it are separated and then each character gets recognized. This helps to collect the vehicle overall project then the capabilities of different techniques into one integrated automatic system are summarized. This kind of systems can be implemented on the roadside and makes a real time comparison between passing car and list of stolen cars. This detected license plate number could also be used in car parking systems. PUC which stands for Pollution Under Control, where emission levels of vehicles and the regular renovation of the PUC certificate is done or not is verified and the details are shown. This will help in keeping an overall check on vehicles and the task which most of the places do manually to check the PUC certificate for checking status, can be verified quickly and the fine can be implemented as per so. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of Malarial Parasites Infection by using deep learning based on Medical image processing Logic

Experimental Analysis of Malarial Parasites Infection by usi...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： N Meenakshisundaram Sajiv G Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Science (SIMATS) Saveetha University Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Malaria remains a significant global health challenge, particularly in resource-limited regions, necessitating accurate and rapid diagnostic tools. This study introduces deepMalariaNet, a deep learning model developed for detecting and classifying malarial parasites using the “Malaria Parasite image - Malaria Species” dataset from Kaggle. The model employs Residual Attention Mechanisms and Parallel Convolutional Stacks (PCS) to improve diagnostic accuracy by focusing on critical image regions and capturing multi-scale features. Experimental results demonstrate that deepMalariaNet achieves 98.5% accuracy for binary classification (infected vs. non-infected) and 95.2% for multiclass classification (species identification). The model's robustness is validated through 10-fold cross-validation and ablation studies, and it outperforms state-of-the-art models such as ResNet-50 and DenseNet-121 in both accuracy and inference time. deepMalariaNet shows significant promise for real-time malaria detection in clinical settings, contributing to early and accurate diagnosis, which is crucial for effective malaria control and treatment.

关键词： deep learning Accuracy Attention mechanisms Malaria Parasitic diseases Sensitivity and specificity Metadata Robustness real-time systems Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

deep learning-based image processing framework for efficient surface litter detection in Computer Vision applications

引用

JOURNAL OF RADIATION RESEARCH AND APPLIED SCIENCES 2025年第2期18卷

作者： Shad, Ifza Zhang, Zuping Asim, Muhammad Al-Habib, Mohammed Chelloug, Samia Allaoua Abd El-Latif, Ahmed Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Prince Sultan Univ Coll Comp & Informat Sci EIAS Data Sci Lab Riyadh 11586 Saudi Arabia Prince Sultan Univ Ctr Excellence Quantum & Intelligent Comp Riyadh 11586 Saudi Arabia Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Technol POB 84428 Riyadh 11671 Saudi Arabia Menoufia Univ Fac Sci Dept Math & Comp Sci Shibin Al Kawm 32511 Egypt

Computer vision plays a vital role in automating environmental analysis by enabling real-time object detection and classification in diverse conditions. Litter pollution poses significant health and environmental risks due to inefficient disposal, and manual oversight is labor intensive. Effective litter detection is crucial for large-scale environmental monitoring. However, existing models face challenges such as the complexity of detecting shadowy objects in varying lighting conditions (e.g., during rain or under sun rays), difficulty in recognizing small objects, low accuracy, and poor real-time performance. Existing two-stage detectors, such as Faster R-CNN, also struggle with these issues. This paper introduces an automated deep learning-based image processing approach for accurate litter detection across different locations, using an enhanced version of YOLOv9s called LD-YOLOv9s. Key improvements in this novel approach include replacing convolutional layers with DynConvLayer in the backbone, integrating an SDConv-ADown module to substitute down-sampling layers in the neck, and using MPD-IoU instead of CIoU. These modifications reduce the chances of overlooking small objects, such as caps or lids, which had the least class meaning in the dataset, achieving a mAP of 78.3% with an inference time of 6.7ms. A significant contribution of this work is the LD-2024 dataset, curated from indoor and outdoor environments with manually annotated images. Performance comparisons were made with several YOLO versions (YOLOv3, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv9 variants) and traditional object detectors (Faster R-CNN, Center Net, Retina Net, Cascade R-CNN). Ablation studies validate the effectiveness of LD-YOLOv9s, which outperforms conventional methods, achieving a 6.3% improvement in mean average precision (mAP) over YOLOv9s on the LD-2024 dataset.

关键词： deep learning Computer vision image processing Litter Detection YOLO DynConvLayer SDConv MPD-IoU LD-YOLOv9s Object Detection

来源：评论

学校读者我要写书评

暂无评论

Lane detection using the concept of deep learning and Digital image processing

Lane detection using the concept of Deep learning and Digita...

引用

Electrical Electronics and Computing Technologies (ICEECT), International Conference on

作者： Shashi Kant Ojha Abhishek Kumar Sandeep Kumar CSE Department Sharda University Greater Noida

ISBN: (数字)9798350378092

ISBN: (纸本)9798350378108

Lane detection technology plays a pivotal role in enabling autonomous navigation in vehicles. However, existing systems primarily cater to well-structured roads with clear lane markings, rendering them ineffective in scenarios where markings are unclear or absent. This study critically evaluates an existing approach for detecting lanes on unmarked roads, followed by the proposal of an enhanced methodology. Both approaches leverage digital image processing techniques and rely solely on vision or camera data. The primary objective is to derive real-time curvature values to facilitate driver-assistance systems in making necessary turns and preventing vehicles from veering off-road.

关键词： deep learning Computers Lane detection Navigation Roads Digital images Rendering (computer graphics) Cameras real-time systems Proposals

来源：评论

学校读者我要写书评

暂无评论

Automated bank cheque verification using image processing and deep learning methods

引用

MULtimeDIA TOOLS AND APPLICATIONS 2021年第4期80卷 5319-5350页

作者： Agrawal, Prateek Chaudhary, deepak Madaan, Vishu Zabrovskiy, Anatoliy Prodan, Radu Kimovski, Dragi Timmerer, Christian Univ Klagenfurt Klagenfurt Austria Lovely Profess Univ Phagwara India Petrozavodsk State Univ Petrozavodsk Russia Bitmovin Inc San Francisco CA USA

Automated bank cheque verification using image processing is an attempt to complement the present cheque truncation system, as well as to provide an alternate methodology for the processing of bank cheques with minimal human intervention. When it comes to the clearance of the bank cheques and monetary transactions, this should not only be reliable and robust but also save time which is one of the major factor for the countries having large population. In order to perform the task of cheque verification, we developed a tool which acquires the cheque leaflet key components, essential for the task of cheque clearance using image processing and deep learning methods. These components include the bank branch code, cheque number, legal as well as courtesy amount, account number, and signature patterns. our innovation aims at benefiting the banking system by re-innovating the other competent cheque-based monetary transaction system which requires automated system intervention. For this research, we used institute of development and research in banking technology (IDRBT) cheque dataset and deep learning based convolutional neural networks (CNN) which gave us an accuracy of 99.14% for handwritten numeric character recognition. It resulted in improved accuracy and precise assessment of the handwritten components of bank cheque. For machine printed script, we used MATLAB in-built OCR method and the accuracy achieved is satisfactory (97.7%) also for verification of Signature we have used Scale Invariant Feature Transform (SIFT) for extraction of features and Support Vector Machine (SVM) as classifier, the accuracy achieved for signature verification is 98.10%.

关键词： Cheque truncation system image segmentation Bank cheque clearance image feature extraction Convolution neural network Support vector machine Scale invariant feature transform

来源：评论

学校读者我要写书评

暂无评论

Enhancing Palm Recognition Accuracy Through image processing deep learning Techniques

Enhancing Palm Recognition Accuracy Through Image Processing...

引用

Data Science and Network Security (ICDSNS), International Conference on

作者： J. Sheela Mercy S. Silvia Priscila Department of Computer Applications Bharath Institute of Higher Education and Research Chennai India Department of Computer Science Bharath Institute of Higher Education and Research Chennai India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

Palm recognition systems play an important role in biometric authentication; however, existing systems frequently have low accuracy and resiliency due to problems such as changing lighting conditions, occlusions, and hand orientations. The paper describes a novel way to improve palm recognition accuracy by combining modern image processing and deep learning approaches. Unlike traditional systems that utilize handcrafted features and shallow learning algorithms, the proposed system uses convolutional neural networks (CNNs) for feature extraction and classification, as well as advanced image preprocessing techniques. The technology preprocesses palm images to increase quality and consistency, thereby reducing the impact of environmental factors. Cross-validation trials yielded consistent results, with an average accuracy of 95%, precision of 92%, recall of 96%, and Fl-score of 94%. Furthermore, computational efficiency comparisons reveal that the proposed system beats existing ones in terms of training time, inference time, and model size, indicating that it is a promising option for accurate and efficient palm recognition in a variety of real-world applications.

关键词： Training deep learning Accuracy image recognition Computational modeling Lighting Biometric authentication

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：