检索结果-内蒙古大学图书馆

Automatic Detection of Threat Objects in X-ray Baggage Inspection Using mask region-based convolutional neural network and Deformable convolutional network

引用

RUSSIAN JOURNAL OF NONDESTRUCTIVE TESTING 2022年第12期58卷 1175-1184页

作者： Kim, Jongchol Ri, Jinmyong Jo, Hyok Univ Sci Dept Control Sci Pyongyang 999093 North Korea

In X-ray baggage inspection, due to the increase in the types of dangerous goods and the composition of the baggage contents, it is not suitable to clearly display various baggage and dangerous goods on the image acquired by the X-ray inspection system. In recent years, many deep learning-based object detection and recognition technologies have appeared, and object detection algorithms are also developing at a rapid pace along with the development of deep learning technologies. Object detection models commonly use convolution networks to process input values, but the convolution network has a problem of using a common filter regardless of the size of the object. This study aims to improve the accuracy of the threat objects detection algorithm in X-ray baggage images by applying deformable convolutional networks that make filters corresponding to objects using offsets. The proposed method was applied to mask R-CNN(mask region based convolutional neural network) using GDXray and SIXray, which are X-ray security inspection image data sets, and the experimental results show that the proposed model performance can be improved compared to the existing algorithms.

关键词： object classification and detection mask region-based convolutional neural network X-ray baggage inspection object detection deformable convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network

引用

JOURNAL OF BIOMEDICAL OPTICS 2020年第11期25卷 116502页

作者： Lin, Yang-Hsien Liao, Ken Y-K Sung, Kung-Bin Natl Taiwan Univ Grad Inst Biomed Elect & Bioinformat Taipei Taiwan Feng Chia Univ Coll Informat & Elect Engn Taichung Taiwan Natl Taiwan Univ Dept Elect Engn Taipei Taiwan Natl Taiwan Univ Mol Imaging Ctr Taipei Taiwan

Significance: Label-free quantitative phase imaging is a promising technique for the automatic detection of abnormal red blood cells (RBCs) in real time. Although deep-learning techniques can accurately detect abnormal RBCs from quantitative phase images efficiently, their applications in diagnostic testing are limited by the lack of transparency. More interpretable results such as morphological and biochemical characteristics of individual RBCs are highly desirable. Aim: An end-to-end deep-learning model was developed to efficiently discriminate thalassemic RBCs (tRBCs) from healthy RBCs (hRBCs) in quantitative phase images and segment RBCs for single-cell characterization. Approach: Two-dimensional quantitative phase images of hRBCs and tRBCs were acquired using digital holographic microscopy. A mask region-based convolutional neural network (mask R-CNN) model was trained to discriminate tRBCs and segment individual RBCs. Characterization of tRBCs was achieved utilizing SHapley Additive exPlanation analysis and canonical correlation analysis on automatically segmented RBC phase images. Results: The implemented model achieved 97.8% accuracy in detecting tRBCs. Phase-shift statistics showed the highest influence on the correct classification of tRBCs. Associations between the phase-shift features and three-dimensional morphological features were revealed. Conclusions: The implemented mask R-CNN model accurately identified tRBCs and segmented RBCs to provide single-RBC characterization, which has the potential to aid clinical decision-making. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License.

关键词： digital holographic microscopy quantitative phase imaging red blood cell thalassemia mask region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

POC-net: pelican optimization-based convolutional neural network for recognizing large pose variation from video

引用

neural COMPUTING & APPLICATIONS 2023年第34期35卷 24091-24107页

作者： Jayabharathi, P. Suresh, A. SRM Inst Sci & Technol Sch Comp Dept Networking & Commun Chennai 603203 Tamil Nadu India SRM Inst Sci & Technol Fac Engn & Technol Sch Comp Dept Networking & Commun Chennai 603203 Tamil Nadu India

Nowadays, face recognition using video surveillance systems becomes one of the active research topics in security domains. Security plays a significant role in everyday life for secure and sustainable developments of smart cities. The conventional techniques provide efficient recognition results only when the faces are captured with complete face images. However, they suffer to handle large pose variation images extracted from video sequences. Therefore, to deal with this issue, this paper specially designed a multidimensional face recognition model to recognize faces under multiple pose variations and angles. Three face video databases, namely facesurv database, IARPA Janus benchmark database and McGill database, are utilized for experimental evaluation. The videos of these three databases are converted into number of image frames through background subtraction process. From the image frames, the large pose variation images with different angles are identified and selected to process further. The video recorded under dynamic environment conditions diminishes recognition performance, so the image frames are processed through several preprocessing pipelines. The preprocessed images are then fed into the proposed optimal mask region-based convolutional neural network with modified short-term memory (OMRCNN-MBiLSTM) model, which learns the facial patterns present in the images more efficiently. The feature vectors learned by the proposed classifier are matched with the input face database to determine the identity of the person. With the ability to handle multiview and large pose variations, the proposed model accurately recognizes faces. The simulation result manifests the superiority of proposed model over other existing methods.

关键词： Face recognition Pose variation mask region-based convolutional neural network Bidirectional long short-term memory Pelican optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Character Recognition of Multi-Style Vehicle License Plates

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 23卷 3768-3777页

作者： Huang, Qiuying Cai, Zhanchuan Lan, Ting Macau Univ Sci & Technol Fac Informat Technol Macau 999078 Peoples R China Beijing Normal Univ Sch Informat Technol Zhuhai Peoples R China

The recognition of vehicle license plate is an important part of the modern intelligent traffic management system, which has been widely used in many fields. On the Hong Kong-Zhuhai-Macao Bridge, the vehicles may have multiple license plates (LPs) with three different styles, and the traditional contour-based vehicle license plate recognition methods cause a considerable miss rate for multi-style license plates. With such a background, this paper proposes a multi-style license plate recognition method based on feature pyramid network with instance segmentation, which translates the license plate recognition into object instance detection and gets rid of the steps of segmentation and optical character recognition of traditional methods. In the scheme, we design a novel license plate recognition network to precisely locate and classify characters and LP regions concurrently, wherein an assembly layer is added for combining the characters into license plates and outputting license plate strings. The experimental results show that the proposed method achieves 98.57% recognition rate of multi-style LPs on the real world applications. Moreover, we also select the standard license plate datasets, that only contain single style license plates, to test the proposed license plate recognition method, and the corresponding results show that the proposed method achieves competitive performance.

关键词： Licenses Optical character recognition software Character recognition Feature extraction Proposals Task analysis Bridges Hong Kong-Zhuhai-Macao Bridge license plate recognition feature pyramid network mask region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A Fast Object Detection-based Framework for Via Modeling on PCB X-Ray CT Images

引用

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS 2023年第4期19卷 1-20页

作者： Koblah, David Selasi Botero, Ulbert J. Costello, Sean P. Dizon-Paradis, Olivia P. Ganji, Fatemeh Woodard, Damon L. Forte, Domenic Univ Florida Elect & Comp Engn Gainesville FL 32611 USA Worcester Polytech Inst Elect & Comp Engn Worcester MA USA

For successful printed circuit board (PCB) reverse engineering (RE), the resulting device must retain the physical characteristics and functionality of the original. Although the applications of RE are within the discretion of the executing party, establishing a viable, non-destructive framework for analysis is vital for any stakeholder in the PCB industry. A widely regarded approach in PCB RE uses non-destructive x-ray computed tomography (CT) to produce three-dimensional volumes with several slices of data corresponding to multi-layered PCBs. However, the noise sources specific to x-ray CT and variability fromdesigners hampers the thorough acquisition of features necessary for successful RE. This article investigates a deep learning approach as a successor to the current state-of-the-art for detecting vias on PCB x-ray CT images;vias are a key building block of PCB designs. During RE, vias offer an understanding of the PCB's electrical connections across multiple layers. Our method is an improvement on an earlier iteration which demonstrates significantly faster runtime with quality of results comparable to or better than the current state-of-the-art, unsupervised iterative Hough-based method. Compared with the Hough-based method, the current framework is 4.5 times faster for the discrete image scenario and 24.1 times faster for the volumetric image scenario. The upgrades to the prior deep learning version include faster feature-based detection for real-world usability and adaptive post-processing methods to improve the quality of detections.

关键词： Clustering deep learning mask region-based convolutional neural network printed circuit board radial template transfer learning x-ray computed tomography

来源：评论

学校读者我要写书评

暂无评论

Correlation of choroidal thickness with age in healthy subjects: automatic detection and segmentation using a deep learning model

引用

INTERNATIONAL OPHTHALMOLOGY 2022年第10期42卷 3061-3070页

作者： Lin, Chen Yu Huang, Yu Len Hsia, Wei Ping Wang, Yang Chang, Chia Jen Taichung Vet Gen Hosp Dept Ophthalmol 1650Sec 4Taiwan Blvd Taichung Taiwan Tunghai Univ Dept Comp Sci Taichung Taiwan Cent Taiwan Univ Sci & Technol Dept Optometry Taichung Taiwan

Propose The proposed deep learning model with a mask region-based convolutional neural network (mask R-CNN) can predict choroidal thickness automatically. Changes in choroidal thickness with age can be detected with manual measurements. In this study, we aimed to investigate choroidal thickness in a comprehensive aspect in healthy eyes by utilizing the mask R-CNN model. Methods A total of 68 eyes from 57 participants without significant ocular disease were recruited. The participants were allocated to one of three groups according to their age and underwent spectral domain optical coherence tomography (SD-OCT) or enhanced depth imaging OCT (EDI-OCT) centered on the fovea. Each OCT sequence included 25 slices. Physicians labeled the choroidal contours in all the OCT sequences. We applied the mask R-CNN model for automatic segmentation. Comparisons of choroidal thicknesses were conducted according to age and prediction accuracy. Results Older age groups had thinner choroids, according to the automatic segmentation results;the mean choroidal thickness was 253.7 +/- 41.9 mu m in the youngest group, 206.8 +/- 35.4 mu m in the middle-aged group, and 152.5 +/- 45.7 mu m in the oldest group (p < 0.01). Measurements obtained using physician sketches demonstrated similar trends. We observed a significant negative correlation between choroidal thickness and age (p < 0.01). The prediction error was lower and less variable in choroids that were thinner than the cutoff point of 280 mu m. Conclusion By observing choroid layer continuously and comprehensively. We found that the mean choroidal thickness decreased with age in healthy subjects. The mask R-CNN model can accurately predict choroidal thickness, especially choroids thinner than 280 mu m. This model can enable exploring larger and more varied choroid datasets comprehensively, automatically, and conveniently.

关键词： Deep learning mask region-based convolutional neural network Optical coherence tomography Choroidal thickness Automatic segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced mask-RCNN for Ship Detection and Segmentation 1

引用

2nd International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS)

作者： Rakhi, Anusree Mondal Dhorajiya, Arya P. Saranya, P. SRM Inst Sci & Technol Dept Comp Technol Chennai Tamil Nadu India

ISBN: (数字)9789811925412

ISBN: (纸本)9789811925412;9789811925405

Ship detection and segmentation using satellite remote sensing imagery have become a hot issue in the scientific community. This sector helps control maritime violence, illegal fishing, and cargo transportation. Most available methods used for detecting ships perform object detection but don't perform semantic segmentation. Besides, previous papers had various flaws, such as the inability to detect small ships, greater false positives, and severe noise in the given Synthetic Aperture Radar (SAR) images, which affects low-level feature learning in shallow layers and makes object detection more difficult. The intricacies of SAR images also significantly reduce the benefits of convolutional neural networks (CNNs). Then there are a few models that can't tell the difference between things that appear to be ships. Furthermore, some existing models performed somewhat worse than other state-of-the-art given and successful frameworks. The cost of computing resources is higher for some models. This research provides a ship detection approach based on an improved mask region-based convolutional neural networks (mask RCNN). At the pixel level, the proposed approach can detect and segment ships. For object detection and segmentation, mask RCNN comprises two parts. In the segmentation part, more convolutional Layers are added, and hyperparameters are changed to improve the overall output. Because of these changes, the proposed model can work more accurately than existing models. Using this mentioned method on the Airbus Ship Detection dataset on Kaggle, we achieved an accuracy of 82.9% on the proposed model.

关键词： Bounding box convolutional neural networks Fully convolutional network mask region-based convolutional neural network regional proposal network Remote sensing images Semantic segmentation Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Gender Identification Using 2D Ear Biometric

Gender Identification Using 2D Ear Biometric

引用

Computing Conference

作者： Srinivasan, Lavanya Univ West London London England

ISBN: (纸本)9783031622717;9783031622694;9783031622687

Due to the advancement of technologies, organizations, and governments increasingly rely on digital technologies to validate a person's identity for secure interactions and to provide services for digital access control. Critical transactions require accurate and reliable authentication and verification of a person to prevent fraud. The most reliable and secure digital technology is biometrics. In this work, we are analyzing ear biometrics. Previous studies in biometrics have shown that gender can be recognized by face and voice. In this paper, ear biometrics are used to recognize and identify genders. Machine learning and deep learning are explored for gender identification. mask RCNN and Grabcut segmentation techniques are used for ear detection, and features are extracted from Histogram-Oriented Gradient and Gabor filters and classified by gender using machine learning and deep learning techniques. The machine and deep network models achieved recognition rates of 81.48% and 87.52% for the EarVN1.0 dataset, respectively. The proposed automated system is useful to recognize people using ear biometrics.

关键词： mask region-based convolutional neural network Histogram Oriented Gradient Gabor GrabCut

来源：评论

学校读者我要写书评

暂无评论

A novel model for eliminating overlapping issues in 3D object recognition using dove swarm optimization based light GBM

引用

International Journal of Information Technology (Singapore) 2023年第5期15卷 2387-2393页

作者： Rajendran, Ramana Murugan, B.S. Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu Srivilliputhur India

This paper proposes a novel modified light gradient boosting machine-based Dove swarm optimization (MLGBM-DSO) model for the accurate recognition of 3D objects. To evaluate the performance, the proposed MLGBM-DSO model utilizes 3D shape CAD images from the ModelNet dataset as input. The 3D shape images are initially preprocessed through data screening and normalization tasks to produce structured data for the proposed classifier. The preprocessed data is provided to the proposed MLGBM-DSO model that effectively extracts and classifies the 3D object images into distinct categories. Here, the modified gradient boosting machine (GBM) is formed by the integration of a mask region-based convolutional neural network (mask RCNN) and light GBM model. To achieve enhanced object recognition accuracy and the overlapping issues that occur during classification are mitigated by using the dove swarm optimization (DSO) algorithm. The efficiency of the proposed MLGBM-DSO model is evaluated using different evaluation indicators such as accuracy, specificity, recall, intersection over union (IoU), precision, and F1-score. The experimental result inherits that the proposed MLGBM-DSO model achieves higher 3D object recognition accuracy of about 97.2%. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： 3D object recognition Accuracy Dove swarm optimization algorithm Light gradient boosting machine mask region-based convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Monitoring Plants Growth in Indoor Vertical Farms Using Computer Vision and AI Techniques

Monitoring Plants Growth in Indoor Vertical Farms Using Comp...

引用

作者： Pillutla, Bhama Krishna Northern Illinois University

学位级别：M.S., Master of Science/Master of Surgery

Climatic conditions like temperature, drought, and heavy metals disturb plant cell structures and, ultimately, plant growth that significantly affects crop production. Due to increasing climate change, maize crop yields are projected to decline by 24% by the end of century. With the increase in food demands and decrease in agricultural land and water resources, the space for effective farming is left much desired. Though limited to a few crops at this moment, Indoor Vertical Farming is one technique that requires much less land space, water, soil, and sunlight when compared to traditional farming. Vertical farming allows artificial control of temperature, light, humidity, water, and gases that make food production indoors possible. Apart from providing an optimal growing environment, tracking crop growth efficiently and automatically is where Indoor Vertical Farming thrives, which will be the focus of this thesis. Growth tracking mechanisms in traditional agricultural practices are typically labor-intensive, hazardous, and may involve destructive practices in certain crop types, and becomes incrementally difficult with micro-greens such as basil and parsley. However, with the technological advancements in Computer Vision and AI techniques, automatically tracking crop growth in much greater detail is much more achievable. This study focuses on designing AI and vision enabled system to track the growth of sweet basil plants, a popular crop cultivated globally. We developed an algorithm leveraging the object segmentation model (mask R-CNN) to detect and segment individual plants’ leaves from the images to compute their area to track growth. We further employed a series of techniques to overcome unforeseen challenges related to continuous growth tracking of the crop.

关键词： Computer vision Deep learning Growth monitoring Leaf segmentation mask region-based convolutional neural network

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：